Movatterモバイル変換


[0]ホーム

URL:


CN110766760B - Method, device, equipment and storage medium for camera calibration - Google Patents

Method, device, equipment and storage medium for camera calibration
Download PDF

Info

Publication number
CN110766760B
CN110766760BCN201911001867.8ACN201911001867ACN110766760BCN 110766760 BCN110766760 BCN 110766760BCN 201911001867 ACN201911001867 ACN 201911001867ACN 110766760 BCN110766760 BCN 110766760B
Authority
CN
China
Prior art keywords
points
extrinsic
extrinsic parameter
camera
parameter
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911001867.8A
Other languages
Chinese (zh)
Other versions
CN110766760A (en
Inventor
时一峰
贾金让
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co LtdfiledCriticalBeijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201911001867.8ApriorityCriticalpatent/CN110766760B/en
Publication of CN110766760ApublicationCriticalpatent/CN110766760A/en
Application grantedgrantedCritical
Publication of CN110766760BpublicationCriticalpatent/CN110766760B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Images

Classifications

Landscapes

Abstract

Translated fromChinese

本公开的实施例提供了用于相机标定的方法、装置、设备和计算机可读存储介质,涉及自动驾驶领域。该方法包括:确定相机的第一外参数,第一外参数指示相机坐标系与世界坐标系的转换关系;获取相机的第二外参数,第二外参数基于相机先前捕获的第二图像而被确定;基于第二外参数和位置信息,从第一图像中确定第三点集合;以及基于第一点集合、第二点集合以及第三点集合,从第一外参数和第二外参数中确定与第一图像相对应的外参数。由此,可以使得标定的外参数更为平滑。

Figure 201911001867

Embodiments of the present disclosure provide a method, apparatus, device, and computer-readable storage medium for camera calibration, and relate to the field of automatic driving. The method includes: determining a first extrinsic parameter of the camera, the first extrinsic parameter indicating the transformation relationship between the camera coordinate system and the world coordinate system; acquiring a second extrinsic parameter of the camera, the second extrinsic parameter is based on a second image previously captured by the camera. determining; based on the second extrinsic parameter and the position information, determining a third set of points from the first image; and based on the first set of points, the second set of points, and the third set of points, from the first extrinsic parameter and the second extrinsic parameter Extrinsic parameters corresponding to the first image are determined. Thus, the calibrated extrinsic parameters can be made smoother.

Figure 201911001867

Description

Translated fromChinese
用于相机标定的方法、装置、设备和存储介质Method, apparatus, device and storage medium for camera calibration

技术领域technical field

本公开的实施例主要涉及计算机技术领域,可用于自动驾驶,并且更具体地,涉及用于相机标定的方法、装置、设备以及计算机可读存储介质。Embodiments of the present disclosure mainly relate to the field of computer technology, which can be used for automatic driving, and more particularly, to a method, apparatus, device, and computer-readable storage medium for camera calibration.

背景技术Background technique

近年来,自动驾驶技术的发展越来越迅速。自动驾驶技术的基础是对车辆周围环境的感知,即识别周围环境的具体状况。已经提出,除了利用车载的传感器装置(例如,车载激光雷达或者车载相机)进行环境感知之外,还可以通过车外的传感器装置(例如,安装在路侧的相机)来获取车辆的环境信息,以更好地支持自动驾驶技术。然而,由于某些原因,安装在路侧的相机的安装位置可能相对于初始安装位置出现抖动,进而影响例如基于路侧相机所捕获的图像数据所确定的车辆或障碍物的位置的准确性。这种位置的误差对于自动驾驶可能是无法接受的。In recent years, autonomous driving technology has developed rapidly. The basis of autonomous driving technology is the perception of the surrounding environment of the vehicle, that is, to identify the specific conditions of the surrounding environment. It has been proposed that, in addition to using on-board sensor devices (for example, on-board lidar or on-board cameras) for environmental perception, it is also possible to obtain vehicle environmental information through external sensor devices (for example, cameras installed on the roadside), to better support autonomous driving technology. However, for some reason, the installation position of the roadside-mounted camera may shake relative to the original installation position, which affects the accuracy of the position of the vehicle or obstacle determined based on image data captured by the roadside camera, for example. This error in position may be unacceptable for autonomous driving.

发明内容SUMMARY OF THE INVENTION

根据本公开的实施例,提供了一种用于相机标定的方案。According to an embodiment of the present disclosure, a solution for camera calibration is provided.

在本公开的第一方面中,提供了一种用于相机标定的方法。该方法包括:基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和第一图像中基于参考线在三维地图中的位置信息确定的第二点集合,确定相机的第一外参数,第一外参数指示相机坐标系与世界坐标系的转换关系;获取相机的第二外参数,第二外参数基于相机先前捕获的第二图像而被确定;基于第二外参数和位置信息,从第一图像中确定第三点集合;以及基于第一点集合、第二点集合以及第三点集合,从第一外参数和第二外参数中确定与第一图像相对应的外参数。In a first aspect of the present disclosure, a method for camera calibration is provided. The method includes: based on determining a first set of points corresponding to a predetermined reference line from a first image captured by a camera and a second set of points in the first image determined based on position information of the reference line in a three-dimensional map, determining The first extrinsic parameter of the camera, the first extrinsic parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system; the second extrinsic parameter of the camera is obtained, and the second extrinsic parameter is determined based on the second image previously captured by the camera; based on the second Extrinsic parameters and position information, determining a third point set from the first image; and determining a correlation with the first image from the first extrinsic parameter and the second extrinsic parameter based on the first point set, the second point set, and the third point set the corresponding external parameters.

在本公开的第二方面中,提供了一种用于相机标定的装置。该装置包括:第一外参数确定模块,被配置为基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和第一图像中基于参考线在三维地图中的位置信息确定的第二点集合,确定相机的第一外参数,第一外参数指示相机坐标系与世界坐标系的转换关系;第一外参数获取模块,被配置为获取相机的第二外参数,第二外参数基于相机先前捕获的第二图像而被确定;外参数选择模块,被配置为基于第二外参数和位置信息,从第一图像中确定第三点集合;以及基于第一点集合、第二点集合以及第三点集合,从第一外参数和第二外参数中确定与第一图像相对应的外参数。In a second aspect of the present disclosure, an apparatus for camera calibration is provided. The device includes: a first extrinsic parameter determination module configured to determine a first set of points corresponding to a predetermined reference line from a first image captured by the camera and a first image based on the reference line in the three-dimensional map The second set of points determined by the position information determines the first external parameter of the camera, and the first external parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system; the first external parameter acquisition module is configured to acquire the second external parameter of the camera , the second extrinsic parameter is determined based on the second image previously captured by the camera; the extrinsic parameter selection module is configured to determine a third set of points from the first image based on the second extrinsic parameter and the position information; and based on the first point The set, the second set of points, and the third set of points determine the extrinsic parameter corresponding to the first image from the first extrinsic parameter and the second extrinsic parameter.

在本公开的第三方面中,提供了一种电子设备,包括一个或多个处理器;以及存储装置,用于存储一个或多个程序,当一个或多个程序被一个或多个处理器执行,使得一个或多个处理器实现根据本公开的第一方面的方法。In a third aspect of the present disclosure, there is provided an electronic device comprising one or more processors; and storage means for storing one or more programs, when the one or more programs are executed by the one or more processors Executing causes the one or more processors to implement the method according to the first aspect of the present disclosure.

在本公开的第四方面中,提供了一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现根据本公开的第一方面的方法。In a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method according to the first aspect of the present disclosure.

应当理解,发明内容部分中所描述的内容并非旨在限定本公开的实施例的关键或重要特征,亦非用于限制本公开的范围。本公开的其它特征将通过以下的描述变得容易理解。It should be understood that the matters described in this Summary are not intended to limit key or critical features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

附图说明Description of drawings

结合附图并参考以下详细说明,本公开各实施例的上述和其他特征、优点及方面将变得更加明显。在附图中,相同或相似的附图标注表示相同或相似的元素,其中:The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent when taken in conjunction with the accompanying drawings and with reference to the following detailed description. In the drawings, the same or similar reference numbers refer to the same or similar elements, wherein:

图1示出了本公开的多个实施例能够在其中实现的示例环境的示意图;1 shows a schematic diagram of an example environment in which various embodiments of the present disclosure can be implemented;

图2示出了根据本公开的一些实施例的用于相机标定的方法的流程图;FIG. 2 shows a flowchart of a method for camera calibration according to some embodiments of the present disclosure;

图3示出了根据本公开的一些实施例的用于确定第一点集合的示例方法的流程图;3 illustrates a flowchart of an example method for determining a first set of points in accordance with some embodiments of the present disclosure;

图4示出了将三维坐标点投影到第一图像的示意图;FIG. 4 shows a schematic diagram of projecting three-dimensional coordinate points to the first image;

图5示出了根据本公开的一些实施例的用于确定相机的第一外参数的示例方法的流程图;5 illustrates a flowchart of an example method for determining a first extrinsic parameter of a camera according to some embodiments of the present disclosure;

图6示出了根据本公开的一些实施例的确定与第一图像对应的外参数的示例方法的流程图;6 illustrates a flowchart of an example method of determining extrinsic parameters corresponding to a first image, according to some embodiments of the present disclosure;

图7示出了根据本公开的一些实施例的更新外参数的示例方法的流程图;7 shows a flowchart of an example method of updating extrinsic parameters according to some embodiments of the present disclosure;

图8示出了根据本公开的另一些实施例的更新外参数的示例方法的流程图;8 shows a flowchart of an example method of updating extrinsic parameters according to other embodiments of the present disclosure;

图9示出了根据本公开的一些实施例的用于确定相机的外参数的装置的示意性结构框图;以及FIG. 9 shows a schematic structural block diagram of an apparatus for determining extrinsic parameters of a camera according to some embodiments of the present disclosure; and

图10示出了能够实施本公开的多个实施例的计算设备的框图。10 illustrates a block diagram of a computing device capable of implementing various embodiments of the present disclosure.

具体实施方式Detailed ways

下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例,然而应当理解的是,本公开可以通过各种形式来实现,而且不应该被解释为限于这里阐述的实施例,相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是,本公开的附图及实施例仅用于示例性作用,并非用于限制本公开的保护范围。Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for the purpose of A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the protection scope of the present disclosure.

在本公开的实施例的描述中,术语“包括”及其类似用语应当理解为开放性包含,即“包括但不限于”。术语“基于”应当理解为“至少部分地基于”。术语“一个实施例”或“该实施例”应当理解为“至少一个实施例”。术语“第一”、“第二”等等可以指代不同的或相同的对象。下文还可能包括其他明确的和隐含的定义。In the description of embodiments of the present disclosure, the term "comprising" and the like should be understood as open-ended inclusion, ie, "including but not limited to". The term "based on" should be understood as "based at least in part on". The terms "one embodiment" or "the embodiment" should be understood to mean "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

如本文中使用的,术语“相机的外参数”例如可以是在相机坐标系与世界坐标系之间进行转换所需要的参数,例如平移矩阵、旋转矩阵,等等。术语“相机的内参数”例如可以是在图像坐标系和/或像素坐标系与相机坐标系之间进行转换所需要的参数,例如平移矩阵、旋转矩阵,等等。“标定相机的外参数”可以是指对相机坐标系与世界坐标系之间的转换参数的确定。As used herein, the term "extrinsic parameters of the camera" may be, for example, parameters required to convert between the camera coordinate system and the world coordinate system, such as translation matrices, rotation matrices, and the like. The term "intrinsic parameters of the camera" may be, for example, parameters required to convert between an image coordinate system and/or a pixel coordinate system and a camera coordinate system, such as translation matrices, rotation matrices, and the like. "Calibrating the extrinsic parameters of the camera" may refer to the determination of conversion parameters between the camera coordinate system and the world coordinate system.

在本公开的上下文中,世界坐标系可以是指覆盖全球范围的参考坐标系统,其例如可以用于辅助车辆的自动驾驶或自主停车等,其示例包括UTM坐标系统、经纬度坐标系统,等等。相机坐标系的原点可以位于成像设备的光心,竖轴(z轴)可以与成像设备的光轴重合,横轴(x轴)和纵轴(y轴)可以与成像平面平行。像素坐标系的原点可以在图像的左上角,横轴和纵轴可以分别为图像所在的像素行和像素列,单位可以为像素。图像坐标系的原点可以在图像的中心(即像素坐标系的中点),横轴和纵轴与像素坐标系平行,单位为可以毫米。但是,将理解,在其他的实施例中,这些坐标系也可以按照在本领域中所接受的其他合理的方式被定义。In the context of the present disclosure, the world coordinate system may refer to a reference coordinate system covering a global scope, which may be used, for example, to assist automatic driving or autonomous parking of vehicles, etc., examples of which include UTM coordinate systems, latitude and longitude coordinate systems, and the like. The origin of the camera coordinate system can be located at the optical center of the imaging device, the vertical axis (z axis) can be coincident with the optical axis of the imaging device, and the horizontal axis (x axis) and the vertical axis (y axis) can be parallel to the imaging plane. The origin of the pixel coordinate system can be the upper left corner of the image, the horizontal axis and the vertical axis can be the pixel row and pixel column where the image is located, respectively, and the unit can be pixels. The origin of the image coordinate system can be at the center of the image (ie, the midpoint of the pixel coordinate system), the horizontal and vertical axes are parallel to the pixel coordinate system, and the unit is millimeters. However, it will be appreciated that in other embodiments, these coordinate systems may also be defined in other reasonable manners accepted in the art.

根据本公开的各种实施例,提供了一种相机标定的方案。在本公开的实施例中,基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和第一图像中基于参考线在三维地图中的位置信息确定的第二点集合,确定相机的第一外参数,第一外参数指示相机坐标系与世界坐标系的转换关系;获取相机的第二外参数,第二外参数基于相机先前捕获的第二图像而被确定;基于第二外参数和位置信息,从第一图像中确定第三点集合;以及基于第一点集合、第二点集合以及第三点集合,从第一外参数和第二外参数中确定与第一图像相对应的外参数。由此,可以使得标定的外参数更为平滑According to various embodiments of the present disclosure, a solution for camera calibration is provided. In an embodiment of the present disclosure, based on a first set of points corresponding to a predetermined reference line determined from a first image captured by a camera and a second set of points determined based on position information of the reference line in the three-dimensional map in the first image Set of points, determine the first extrinsic parameter of the camera, the first extrinsic parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system; obtain the second extrinsic parameter of the camera, the second extrinsic parameter is determined based on the second image previously captured by the camera ; determine a third set of points from the first image based on the second extrinsic parameter and the position information; and determine from the first extrinsic parameter and the second extrinsic parameter based on the first set of points, the second set of points and the third set of points Extrinsic parameters corresponding to the first image. In this way, the calibrated external parameters can be made smoother

以下将参照附图来具体描述本公开的实施例。Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

图1示出了本公开的多个实施例能够在其中实现的示例环境100的示意图。在该示例环境100中示意性示出了一些典型物体,包括道路102、以及在道路102上行驶的车辆110。如图1所示,道路102例如包括停止标志线115-1和车道标志线115-2(单独或统一称为标志线115),此外,环境100中还包括用于感测道路102的环境信息的相机105。应当理解,这些示出的设施和物体仅是示例,根据实际情况,不同交通环境中存在可能出现的物体将会变化。本公开的范围在此方面不受限制。FIG. 1 shows a schematic diagram of anexample environment 100 in which various embodiments of the present disclosure can be implemented. Some typical objects are schematically shown in thisexample environment 100 , including aroad 102 , and avehicle 110 traveling on theroad 102 . As shown in FIG. 1 , theroad 102 includes, for example, a stop mark 115 - 1 and a lane mark 115 - 2 (referred to individually or collectively as the marks 115 ), and theenvironment 100 also includes environmental information for sensing theroad 102camera 105. It should be understood that the facilities and objects shown are only examples, and objects that may appear in different traffic environments will vary according to actual situations. The scope of the present disclosure is not limited in this regard.

车辆110可以是可以承载人和/或物并且通过发动机等动力系统移动的任何类型的车辆,包括但不限于轿车、卡车、巴士、电动车、摩托车、房车、火车等等。环境100中的一个或多个车辆110可以是具有一定自动驾驶能力的车辆,这样的车辆也被称为无人驾驶车辆。当然,环境100中的另外一个或一些车辆110还可以是不具有自动驾驶能力的车辆。Vehicle 110 may be any type of vehicle that can carry people and/or things and be moved by a power system such as an engine, including but not limited to cars, trucks, buses, electric vehicles, motorcycles, motorhomes, trains, and the like. One or more of thevehicles 110 in theenvironment 100 may be vehicles with certain autonomous driving capabilities, such vehicles are also referred to as unmanned vehicles. Of course, the other or some of thevehicles 110 in theenvironment 100 may also be vehicles that do not have autonomous driving capabilities.

在一些实施例中,相机105可以被布置在道路102的上方。在一些实施例中,相机105例如还可以被布置在道路102的两侧。如图1所示,相机105可以通信地耦合到计算设备120。虽然被示出为单独的实体,但计算设备120可以被嵌入在相机105中。计算设备120也可以是相机105外部的实体,并且可以经由无线网络与相机105通信。计算设备120可以被实现为一个或多个计算设备,其至少包含处理器、存储器以及其他通常存在于通用计算机中的组件,以便实现计算、存储、通信、控制等功能。In some embodiments, thecamera 105 may be positioned above theroad 102 . In some embodiments, thecameras 105 may also be arranged on both sides of theroad 102, for example. As shown in FIG. 1 ,camera 105 may be communicatively coupled to computingdevice 120 . Although shown as a separate entity,computing device 120 may be embedded incamera 105 .Computing device 120 may also be an entity external tocamera 105 and may communicate withcamera 105 via a wireless network.Computing device 120 may be implemented as one or more computing devices that include at least a processor, memory, and other components typically found in a general-purpose computer to perform computing, storage, communication, control, and other functions.

在一些实施例中,相机105可以获取与道路102相关的环境信息(例如,车道线信息、道路边界信息或障碍物信息),并将该环境信息发送至车辆110,以用于车辆110的行驶决策。在一些实施例中,相机105也可以基于相机的外参数和内参数以及所捕获的车辆110的图像,以确定车辆110的位置,并将该位置发送至车辆110,以实现车辆110的定位。能够看到,无论是获取准确的环境信息,还是确定准确的位置信息,确定相机准确的内参数及外参数都是必须的。In some embodiments, thecamera 105 may obtain environmental information (eg, lane line information, road boundary information, or obstacle information) related to theroad 102 and transmit the environmental information to thevehicle 110 for use in thevehicle 110 to travel decision making. In some embodiments, thecamera 105 may also determine the position of thevehicle 110 based on the extrinsic and intrinsic parameters of the camera and the captured image of thevehicle 110 and transmit the position to thevehicle 110 to enable the positioning of thevehicle 110 . It can be seen that whether it is to obtain accurate environmental information or to determine accurate location information, it is necessary to determine the accurate internal and external parameters of the camera.

以下将结合图2至图6来描述根据本公开的实施例的相机标定的过程。图2示出了根据本公开的实施例的用于相机标定的方法200的流程图。方法200例如可以由图1中所示的计算设备120来执行。The process of camera calibration according to an embodiment of the present disclosure will be described below with reference to FIGS. 2 to 6 . FIG. 2 shows a flowchart of amethod 200 for camera calibration according to an embodiment of the present disclosure.Method 200 may be performed, for example, by computingdevice 120 shown in FIG. 1 .

如图2所示,在框202,计算设备120基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和第一图像中基于参考线在三维地图中的位置信息确定的第二点集合,确定相机的第一外参数,其中第一外参数指示相机坐标系与世界坐标系的转换关系。As shown in FIG. 2, atblock 202, thecomputing device 120 is based on determining a first set of points corresponding to a predetermined reference line from a first image captured by the camera and a location in the first image based on the reference line in the three-dimensional map The second set of points determined by the information determines the first extrinsic parameter of the camera, wherein the first extrinsic parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system.

在一些实施例中,相机105可以实时获取周围环境的图像。计算设备120可以获取相机105当前拍摄的第一图像。计算设备120可以从由相机105所捕获的第一图像中确定与预定的参考线对应的第一点集合。在一些实施例中,参考线例如可以是环境中正交的两条线,例如图1中所示的道路102的车道标志线115-2和停止标志线115-1。在一些实施例中,参考线例如也可以是用于标定目的而在道路102上喷涂的特殊的标志线,例如一组或多组相交线。在一些实施例中,当已知至少两个特征点在世界坐标系和图像坐标系中的位置时,参考线也可以仅包括一条线。In some embodiments, thecamera 105 may acquire images of the surrounding environment in real time. Thecomputing device 120 may acquire the first image currently captured by thecamera 105 .Computing device 120 may determine a first set of points corresponding to a predetermined reference line from the first image captured bycamera 105 . In some embodiments, the reference line may be, for example, two lines that are orthogonal in the environment, such as the lane marking line 115-2 and the stop marking line 115-1 of theroad 102 shown in FIG. 1 . In some embodiments, the reference lines may also be, for example, special marking lines painted on theroad 102 for calibration purposes, such as one or more sets of intersecting lines. In some embodiments, when the positions of at least two feature points in the world coordinate system and the image coordinate system are known, the reference line may also include only one line.

在一些实施例中,计算设备120可以通过图像识别技术以从相机105所捕获的二维图像中确定与参考线对应的第一点集合。图3示出了根据本公开实施例的确定第一点集合的过程的流程图。In some embodiments, thecomputing device 120 may determine the first set of points corresponding to the reference line from the two-dimensional image captured by thecamera 105 through image recognition techniques. FIG. 3 shows a flowchart of a process of determining a first set of points according to an embodiment of the present disclosure.

如图3所示,在框302,计算设备120可以获取第一图像的掩码图像。根据本公开的一些实施例,计算设备120可以获取由经校准后的相机105捕获的第一图像,其中在掩码图像中位于参考线上的点和位于参考线外的点被不同地标识。以图1作为示例,计算设备120可以利用标志线检测模型来确定标志线115(停止标志线115-1和车道标志线115-2),可以在掩码图像中将被确定为停止标志线115-1和车道标志线115-2的点标记为白色,而将其他点标记为黑色,从而形成掩码图像。As shown in FIG. 3, atblock 302,computing device 120 may obtain a mask image for the first image. According to some embodiments of the present disclosure,computing device 120 may acquire a first image captured by calibratedcamera 105 in which points in the mask image that lie on the reference line and points that lie outside the reference line are identified differently. Taking FIG. 1 as an example, thecomputing device 120 may utilize a marking detection model to determine the marking 115 (stop marking 115-1 and lane marking 115-2), which may be determined as stop marking 115 in the mask image The points of -1 and lane marking line 115-2 are marked in white, while the other points are marked in black, forming a mask image.

例如,图4示出了将三维位置投影到第一图像的示意图400。如图4所示,停止标志线115-1和车道标志线115-2被示出为图4中的斜线区域。For example, FIG. 4 shows a schematic diagram 400 of projecting a three-dimensional position to a first image. As shown in FIG. 4 , the stop marker line 115 - 1 and the lane marker line 115 - 2 are shown as hatched areas in FIG. 4 .

在一些实施例中,计算设备120可以在获取第一图像前对相机105进行内参数标定。内参数是指与成像设备自身特性相关的参数。以相机为例,内参数是指比如焦距、像素大小等参数。在一些实施例中,相机105可以经畸变校正后捕获该第一图像。在一些实施例中,相机105可以经内参数标定和畸变校正后捕获该第一图像。由此可以有利于提高相机的外参数标定的准确性。In some embodiments,computing device 120 may perform intrinsic calibration oncamera 105 before acquiring the first image. Intrinsic parameters refer to parameters related to the characteristics of the imaging device itself. Taking a camera as an example, internal parameters refer to parameters such as focal length and pixel size. In some embodiments, thecamera 105 may capture the first image after distortion correction. In some embodiments, thecamera 105 may capture the first image after intrinsic calibration and distortion correction. This can help to improve the accuracy of the camera's external parameter calibration.

在框304,计算设备120可以从掩码图像中确定与位于参考线上的点相对应的区域的中心线。在一些实施例中,计算设备120例如可以利用骨骼提取模型来确定被标记为标志线115的区域的中心线。Atblock 304, thecomputing device 120 may determine, from the mask image, the centerline of the area corresponding to the point lying on the reference line. In some embodiments,computing device 120 may utilize a bone extraction model, for example, to determine the centerline of the area marked as landmark 115 .

在框306,计算设备120可以基于中心线确定第一点集合。在一些实施例中,计算设备120利用可以对所确定的中心线进行采样,以确定中心线上的多个点,以构成第一点集合。例如,如图4所示,计算设备120可以确定与标志线115所对应的多个点405(在图4中被示出为黑色实心点),所标识的多个点405构成第一点集合。Atblock 306, thecomputing device 120 may determine a first set of points based on the centerline. In some embodiments,computing device 120 utilizes may sample the determined centerline to determine a plurality of points on the centerline to form the first set of points. For example, as shown in FIG. 4,computing device 120 may determine a plurality of points 405 (shown as solid black dots in FIG. 4) corresponding to marker line 115, the identified plurality ofpoints 405 constituting a first set of points .

在一些实施例中,计算设备120还可以基于参考线在三维地图中的位置信息,从第一图像中确定第二点集合。在一些实施例中,三维地图可以由地图数据采集车来采集环境100相关的信息并且基于这样的信息而生成。例如,针对没有GPS信号的场景,可以通过即时定位与地图构建(SLAM)方法,让采集车从室外有GPS信号的位置驶入该场景,利用车载激光雷达、摄像头以及环视影像采集系统来采集道路环境信息,之后进行识别和融合,以将采集到的数据叠加在一起,生成三维地图。应理解到,可以通过其它任意合适方式来生成三维地图,本申请对三维地图的生成方式并不做任何限制。In some embodiments,computing device 120 may also determine the second set of points from the first image based on the location information of the reference line in the three-dimensional map. In some embodiments, a three-dimensional map may be collected by a map data collection vehicle to collect information about theenvironment 100 and generated based on such information. For example, for scenes without GPS signals, the real-time positioning and map building (SLAM) method can be used to allow the collection vehicle to drive into the scene from an outdoor location with GPS signals, and use on-board lidar, cameras, and surround-view image collection systems to collect roads. Environmental information is then identified and fused to overlay the collected data to generate a 3D map. It should be understood that the three-dimensional map may be generated in any other suitable manner, and the present application does not impose any limitation on the generating manner of the three-dimensional map.

根据本公开的一些实施例,计算设备120可以从三维地图确定与参考线对应的位置信息。例如,计算设备120可以确定停止标志线115-1和车道标志线115-2在三维地图中的位置信息,这样的位置信息例如可以被表示为一组三维坐标点。According to some embodiments of the present disclosure, thecomputing device 120 may determine the location information corresponding to the reference line from the three-dimensional map. For example,computing device 120 may determine location information for stop marker line 115-1 and lane marker line 115-2 in a three-dimensional map, such location information may be represented, for example, as a set of three-dimensional coordinate points.

在一些实施例中,计算设备120可以获取相机105的初始外参数。在一些实施例,初始外参数例如可以是在安装相机105时所确定的,其至少可以指示相机105在世界坐标系中的位置和角度。在一些实施例中,初始外参数例如也可以是上次标定相机105所确定的外参数。In some embodiments,computing device 120 may obtain initial extrinsic parameters ofcamera 105 . In some embodiments, the initial extrinsic parameters may be determined when thecamera 105 is installed, for example, and may indicate at least the position and angle of thecamera 105 in the world coordinate system. In some embodiments, the initial extrinsic parameter may also be, for example, the extrinsic parameter determined by thecamera 105 last calibration.

在一些实施例中,计算设备120可以基于初始外参数和参考线在三维地图中的位置信息,确定第一图像中的第二点集合。在一些实施例中,计算设备120可以基于初始外参数和相机105已知的内参数,而将位置信息所对应的一组三维坐标点投影到第一图像所对应的图像坐标系或像素坐标系中,从而获得第二点集合。In some embodiments,computing device 120 may determine the second set of points in the first image based on the initial extrinsic parameters and the location information of the reference line in the three-dimensional map. In some embodiments, thecomputing device 120 may project a set of three-dimensional coordinate points corresponding to the position information to an image coordinate system or a pixel coordinate system corresponding to the first image based on the initial extrinsic parameters and the intrinsic parameters known to thecamera 105 , so as to obtain the second set of points.

例如,如图4所示,基于参考线(例如,标志线115)在三维地图中的位置信息,计算设备120可以确定与位置信息所对应一组三维坐标点在第一图像中的投影点410(在图4中被示出为空心点)。该组投影点410构成了第二点集合。应当理解,第二点集合例如可以仅考虑落在第一图像的范围内的点。例如,由于三维地图中车道标志线115-2的距离较长,某些点可能被投影到第一图像外的点,这些点可以不被加入到第二点集合中。For example, as shown in FIG. 4 , based on the position information of the reference line (eg, the marker line 115 ) in the three-dimensional map, thecomputing device 120 may determine theprojection point 410 in the first image of a set of three-dimensional coordinate points corresponding to the position information (shown as hollow dots in Figure 4). The set of projectedpoints 410 constitutes a second set of points. It should be understood that the second set of points may, for example, only consider points falling within the range of the first image. For example, due to the long distance of the lane marking line 115-2 in the three-dimensional map, some points may be projected to points outside the first image, and these points may not be added to the second point set.

在一些实施例中,计算设备120可以基于第一点集合与第二点集合的匹配来确定相机105的针对第一图像的第一外参数。以下将参考图5来描述框202的具体过程。图5示出了根据本公开实施例的确定第一外参数的过程的流程图。In some embodiments,computing device 120 may determine a first extrinsic parameter ofcamera 105 for the first image based on a match of the first set of points with the second set of points. The specific process ofblock 202 will be described below with reference to FIG. 5 . FIG. 5 shows a flowchart of a process of determining a first extrinsic parameter according to an embodiment of the present disclosure.

如图5所示,在框502,计算设备120可以确定第一点集合和第二点集合的距离,其中该距离基于第二点集合中的点与第一点集合中的对应点之间的距离而确定。在一些实施例中,计算设备120可以从第一点集合中确定与第二点集合中的每个投影点相对应的临近点,其中临近点表示第一点集合中与投影点距离最近的点。例如,对于图4的示例,与投影点410最近的临近点为点405。As shown in FIG. 5, atblock 502, thecomputing device 120 may determine a distance between the first set of points and the second set of points, where the distance is based on a distance between a point in the second set of points and a corresponding point in the first set of points distance is determined. In some embodiments,computing device 120 may determine, from the first set of points, a neighboring point corresponding to each projected point in the second set of points, where the neighboring point represents a point in the first set of points that is closest to the projected point . For example, for the example of FIG. 4 , the closest neighbor to projectedpoint 410 ispoint 405 .

计算设备120随后可以确定第二点集合中的每个点与对应的临近点的距离。在一些实施例中,计算设备120例如可以将所有距离的总和确定作为第一点集合和第二点集合的距离。在一些实施例中,计算设备120例如还可以将所有距离的平均值确定作为第一点集合和第二点集合之间的距离。Computing device 120 may then determine the distance of each point in the second set of points from the corresponding neighboring point. In some embodiments,computing device 120 may, for example, determine the sum of all distances as the distance for the first set of points and the second set of points. In some embodiments, thecomputing device 120 may, for example, also determine the average value of all the distances as the distance between the first set of points and the second set of points.

在框504,根据第一点集合和第二点集合的距离大于预定的阈值的确定,计算设备120可以调整相机105的初始外参数。在一些实施例中,在一些实施例中,计算设备120可以基于最小重投影误差方法来调整相机105的初始外参数。具体地,计算设备120可以确定所述距离关于所述外参数的雅可比(Jacobi)矩阵,例如该雅可比矩阵可以表示为:Atblock 504 ,computing device 120 may adjust initial extrinsic parameters ofcamera 105 based on a determination that the distance between the first set of points and the second set of points is greater than a predetermined threshold. In some embodiments,computing device 120 may adjust the initial extrinsic parameters ofcamera 105 based on a minimum reprojection error method. Specifically, thecomputing device 120 may determine a Jacobian matrix of the distance with respect to the external parameter, for example, the Jacobian matrix may be expressed as:

Figure BDA0002241579040000091
Figure BDA0002241579040000091

其中e表示第二点集合中的投影点与对应的临近点的距离,δξ表示位姿在李代数下的表示,其中X、Y、Z表示投影点在世界坐标系中的坐标,X’、Y’、Z’表示经位姿变换后在相机坐标系中的位置,fx、fy表示相机105的内参数,由此可见,雅可比矩阵给出了距离关于位姿的导数。计算设备120进一步可以基于所确定的雅克比矩阵来调整相机105的初始外参数。Where e represents the distance between the projected point in the second point set and the corresponding adjacent point, δξ represents the representation of the pose in Lie algebra, where X, Y, Z represent the coordinates of the projected point in the world coordinate system, X', Y', Z' represent the position in the camera coordinate system after pose transformation, and fx and fy represent the internal parameters of thecamera 105. It can be seen that the Jacobian matrix gives the derivative of the distance with respect to the pose.Computing device 120 may further adjust initial extrinsic parameters ofcamera 105 based on the determined Jacobian matrix.

在框506,计算设备120可以基于经调整的外参数确定经更新的第二点集合。应当理解,计算设备120可以利用经调整的外参数和相机105的内参数来将三维地图中与参考线对应的一组三维坐标点投影到第一图像中,以获得经更新的第二点集合。Atblock 506,computing device 120 may determine an updated second set of points based on the adjusted extrinsic parameters. It should be understood that thecomputing device 120 may utilize the adjusted extrinsic parameters and the intrinsic parameters of thecamera 105 to project a set of three-dimensional coordinate points in the three-dimensional map corresponding to the reference lines into the first image to obtain an updated second set of points .

在框508,计算设备120可以确定所述第一点集合与所述经更新的第二点集合的距离小于或等于第一阈值距离。响应于在框508确定距离仍大于第一阈值距离,则方法可以进行到框504,继续调整外参数,即进入下一次迭代。响应于在框508确定距离小于或等于第一阈值距离时,则方法可以进行到框510,即计算设备120可以将经调整的外参数确定为相机105的针对第一图像的第一外参数。Atblock 508,computing device 120 may determine that the distance of the first set of points from the updated second set of points is less than or equal to a first threshold distance. In response to determining atblock 508 that the distance is still greater than the first threshold distance, the method may proceed to block 504 to continue adjusting the extrinsic parameters, ie, to the next iteration. In response to determining atblock 508 that the distance is less than or equal to the first threshold distance, the method may proceed to block 510 wherecomputing device 120 may determine the adjusted extrinsic parameter as the first extrinsic parameter ofcamera 105 for the first image.

在一些实施例中,迭代的终止条件也可以被设置为当迭代达到预定的次数即终止迭代。也即,当第一点集合与第二点集合的距离大于预定的阈值时,计算设备120例如可以基于雅可比矩阵来调整初始的外参数直到调整的次数达到预定的次数阈值。计算设备120可以将迭代终止时所调整的初始外参数确定为相机105的外参数。In some embodiments, the termination condition of the iteration can also be set to terminate the iteration when the iteration reaches a predetermined number of times. That is, when the distance between the first point set and the second point set is greater than a predetermined threshold, thecomputing device 120 may, for example, adjust the initial extrinsic parameter based on the Jacobian matrix until the number of adjustments reaches the predetermined threshold.Computing device 120 may determine the initial extrinsic parameters adjusted when the iteration is terminated as extrinsic parameters ofcamera 105 .

在一些实施例中,计算设备120也可以通过姿态搜索的方法来调整相机105的初始外参数。具体地,计算设备120可以通过搜索外参数所对应的六个自由度,即相机的安装位置的三维坐标以及相机的角度(俯仰角、偏航角和翻滚角),并搜索可能的解空间中使得第一点集合和第二点集合距离最近的外参数。In some embodiments, thecomputing device 120 may also adjust the initial extrinsic parameters of thecamera 105 through a pose search method. Specifically, thecomputing device 120 can search the six degrees of freedom corresponding to the extrinsic parameters, that is, the three-dimensional coordinates of the installation position of the camera and the angles of the camera (pitch angle, yaw angle, and roll angle), and search for possible solutions in the space. The extrinsic parameter that makes the first point set and the second point set the closest distance.

在一些实施例中,如上文所描述的,参考线可以包括在世界坐标系中两条相交的线。基于上文的最小重投影误差方法或者姿态搜索的方法可以确定最优的外参数。In some embodiments, as described above, the reference line may comprise two intersecting lines in the world coordinate system. The optimal extrinsic parameters can be determined based on the minimum reprojection error method or the pose search method above.

在一些实施例中,参考线例如可以仅包括一条线,例如,仅包括车道标志线115-2,在这种情况下,仅基于车道标志线115-2在三维地图中的位置信息和二维地图中的对应点可能无法获得唯一的外参数。在该实施例中,计算设备120可以利用已知位置的参考点作为另一约束来求解最优的外参数。具体地,计算设备120在确定外参数时,可以在满足将已知世界坐标系中的绝对位置的参考点匹配到第一图像中的参考点的前提下,通过最小冲投影误差或姿态搜索使得参考点所对应的第一点集合和第二点集合的距离小于预定的阈值,从而获得最优的外参数。应当理解,参考点可以是任何已知世界坐标的点,例如,已知位置的交通标志、已知位置的喷涂的参考点、或者其他任何已知位置的参考物。In some embodiments, the reference line may include, for example, only one line, eg, only the lane marking 115-2, in which case, it is based only on the location information of the lane marking 115-2 in the three-dimensional map and the two-dimensional Corresponding points in the map may not get unique extrinsic parameters. In this embodiment,computing device 120 may use a reference point of known location as another constraint to solve for optimal extrinsic parameters. Specifically, when determining the extrinsic parameter, thecomputing device 120 may, on the premise of matching the reference point of the known absolute position in the world coordinate system to the reference point in the first image, make the minimum overprojection error or attitude search such that The distance between the first point set and the second point set corresponding to the reference point is less than a predetermined threshold, so as to obtain optimal external parameters. It should be understood that the reference point may be any point with known world coordinates, eg, a traffic sign with a known location, a painted reference point with a known location, or any other reference with a known location.

继续参考图2,在框204,计算设备120获取相机105的第二外参数,其中第二外参数基于相机105先前捕获的第二图像而被确定。在一些实施例中,例如,第二图像可以是第一图像的前一帧图像。在一些实施例中,第二图像也可以是早于第一图像特定帧数的图像。应当理解,可以基于参考框202描述的过程来确定针对第二图像的第二外参数。所确定的第二外参数例如可以被存储在存储装置中,计算设备120可以从该存储装置中获取针对第二图像的第二外参数。With continued reference to FIG. 2 , atblock 204 ,computing device 120 obtains a second extrinsic parameter ofcamera 105 , where the second extrinsic parameter is determined based on a second image previously captured bycamera 105 . In some embodiments, for example, the second image may be a previous frame of the first image. In some embodiments, the second image may also be an image that is a certain number of frames earlier than the first image. It should be understood that the second extrinsic parameter for the second image may be determined based on the process described with reference to block 202 . The determined second extrinsic parameter may, for example, be stored in a storage device from which thecomputing device 120 may obtain the second extrinsic parameter for the second image.

在框206,计算设备120基于第二外参数和位置信息,从第一图像中确定第三点集合。在一些实施例中,计算设备120可以基于所获取的第二外参数和相机105已知的内参数,而将位置信息所对应的一组三维坐标点投影到第一图像所对应的图像坐标系或像素坐标系中,从而获得第三点集合。Atblock 206, thecomputing device 120 determines a third set of points from the first image based on the second extrinsic parameter and the location information. In some embodiments, thecomputing device 120 may project a set of three-dimensional coordinate points corresponding to the position information to an image coordinate system corresponding to the first image based on the acquired second extrinsic parameters and the intrinsic parameters known to thecamera 105 Or in the pixel coordinate system to obtain the third set of points.

在框208,计算设备120基于第一点集合、第二点集合以及第三点集合,从第一外参数和第二外参数中确定与第一图像相对应的外参数。以下将结合图6来描述框208的具体过程,图6示出了根据本公开实施例的确定与第一图像对应的外参数的方法的过程。Atblock 208, thecomputing device 120 determines an extrinsic parameter corresponding to the first image from the first extrinsic parameter and the second extrinsic parameter based on the first set of points, the second set of points, and the third set of points. The specific process ofblock 208 will be described below with reference to FIG. 6 , which shows a process of a method for determining an extrinsic parameter corresponding to the first image according to an embodiment of the present disclosure.

如图6所示,在框602,计算设备120可以基于第一点集合和第二点集合确定针对第一外参数的第一评价度量。在一些实施例中,第一评价度量可以指示第一点集合与第二点集合的距离。如上文所讨论的,计算设备120可以确定第二点集合中的每个点与对应的临近点的距离。在一些实施例中,计算设备120例如可以将所有距离的总和确定作为第一点集合和第二点集合的距离。在一些实施例中,计算设备120例如还可以将所有距离的平均值确定作为第一点集合和第二点集合之间的距离。应当理解,当总距离越大时,其表示该外参数并不能够很好地反映相机当前的位姿,因此第一评价度量可以被较小地设置,例如被设置为与总距离成反比的数值(例如总距离的倒数)。As shown in FIG. 6, atblock 602, thecomputing device 120 may determine a first evaluation metric for the first extrinsic parameter based on the first set of points and the second set of points. In some embodiments, the first evaluation metric may indicate a distance of the first set of points from the second set of points. As discussed above,computing device 120 may determine the distance of each point in the second set of points from the corresponding neighboring point. In some embodiments,computing device 120 may, for example, determine the sum of all distances as the distance for the first set of points and the second set of points. In some embodiments, thecomputing device 120 may, for example, also determine the average value of all the distances as the distance between the first set of points and the second set of points. It should be understood that when the total distance is larger, it means that the external parameter cannot reflect the current pose of the camera well, so the first evaluation metric can be set smaller, for example, set to be inversely proportional to the total distance Numeric value (eg the inverse of the total distance).

在一些实施例中,第一评价度量还可以指示第一点集合和第二点集合中匹配点对的数目,其中匹配点对中的点与另一点的距离小于第二阈值距离。第二集合中的点与第一集合中对应的临近点可以被称为匹配点对。当匹配的点数越多时,其表示该外参数能够较好地反映相机当前的位姿,因此,第一评价度量可以被较高的设置。In some embodiments, the first evaluation metric may also indicate the number of matching point pairs in the first set of points and the second set of points, wherein a point in the matching point pair is less than a second threshold distance from another point. Points in the second set and corresponding adjacent points in the first set may be referred to as matched point pairs. When the number of matching points is more, it means that the external parameter can better reflect the current pose of the camera, therefore, the first evaluation metric can be set higher.

在一些实施例中,第一评价度量例如还可以指示第一点集合与第二点集合的距离和第一点集合和第二点集合中匹配点对的数目两者。例如,第一评价度量可以被取值为基于距离确定的值和基于匹配点对的数目确定的值的加权和。In some embodiments, the first evaluation metric may also indicate, for example, both the distance of the first set of points and the second set of points and the number of matching point pairs in the first set of points and the second set of points. For example, the first evaluation metric may be taken as a weighted sum of a value determined based on the distance and a value determined based on the number of matching point pairs.

在框604,计算设备120可以基于第一点集合和第三点集合,确定针对第二外参数的第二评价度量。类似地,第二评价度量可以指示以下中的至少一项:第一点集合与第三点集合的距离,或者第一点集合和第三点集合中匹配点对的数目。Atblock 604, thecomputing device 120 may determine a second evaluation metric for the second extrinsic parameter based on the first set of points and the third set of points. Similarly, the second evaluation metric may indicate at least one of: the distance between the first set of points and the third set of points, or the number of matching point pairs in the first set of points and the third set of points.

在框606,计算设备120可以确定第一评价度量与第二评价度量的差异是否小于第一阈值。当在框606确定第一评价度量与第二评价度量的差异小于第一阈值,则方法进行到框608,即计算设备120可以将第二外参数确定为与第一图像相对应的外参数。相反,当在框606确定第一评价度量与第二评价度量的差异大于或等于第一阈值,则方法进行到框610,即计算设备120可以将第一外参数确定为与第一图像相对应的外参数。Atblock 606, thecomputing device 120 may determine whether the difference between the first evaluation metric and the second evaluation metric is less than a first threshold. When it is determined atblock 606 that the difference between the first evaluation metric and the second evaluation metric is less than the first threshold, the method proceeds to block 608 where thecomputing device 120 may determine the second extrinsic parameter as the extrinsic parameter corresponding to the first image. Conversely, when it is determined atblock 606 that the difference between the first evaluation metric and the second evaluation metric is greater than or equal to the first threshold, the method proceeds to block 610 where thecomputing device 120 may determine the first extrinsic parameter as corresponding to the first image external parameters.

以第一评价度量指示距离作为示例,当基于第一外参数确定的距离大于基于第二外参数确定的距离时,计算设备120可以确定第一外参数并没有优于第二外参数,因此计算设备120可以继续使用基于先前的第二图像所确定的第二外参数作为相机105的针对当前的第一图像的外参数。在一些实施例中,基于第一外参数确定的距离虽然小于基于第二外参数确定的距离,但两者的差异小于第一阈值时,计算设备120为了避免输出的外参数不平滑,而继续使用基于先前的第二图像所确定的第二外参数。Taking the distance indicated by the first evaluation metric as an example, when the distance determined based on the first extrinsic parameter is greater than the distance determined based on the second extrinsic parameter, thecomputing device 120 may determine that the first extrinsic parameter is not better than the second extrinsic parameter, and therefore calculates Thedevice 120 may continue to use the second extrinsic parameter determined based on the previous second image as the extrinsic parameter of thecamera 105 for the current first image. In some embodiments, although the distance determined based on the first extrinsic parameter is smaller than the distance determined based on the second extrinsic parameter, when the difference between the two is smaller than the first threshold, thecomputing device 120 continues to prevent the output extrinsic parameter from being unsmoothed. A second extrinsic parameter determined based on the previous second image is used.

类似地,以第一评价度量指示匹配数目作为示例,只有在基于第一外参数确定的匹配点对的数目远优于基于第二外参数确定的匹配点对的数目时,计算设备120才将第一外参数确定作为针对第一图像的外参数。Similarly, taking the number of matches indicated by the first evaluation metric as an example, thecomputing device 120 will only assign the number of matching point pairs determined based on the first extrinsic parameter is far superior to the number of matching point pairs determined based on the second extrinsic parameter. The first extrinsic parameter is determined as an extrinsic parameter for the first image.

在一些实施例中,计算设备120还可以仅在第一外参数确定的距离远小于基于第二外参数确定的距离、且基于第一外参数确定的匹配点对的数目远优于基于第二外参数确定的匹配点对的数目时,计算设备120才将第一外参数确定作为针对第一图像的外参数。In some embodiments, thecomputing device 120 may also only determine if the distance determined based on the first extrinsic parameter is much smaller than the distance determined based on the second extrinsic parameter, and the number of matching point pairs determined based on the first extrinsic parameter is much greater than that determined based on the second extrinsic parameter. Only when the number of matching point pairs determined by the extrinsic parameter is determined, thecomputing device 120 determines the first extrinsic parameter as the extrinsic parameter for the first image.

基于上文所述的方法,本公开的实施例避免所输出的相机外参数变化过大,进而在保证输出外参数质量的情况下,还能够使得输出的相机外参数更为平滑。Based on the methods described above, the embodiments of the present disclosure avoid excessive changes in the output extrinsic parameters, and further enable the output extrinsic parameters to be smoother while ensuring the quality of the output extrinsic parameters.

在一些实施例中,计算设备120还可以进一步将所确定的外参数与相机105的默认外参数进行比较,以确定是否采用默认外参数。图7示出了根据本公开的一些实施例的更新外参数的示例方法700的流程图。In some embodiments,computing device 120 may further compare the determined extrinsic parameters to default extrinsic parameters ofcamera 105 to determine whether to employ default extrinsic parameters. FIG. 7 illustrates a flow diagram of anexample method 700 of updating extrinsic parameters in accordance with some embodiments of the present disclosure.

如图7所示,在框702,计算设备120可以基于相机105的默认外参数和位置信息,从第一图像中确定第四点集合。在一些实施例中,相机105的默认外参数可以是在安装相机105时所确定的,其至少可以指示相机105在世界坐标系中的位置和角度。在一些实施例中,计算设备120可以基于默认外参数和相机105已知的内参数,而将位置信息所对应的一组三维坐标点投影到第一图像所对应的图像坐标系或像素坐标系中,从而获得第四点集合。As shown in FIG. 7 , atblock 702 ,computing device 120 may determine a fourth set of points from the first image based on default extrinsic parameters and location information ofcamera 105 . In some embodiments, the default extrinsic parameters of thecamera 105 may be determined when thecamera 105 is installed, which may at least indicate the position and angle of thecamera 105 in the world coordinate system. In some embodiments, thecomputing device 120 may project a set of three-dimensional coordinate points corresponding to the position information to an image coordinate system or a pixel coordinate system corresponding to the first image based on default extrinsic parameters and intrinsic parameters known to thecamera 105 , so as to obtain the fourth set of points.

在框704,计算设备120可以基于第一点集合和第四点集合,确定针对默认外参数的第三评价度量。在一些实施例中,第三评价度量指示以下中的至少一项:第一点集合与第四点集合的距离,或者第一点集合和第四点集合中匹配点对的数目。应当理解,可以参考上文关于框602所描述的过程来确定针对默认外参数的第三评价度量。Atblock 704,computing device 120 may determine a third evaluation metric for the default extrinsic parameter based on the first set of points and the fourth set of points. In some embodiments, the third evaluation metric indicates at least one of: the distance of the first set of points and the fourth set of points, or the number of matching point pairs in the first set of points and the fourth set of points. It should be appreciated that the third evaluation metric for the default extrinsic parameter may be determined with reference to the process described above with respect to block 602 .

在框706,计算设备120从第一评价度量和第二评价度量中确定针对经确定的外参数的第四评价度量。具体地,计算设备120可以获取基于方法200所确定的外参数是第一外参数还是第二外参数,从而确定与所确定的外参数对应的第四评价度量(第一评价度量或第二评价度量)。Atblock 706, thecomputing device 120 determines a fourth evaluation metric for the determined extrinsic parameter from the first evaluation metric and the second evaluation metric. Specifically, thecomputing device 120 may obtain whether the extrinsic parameter determined based on themethod 200 is the first extrinsic parameter or the second extrinsic parameter, so as to determine the fourth evaluation metric (the first evaluation metric or the second evaluation metric) corresponding to the determined extrinsic parameter measure).

在框708,计算设备120可以确定第四评价度量与第三评价度量的差异是否小于第二阈值。当在框708确定第四评价度量与第三评价度量的差异大于或等于第二阈值,则方法进行到框710,即计算设备120可以利用相机105的默认外参数更新经确定的外参数。例如,当所确定的外参数没有明显优于或者甚至差于离线外参数时,考虑到在安装相机105所确定的默认外参数时经过严格测量的,因此计算设备120可以使用相机105的默认外参数来代替所确定的外参数,从而避免因为某些错误导致所确定的外参数误差过大。Atblock 708,computing device 120 may determine whether the difference between the fourth evaluation metric and the third evaluation metric is less than a second threshold. When it is determined atblock 708 that the difference between the fourth evaluation metric and the third evaluation metric is greater than or equal to the second threshold, the method proceeds to block 710 wherecomputing device 120 may update the determined extrinsic parameters with default extrinsic parameters ofcamera 105 . For example, when the determined extrinsic parameters are not significantly better or even worse than offline extrinsic parameters, thecomputing device 120 may use the default extrinsic parameters of thecamera 105 considering that the default extrinsic parameters determined by thecamera 105 were strictly measured when thecamera 105 was installed to replace the determined external parameters, so as to avoid excessive errors of the determined external parameters due to some errors.

相反,当在框708确定第四评价度量与第三评价度量的差异小于第二阈值,则计算设备120可以继续使用所确定的外参数(图中未示出)。Conversely, when it is determined atblock 708 that the difference between the fourth evaluation metric and the third evaluation metric is less than the second threshold,computing device 120 may continue to use the determined extrinsic parameter (not shown).

在一些实施例中,计算设备120还可以通过用于确定外参数的匹配点对的数目来避免因为参考线的遮挡而导致所计算的外参数误差过大。图8示出了根据本公开的另一些实施例的更新外参数的示例方法800的流程图。In some embodiments, thecomputing device 120 can also avoid excessive errors in the calculated extrinsic parameters due to the occlusion of the reference line by the number of matching point pairs used to determine the extrinsic parameters. FIG. 8 shows a flowchart of anexample method 800 of updating extrinsic parameters according to further embodiments of the present disclosure.

如图8所示,在框802,计算设备120可以确定第一点集合中用于确定经确定的外参数的点的数目。具体地,当基于方法200选择的外参数为第一外参数时,计算设备120可以确定该数目为第一点集合和第二点集合的匹配点对的数目。相反,当基于方法200选择的外参数为第二外参数时,计算设备120可以确定该数目为第一点集合和第三点集合的匹配点对的数目。As shown in FIG. 8, atblock 802,computing device 120 may determine the number of points in the first set of points for use in determining the determined extrinsic parameter. Specifically, when the extrinsic parameter selected based on themethod 200 is the first extrinsic parameter, thecomputing device 120 may determine the number as the number of matching point pairs of the first point set and the second point set. Conversely, when the extrinsic parameter selected based on themethod 200 is the second extrinsic parameter, thecomputing device 120 may determine the number as the number of matching point pairs of the first point set and the third point set.

在框804,计算设备120可以确定该数目是否小于预定的数目阈值。当在框804确定该数目小于预定的数目阈值时,则方法800可以进行到框806,即计算设备120可以利用相机的默认外参数更新经确定的外参数。在一些实施例中,该数目阈值可以是基于历史的图像帧确定外参数时所使用的匹配点对的数目而确定的。例如,该数目阈值可以被设置为一定时间内历史的图像帧中用于确定外参数的匹配点对的数目的最大值。Atblock 804,computing device 120 may determine whether the number is less than a predetermined number threshold. When it is determined atblock 804 that the number is less than the predetermined number threshold, then themethod 800 may proceed to block 806 where thecomputing device 120 may update the determined extrinsic parameters with the camera's default extrinsic parameters. In some embodiments, the number threshold may be determined based on the number of matching point pairs used in determining the extrinsic parameter based on historical image frames. For example, the number threshold may be set to the maximum value of the number of matching point pairs used to determine the extrinsic parameter in the historical image frames over a certain period of time.

在一些实施例中,当该数目过小时,其表示用于确定该外参数的匹配点的数目过低,也即,可能存在参考线被遮挡的情形,在这种情况下,计算设备120可以使用相机105的默认外参数来代替所确定的外参数,从而避免因为某些错误导致所确定的外参数误差过大。In some embodiments, when the number is too small, it indicates that the number of matching points used to determine the extrinsic parameter is too low, that is, there may be a situation where the reference line is occluded, in this case, thecomputing device 120 may The default extrinsic parameters of thecamera 105 are used to replace the determined extrinsic parameters, so as to avoid excessive errors of the determined extrinsic parameters due to some errors.

相反,当在框804确定该数目大于或等于预定的数目阈值,则计算设备120可以继续使用所确定的外参数(图中未示出)。Conversely, when it is determined atblock 804 that the number is greater than or equal to the predetermined number threshold,computing device 120 may continue to use the determined extrinsic parameter (not shown).

在一些实施例中,由相机105捕获的第一图像还可以用于障碍物检测。应当理解,障碍物检测和上文所描述的相机标定过程例如可以利用不同的线程而并行地进行,从而提高处理效率。在一些实施例中,当从第一图像检测到障碍物时,计算设备120可以确定第一图像中与障碍物所对应的区域。应当理解,障碍物可以包括任何的动态障碍物,例如,车辆、行人、或动物等,障碍物也可以包括任何的静态障碍物。本公开不旨在对障碍物的类型进行任何的限定。In some embodiments, the first image captured by thecamera 105 may also be used for obstacle detection. It should be understood that the obstacle detection and the camera calibration process described above may be performed in parallel using different threads, for example, to improve processing efficiency. In some embodiments, when an obstacle is detected from the first image,computing device 120 may determine a region in the first image that corresponds to the obstacle. It should be understood that the obstacles can include any dynamic obstacles, such as vehicles, pedestrians, or animals, and the obstacles can also include any static obstacles. The present disclosure is not intended to place any limitation on the types of obstacles.

进一步地,计算设备120可以基于所确定的外参数和该区域,确定障碍物在世界坐标系中的位置。具体地,计算设备120可以利用相机已知的内参数和经确定的外参数,实现该区域从图像坐标系到世界坐标系的转换。Further, thecomputing device 120 may determine the location of the obstacle in the world coordinate system based on the determined extrinsic parameters and the area. Specifically, thecomputing device 120 may utilize the known intrinsic parameters of the camera and the determined extrinsic parameters to realize the conversion of the region from the image coordinate system to the world coordinate system.

在一些实施例中,计算设备120还可以提供障碍物在世界坐标系中的位置。例如,计算设备120可以向周边的车辆(例如,车辆110)广播关于道路102的障碍物信息,从而为车辆的自动驾驶决策提供基础。在一些实施例中,计算设备120还可以基于所确定的外参数例如确定车辆110的位置,并将该位置发送至车辆110以实现车辆110的定位。In some embodiments,computing device 120 may also provide the location of the obstacle in the world coordinate system. For example,computing device 120 may broadcast obstacle information aboutroad 102 to surrounding vehicles (eg, vehicle 110 ) to provide a basis for autonomous driving decisions of the vehicle. In some embodiments, thecomputing device 120 may also determine the location of thevehicle 110 based on the determined extrinsic parameters, for example, and transmit the location to thevehicle 110 to enable the location of thevehicle 110 .

应当理解,虽然本公开的方法参考路测相机的示例来进行描述,但是应当理解,这样的环境仅是示意性的,本公开的方法还可以用于例如位于其他位置的相机(例如,安装在车辆上的相机的初始标定)的标定。本公开不旨在对相机所安装的位置进行任何的限定。It should be understood that although the method of the present disclosure is described with reference to the example of a drive test camera, it should be understood that such an environment is merely illustrative and that the method of the present disclosure may also be used, for example, with cameras located in other locations (eg, mounted in Initial calibration of the camera on the vehicle). This disclosure is not intended to place any limitation on the location where the camera is mounted.

本公开的实施例还提供了用于实现上述方法或过程的相应装置。图9示出了根据本公开的一些实施例的相机标定的装置900的示意性结构框图。该装置900可以在例如图1的计算设备120处实施。Embodiments of the present disclosure also provide corresponding apparatuses for implementing the above-mentioned methods or processes. FIG. 9 shows a schematic structural block diagram of anapparatus 900 for camera calibration according to some embodiments of the present disclosure. Theapparatus 900 may be implemented, for example, at thecomputing device 120 of FIG. 1 .

如图9所示,装置900可以包括第一外参数确定模块910,被配置为基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和第一图像中基于参考线在三维地图中的位置信息确定的第二点集合,确定相机的第一外参数,第一外参数指示相机坐标系与世界坐标系的转换关系。装置900还可以包括第二外参数获取模块920,被配置为获取相机的第二外参数,第二外参数基于相机先前捕获的第二图像而被确定。此外,装置900还可以包括第三点集合确定模块930,被配置为基于第二外参数和位置信息,从第一图像中确定第三点集合。装置900还可以包括第一外参数选择模块940,被配置为基于第一点集合、第二点集合以及第三点集合,从第一外参数和第二外参数中确定与第一图像相对应的外参数。As shown in FIG. 9 , theapparatus 900 may include a first extrinsicparameter determination module 910 configured to determine a first set of points corresponding to a predetermined reference line from a first image captured by the camera and a The second set of points determined by the position information of the reference line in the three-dimensional map determines the first external parameter of the camera, and the first external parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system. Theapparatus 900 may further include a second extrinsicparameter acquisition module 920 configured to acquire a second extrinsic parameter of the camera, the second extrinsic parameter being determined based on a second image previously captured by the camera. In addition, theapparatus 900 may further include a third point setdetermination module 930 configured to determine a third point set from the first image based on the second extrinsic parameter and the location information. Theapparatus 900 may further include a first extrinsicparameter selection module 940 configured to determine from the first extrinsic parameter and the second extrinsic parameter corresponding to the first image based on the first set of points, the second set of points and the third set of points external parameters.

在一些实施例中,第一外参数确定模块910包括:第一调整模块,被配置为响应于第一点集合与第二点集合的距离大于预定的阈值,调整相机的初始外参数,其中距离基于第二点集合中的点与第一点集合中的对应点之间的距离而确定;更新模块,被配置为基于经调整的初始外参数确定经更新的第二点集合;以及第一外参数输出模块,被配置为响应于第一点集合与经更新的第二点集合的距离小于或等于第一阈值距离,将经调整的初始外参数确定为相机的第一外参数。In some embodiments, the first extrinsicparameter determination module 910 includes: a first adjustment module configured to adjust the initial extrinsic parameters of the camera in response to the distance between the first set of points and the second set of points being greater than a predetermined threshold, wherein the distance determined based on distances between points in the second set of points and corresponding points in the first set of points; an update module configured to determine an updated second set of points based on the adjusted initial extrinsic parameters; and a first extrinsic parameter A parameter output module configured to determine the adjusted initial extrinsic parameter as the first extrinsic parameter of the camera in response to the distance between the first set of points and the updated second set of points being less than or equal to the first threshold distance.

在一些实施例中,第一调整模块包括:雅可比矩阵确定模块,确定距离关于外参数的雅可比矩阵;以及第二调整模块,被配置为基于雅可比矩阵调整初始外参数。In some embodiments, the first adjustment module includes: a Jacobian matrix determination module that determines a Jacobian matrix of distances with respect to the extrinsic parameter; and a second adjustment module configured to adjust the initial extrinsic parameter based on the Jacobian matrix.

在一些实施例中,第一外参数选择模块940包括:第一评价度量确定模块,被配置为基于第一点集合和第二点集合,确定针对第一外参数的第一评价度量;第二评价度量确定模块,被配置为基于第一点集合和第三点集合,确定针对第二外参数的第二评价度量;以及第二外参数选择模块,被配置为响应于第一评价度量与第二评价度量的差小于第一阈值,将第二外参数确定为与第一图像相对应的外参数。In some embodiments, the first extrinsicparameter selection module 940 includes: a first evaluation metric determination module configured to determine a first evaluation metric for the first extrinsic parameter based on the first set of points and the second set of points; a second an evaluation metric determination module configured to determine a second evaluation metric for the second extrinsic parameter based on the first set of points and the third set of points; and a second extrinsic parameter selection module configured to respond to the first evaluation metric and the third extrinsic parameter The difference between the two evaluation metrics is smaller than the first threshold, and the second extrinsic parameter is determined as the extrinsic parameter corresponding to the first image.

在一些实施例中,其中第一评价度量指示以下中的至少一项:第一点集合与第二点集合的距离,或者第一点集合和第二点集合中匹配点对的数目,其中匹配点对中的点与另一点的距离小于第二阈值距离。In some embodiments, wherein the first evaluation metric indicates at least one of: the distance of the first set of points from the second set of points, or the number of matching point pairs in the first set of points and the second set of points, where matching A point in a point pair is less than a second threshold distance from the other point.

在一些实施例中,第一外参数选择模块940还包括:第三外参数选择模块,响应于第一评价度量与第二评价度量的差大于或等于第一阈值,将第一外参数确定为与第一图像相对应的外参数。In some embodiments, the first extrinsicparameter selection module 940 further includes: a third extrinsic parameter selection module, in response to the difference between the first evaluation metric and the second evaluation metric being greater than or equal to the first threshold, determining the first extrinsic parameter as Extrinsic parameters corresponding to the first image.

在一些实施例中,装置900还包括:第四点集合确定模块,被配置为基于相机的默认外参数和位置信息,从第一图像中确定第四点集合;第三评价度量确定模块,被配置为基于第一点集合和第四点集合,确定针对默认外参数的第三评价度量,第三评价度量指示以下中的至少一项:第一点集合与第四点集合的距离,或者第一点集合和第四点集合中匹配点对的数目;第四评价度量确定模块,被配置为从第一评价度量和第二评价度量中确定针对经确定的外参数的第四评价度量;以及第一外参数更新模块,被配置为响应于第四评价度量与第三评价度量的差异大于或等于第二阈值,利用相机的默认外参数更新经确定的外参数。In some embodiments, theapparatus 900 further includes: a fourth point set determination module, configured to determine a fourth point set from the first image based on the camera's default extrinsic parameters and location information; a third evaluation metric determination module, configured by is configured to determine a third evaluation metric for the default extrinsic parameter based on the first set of points and the fourth set of points, the third evaluation metric indicating at least one of the following: the distance between the first set of points and the fourth set of points, or the the number of matching point pairs in the set of points and the fourth set of points; a fourth evaluation metric determination module configured to determine a fourth evaluation metric for the determined extrinsic parameter from the first evaluation metric and the second evaluation metric; and The first extrinsic parameter updating module is configured to update the determined extrinsic parameters with the camera's default extrinsic parameters in response to the difference between the fourth evaluation metric and the third evaluation metric being greater than or equal to the second threshold.

在一些实施例中,装置900还包括:数目确定模块,被配置为确定第一点集合中用于确定经确定的外参数的点的数目;以及第二外参数更新模块,被配置为响应于数目小于预定的数目阈值,利用相机的默认外参数更新经确定的外参数。In some embodiments, theapparatus 900 further includes: a number determination module configured to determine the number of points in the first set of points for determining the determined extrinsic parameter; and a second extrinsic parameter update module configured to respond to If the number is less than a predetermined number threshold, the determined extrinsic parameters are updated with the camera's default extrinsic parameters.

在一些实施例中,装置900还包括:区域确定模块,被配置为响应于从第一图像检测到障碍物,确定第一图像中与障碍物对应的区域;以及位置确定模块,被配置为基于外参数和区域,确定障碍物在世界坐标系中的位置。In some embodiments,apparatus 900 further includes: an area determination module configured to determine an area corresponding to the obstacle in the first image in response to detecting the obstacle from the first image; and a location determination module configured to be based on Extrinsic parameters and regions, determine the location of obstacles in the world coordinate system.

在一些实施例中,装置900还包括:提供模块,被配置为提供障碍物的位置。In some embodiments, theapparatus 900 further includes a providing module configured to provide the location of the obstacle.

装置900中所包括的单元可以利用各种方式来实现,包括软件、硬件、固件或其任意组合。在一些实施例中,一个或多个单元可以使用软件和/或固件来实现,例如存储在存储介质上的机器可执行指令。除了机器可执行指令之外或者作为替代,装置900中的部分或者全部单元可以至少部分地由一个或多个硬件逻辑组件来实现。作为示例而非限制,可以使用的示范类型的硬件逻辑组件包括现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准品(ASSP)、片上系统(SOC)、复杂可编程逻辑器件(CPLD),等等。The units included in theapparatus 900 may be implemented in various manners, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units may be implemented using software and/or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units inapparatus 900 may be implemented, at least in part, by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that may be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standards (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLD), etc.

图9中所示的这些单元可以部分或者全部地实现为硬件模块、软件模块、固件模块或者其任意组合。特别地,在某些实施例中,上文描述的流程、方法或过程可以由存储系统或与存储系统对应的主机或独立于存储系统的其它计算设备中的硬件来实现。The units shown in FIG. 9 may be partially or fully implemented as hardware modules, software modules, firmware modules, or any combination thereof. In particular, in some embodiments, the procedures, methods or processes described above may be implemented by hardware in a storage system or a host corresponding to the storage system or other computing device independent of the storage system.

图10示出了可以用来实施本公开的实施例的示例设备1000的示意性框图。设备1000可以用于实现计算设备120。如图所示,设备1000包括中央处理单元(CPU)1001,其可以根据存储在只读存储器(ROM)1002中的计算机程序指令或者从存储单元1008加载到随机访问存储器(RAM)1003中的计算机程序指令,来执行各种适当的动作和处理。在RAM 1003中,还可存储设备1000操作所需的各种程序和数据。CPU 1001、ROM 1002以及RAM 1003通过总线1004彼此相连。输入/输出(I/O)接口1005也连接至总线1004。10 shows a schematic block diagram of anexample device 1000 that may be used to implement embodiments of the present disclosure.Device 1000 may be used to implementcomputing device 120 . As shown,device 1000 includes a central processing unit (CPU) 1001 that may be loaded into a computer in random access memory (RAM) 1003 according to computer program instructions stored in read only memory (ROM) 1002 or fromstorage unit 1008 Program instructions to perform various appropriate actions and processes. In theRAM 1003, various programs and data necessary for the operation of thedevice 1000 can also be stored. TheCPU 1001 , theROM 1002 , and theRAM 1003 are connected to each other through abus 1004 . An input/output (I/O)interface 1005 is also connected to thebus 1004 .

设备1000中的多个部件连接至I/O接口1005,包括:输入单元1006,例如键盘、鼠标等;输出单元1007,例如各种类型的显示器、扬声器等;存储单元1008,例如磁盘、光盘等;以及通信单元1009,例如网卡、调制解调器、无线通信收发机等。通信单元1009允许设备1000通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。Various components in thedevice 1000 are connected to the I/O interface 1005, including: aninput unit 1006, such as a keyboard, mouse, etc.; anoutput unit 1007, such as various types of displays, speakers, etc.; astorage unit 1008, such as a magnetic disk, an optical disk, etc. ; and acommunication unit 1009, such as a network card, a modem, a wireless communication transceiver, and the like. Thecommunication unit 1009 allows thedevice 1000 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

处理单元1001执行上文所描述的各个方法和处理,例如方法200、300、700和/或800。例如,在一些实施例中,方法200、300、700和/或800可被实现为计算机软件程序,其被有形地包含于机器可读介质,例如存储单元1008。在一些实施例中,计算机程序的部分或者全部可以经由ROM 1002和/或通信单元1009而被载入和/或安装到设备1000上。当计算机程序加载到RAM 1003并由CPU 1001执行时,可以执行上文描述的方法200、300、700和/或800的一个或多个步骤。备选地,在其他实施例中,CPU 801可以通过其他任何适当的方式(例如,借助于固件)而被配置为执行方法200、300、700和/或800。Theprocessing unit 1001 performs the various methods and processes described above, eg,methods 200 , 300 , 700 and/or 800 . For example, in some embodiments,methods 200 , 300 , 700 and/or 800 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such asstorage unit 1008 . In some embodiments, part or all of the computer program may be loaded and/or installed on thedevice 1000 via theROM 1002 and/or thecommunication unit 1009 . When a computer program is loaded intoRAM 1003 and executed byCPU 1001, one or more steps ofmethods 200, 300, 700 and/or 800 described above may be performed. Alternatively, in other embodiments, CPU 801 may be configured to performmethods 200, 300, 700 and/or 800 by any other suitable means (eg, by means of firmware).

用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器,使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行,作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.

在本公开的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

此外,虽然采用特定次序描绘了各操作,但是这应当理解为要求这样操作以所示出的特定次序或以顺序次序执行,或者要求所有图示的操作应被执行以取得期望的结果。在一定环境下,多任务和并行处理可能是有利的。同样地,虽然在上面论述中包含了若干具体实现细节,但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实现中。相反地,在单个实现的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实现中。Additionally, although operations are depicted in a particular order, this should be understood to require that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations should be performed to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although the above discussion contains several implementation-specific details, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.

尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题,但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反,上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。Although the subject matter has been described in language specific to structural features and/or logical acts of method, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims (22)

Translated fromChinese
1.一种用于相机标定的方法,包括:1. A method for camera calibration, comprising:基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和所述第一图像中基于所述参考线在三维地图中的位置信息确定的第二点集合,确定所述相机的第一外参数,所述第一外参数指示相机坐标系与世界坐标系的转换关系;based on determining a first set of points corresponding to a predetermined reference line from a first image captured by the camera and a second set of points in the first image determined based on position information of the reference line in the three-dimensional map, determining The first external parameter of the camera, the first external parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system;获取所述相机的第二外参数,所述第二外参数基于所述相机先前捕获的第二图像而被确定;obtaining a second extrinsic parameter of the camera, the second extrinsic parameter being determined based on a second image previously captured by the camera;基于所述第二外参数和所述位置信息,从所述第一图像中确定第三点集合;以及determining a third set of points from the first image based on the second extrinsic parameter and the location information; and基于第一点集合、所述第二点集合以及所述第三点集合,从所述第一外参数和所述第二外参数中确定与所述第一图像相对应的外参数。An extrinsic parameter corresponding to the first image is determined from the first extrinsic parameter and the second extrinsic parameter based on the first set of points, the second set of points, and the third set of points.2.根据权利要求1所述的方法,其中确定所述相机的所述第一外参数包括:2. The method of claim 1, wherein determining the first extrinsic parameter of the camera comprises:响应于所述第一点集合与所述第二点集合的距离大于预定的阈值,调整所述相机的初始外参数,其中所述距离基于所述第二点集合中的点与所述第一点集合中的对应点之间的距离而确定;Adjusting initial extrinsic parameters of the camera in response to a distance between the first set of points and the second set of points being greater than a predetermined threshold, wherein the distance is based on points in the second set of points and the first set of points The distance between the corresponding points in the point set is determined;基于经调整的初始外参数确定经更新的第二点集合;以及determining an updated second set of points based on the adjusted initial extrinsic parameters; and响应于所述第一点集合与所述经更新的第二点集合的距离小于或等于第一阈值距离,将经调整的初始外参数确定为所述相机的所述第一外参数。An adjusted initial extrinsic parameter is determined to be the first extrinsic parameter of the camera in response to a distance of the first set of points from the updated second set of points being less than or equal to a first threshold distance.3.根据权利要求2所述的方法,其中调整所述初始外参数包括:3. The method of claim 2, wherein adjusting the initial extrinsic parameter comprises:确定所述距离关于所述外参数的雅可比矩阵;以及determining a Jacobian of the distance with respect to the extrinsic parameter; and基于所述雅可比矩阵调整所述初始外参数。The initial extrinsic parameters are adjusted based on the Jacobian matrix.4.根据权利要求1所述的方法,其中从所述第一外参数和所述第二外参数确定与所述第一图像相对应的外参数包括:4. The method of claim 1, wherein determining an extrinsic parameter corresponding to the first image from the first extrinsic parameter and the second extrinsic parameter comprises:基于所述第一点集合和所述第二点集合,确定针对所述第一外参数的第一评价度量;determining a first evaluation metric for the first extrinsic parameter based on the first set of points and the second set of points;基于所述第一点集合和所述第三点集合,确定针对所述第二外参数的第二评价度量;以及determining a second evaluation metric for the second extrinsic parameter based on the first set of points and the third set of points; and响应于所述第一评价度量与所述第二评价度量的差异小于第一阈值,将所述第二外参数确定为与所述第一图像相对应的所述外参数。The second extrinsic parameter is determined as the extrinsic parameter corresponding to the first image in response to the difference between the first evaluation metric and the second evaluation metric being less than a first threshold.5.根据权利要求4所述的方法,其中所述第一评价度量指示以下中的至少一项:所述第一点集合与所述第二点集合的距离,或者所述第一点集合和所述第二点集合中匹配点对的数目,其中所述匹配点对中的点与另一点的距离小于第二阈值距离。5. The method of claim 4, wherein the first evaluation metric indicates at least one of: a distance between the first set of points and the second set of points, or the first set of points and the The number of matching point pairs in the second set of points, wherein a point in the matching point pair is less than a second threshold distance from another point.6.根据权利要求4所述的方法,其中从所述第一外参数和所述第二外参数确定与所述第一图像相对应的外参数还包括:6. The method of claim 4, wherein determining an extrinsic parameter corresponding to the first image from the first extrinsic parameter and the second extrinsic parameter further comprises:响应于所述第一评价度量与所述第二评价度量的差异大于或等于所述第一阈值,将所述第一外参数确定为与所述第一图像相对应的所述外参数。The first extrinsic parameter is determined as the extrinsic parameter corresponding to the first image in response to the difference between the first evaluation metric and the second evaluation metric being greater than or equal to the first threshold.7.根据权利要求4至6中任一项所述的方法,还包括:7. The method of any one of claims 4 to 6, further comprising:基于所述相机的默认外参数和所述位置信息,从所述第一图像中确定第四点集合;determining a fourth set of points from the first image based on default extrinsic parameters of the camera and the location information;基于所述第一点集合和所述第四点集合,确定针对所述默认外参数的第三评价度量,所述第三评价度量指示以下中的至少一项:所述第一点集合与所述第四点集合的距离,或者所述第一点集合和所述第四点集合中匹配点对的数目;Based on the first set of points and the fourth set of points, a third evaluation metric for the default extrinsic parameter is determined, the third evaluation metric indicating at least one of the following: the first set of points and the the distance of the fourth point set, or the number of matching point pairs in the first point set and the fourth point set;从所述第一评价度量和所述第二评价度量中确定针对经确定的所述外参数的第四评价度量;以及determining a fourth evaluation metric for the determined extrinsic parameter from the first evaluation metric and the second evaluation metric; and响应于所述第四评价度量与所述第三评价度量的差异大于或等于第二阈值,利用所述相机的所述默认外参数更新经确定的所述外参数。The determined extrinsic parameters are updated with the default extrinsic parameters of the camera in response to a difference between the fourth evaluation metric and the third evaluation metric being greater than or equal to a second threshold.8.根据权利要求1所述的方法,还包括:8. The method of claim 1, further comprising:确定第一点集合中用于确定所述外参数的点的数目;以及determining the number of points in the first set of points used to determine the extrinsic parameter; and响应于所述数目小于预定的数目阈值,利用所述相机的默认外参数更新经确定的所述外参数。In response to the number being less than a predetermined number threshold, the determined extrinsic parameters are updated with default extrinsic parameters of the camera.9.根据权利要求1所述的方法,还包括:9. The method of claim 1, further comprising:响应于从所述第一图像检测到障碍物,确定所述第一图像中与所述障碍物对应的区域;以及in response to detecting an obstacle from the first image, determining a region in the first image corresponding to the obstacle; and基于所述外参数和所述区域,确定所述障碍物在所述世界坐标系中的位置。Based on the extrinsic parameters and the region, the position of the obstacle in the world coordinate system is determined.10.根据权利要求9所述的方法,还包括:10. The method of claim 9, further comprising:提供所述障碍物的所述位置。The location of the obstacle is provided.11.一种用于相机标定的装置,包括:11. An apparatus for camera calibration, comprising:第一外参数确定模块,被配置为基于从由相机所捕获的第一图像中确定与预定的参考线对应的第一点集合和所述第一图像中基于所述参考线在三维地图中的位置信息确定的第二点集合,确定所述相机的第一外参数,所述第一外参数指示相机坐标系与世界坐标系的转换关系;A first extrinsic parameter determination module configured to determine a first set of points corresponding to a predetermined reference line from a first image captured by the camera and a first set of points in the first image based on the reference line in the three-dimensional map The second set of points determined by the position information determines the first external parameter of the camera, where the first external parameter indicates the conversion relationship between the camera coordinate system and the world coordinate system;第二外参数获取模块,被配置为获取所述相机的第二外参数,所述第二外参数基于所述相机先前捕获的第二图像而被确定;A second extrinsic parameter acquisition module configured to acquire a second extrinsic parameter of the camera, the second extrinsic parameter being determined based on a second image previously captured by the camera;第三点集合确定模块,被配置为基于所述第二外参数和所述位置信息,从所述第一图像中确定第三点集合;以及a third set of points determination module configured to determine a third set of points from the first image based on the second extrinsic parameter and the location information; and第一外参数选择模块,被配置为基于第一点集合、所述第二点集合以及所述第三点集合,从所述第一外参数和所述第二外参数中确定与所述第一图像相对应的外参数。A first extrinsic parameter selection module is configured to, based on the first set of points, the second set of points, and the third set of points, determine from the first extrinsic parameter and the second extrinsic parameter the difference between the first extrinsic parameter and the second extrinsic parameter. The extrinsic parameters corresponding to an image.12.根据权利要求11所述的装置,其中所述第一外参数确定模块包括:12. The apparatus of claim 11, wherein the first extrinsic parameter determination module comprises:第一调整模块,被配置为响应于所述第一点集合与所述第二点集合的距离大于预定的阈值,调整所述相机的初始外参数,其中所述距离基于所述第二点集合中的点与所述第一点集合中的对应点之间的距离而确定;a first adjustment module configured to adjust an initial extrinsic parameter of the camera in response to a distance between the first set of points and the second set of points being greater than a predetermined threshold, wherein the distance is based on the second set of points is determined by the distance between the point in the first point set and the corresponding point in the first point set;更新模块,被配置为基于经调整的初始外参数确定经更新的第二点集合;以及an update module configured to determine an updated second set of points based on the adjusted initial extrinsic parameters; and第一外参数输出模块,被配置为响应于所述第一点集合与所述经更新的第二点集合的距离小于或等于第一阈值距离,将经调整的初始外参数确定为所述相机的所述第一外参数。a first extrinsic parameter output module configured to determine an adjusted initial extrinsic parameter as the camera in response to the distance between the first set of points and the updated second set of points being less than or equal to a first threshold distance The first external parameter of .13.根据权利要求12所述的装置,其中所述第一调整模块包括:13. The apparatus of claim 12, wherein the first adjustment module comprises:雅可比矩阵确定模块,确定所述距离关于所述外参数的雅可比矩阵;以及a Jacobian matrix determination module that determines a Jacobian matrix of the distance with respect to the extrinsic parameter; and第二调整模块,被配置为基于所述雅可比矩阵调整所述初始外参数。A second adjustment module configured to adjust the initial extrinsic parameter based on the Jacobian matrix.14.根据权利要求11所述的装置,其中所述第一外参数选择模块包括:14. The apparatus of claim 11, wherein the first extrinsic parameter selection module comprises:第一评价度量确定模块,被配置为基于所述第一点集合和所述第二点集合,确定针对所述第一外参数的第一评价度量;a first evaluation metric determination module configured to determine a first evaluation metric for the first extrinsic parameter based on the first set of points and the second set of points;第二评价度量确定模块,被配置为基于所述第一点集合和所述第三点集合,确定针对所述第二外参数的第二评价度量;以及A second evaluation metric determination module configured to determine a second evaluation metric for the second extrinsic parameter based on the first set of points and the third set of points; and第二外参数选择模块,被配置为响应于所述第一评价度量与所述第二评价度量的差小于第一阈值,将所述第二外参数确定为与所述第一图像相对应的所述外参数。A second extrinsic parameter selection module configured to determine the second extrinsic parameter as corresponding to the first image in response to the difference between the first evaluation metric and the second evaluation metric being less than a first threshold the external parameters.15.根据权利要求14所述的装置,其中所述第一评价度量指示以下中的至少一项:所述第一点集合与所述第二点集合的距离,或者所述第一点集合和所述第二点集合中匹配点对的数目,其中所述匹配点对中的点与另一点的距离小于第二阈值距离。15. The apparatus of claim 14, wherein the first evaluation metric indicates at least one of: a distance of the first set of points from the second set of points, or the first set of points and the The number of matching point pairs in the second set of points, wherein a point in the matching point pair is less than a second threshold distance from another point.16.根据权利要求14所述的装置,所述第一外参数选择模块还包括:16. The apparatus of claim 14, the first extrinsic parameter selection module further comprising:第三外参数选择模块,响应于所述第一评价度量与所述第二评价度量的差大于或等于所述第一阈值,将所述第一外参数确定为与所述第一图像相对应的所述外参数。A third extrinsic parameter selection module, in response to the difference between the first evaluation metric and the second evaluation metric being greater than or equal to the first threshold, determining the first extrinsic parameter as corresponding to the first image of the external parameters.17.根据权利要求14至16中任一项所述的装置,还包括:17. The apparatus of any one of claims 14 to 16, further comprising:第四点集合确定模块,被配置为基于所述相机的默认外参数和所述位置信息,从所述第一图像中确定第四点集合;a fourth point set determination module configured to determine a fourth point set from the first image based on default extrinsic parameters of the camera and the location information;第三评价度量确定模块,被配置为基于所述第一点集合和所述第四点集合,确定针对所述默认外参数的第三评价度量,所述第三评价度量指示以下中的至少一项:所述第一点集合与所述第四点集合的距离,或者所述第一点集合和所述第四点集合中匹配点对的数目;A third evaluation metric determination module configured to determine a third evaluation metric for the default extrinsic parameter based on the first set of points and the fourth set of points, the third evaluation metric indicating at least one of the following Item: the distance between the first point set and the fourth point set, or the number of matching point pairs in the first point set and the fourth point set;第四评价度量确定模块,被配置为从所述第一评价度量和所述第二评价度量中确定针对经确定的所述外参数的第四评价度量;以及a fourth evaluation metric determination module configured to determine a fourth evaluation metric for the determined extrinsic parameter from the first evaluation metric and the second evaluation metric; and第一外参数更新模块,被配置为响应于所述第四评价度量与所述第三评价度量的差异大于或等于第二阈值,利用所述相机的所述默认外参数更新经确定的所述外参数。a first extrinsic parameter update module configured to update the determined extrinsic parameter with the default extrinsic parameter of the camera in response to the difference between the fourth evaluation metric and the third evaluation metric being greater than or equal to a second threshold external parameters.18.根据权利要求11所述的装置,还包括:18. The apparatus of claim 11, further comprising:数目确定模块,被配置为确定第一点集合中用于确定所述外参数的点的数目;以及a number determination module configured to determine the number of points in the first set of points for determining the extrinsic parameter; and第二外参数更新模块,被配置为响应于所述数目小于预定的数目阈值,利用所述相机的默认外参数更新经确定的所述外参数。A second extrinsic parameter update module configured to update the determined extrinsic parameters with default extrinsic parameters of the camera in response to the number being less than a predetermined number threshold.19.根据权利要求11所述的装置,还包括:19. The apparatus of claim 11, further comprising:区域确定模块,被配置为响应于从所述第一图像检测到障碍物,确定所述第一图像中与所述障碍物对应的区域;以及an area determination module configured to, in response to detecting an obstacle from the first image, determine an area in the first image corresponding to the obstacle; and位置确定模块,被配置为基于所述外参数和所述区域,确定所述障碍物在所述世界坐标系中的位置。A position determination module is configured to determine a position of the obstacle in the world coordinate system based on the extrinsic parameter and the region.20.根据权利要求19所述的装置,还包括:20. The apparatus of claim 19, further comprising:提供模块,被配置为提供所述障碍物的所述位置。A providing module is configured to provide the location of the obstacle.21.一种电子设备,所述设备包括:21. An electronic device comprising:一个或多个处理器;以及one or more processors; and存储装置,用于存储一个或多个程序,当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如权利要求1-10中任一项所述的方法。storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement any one of claims 1-10 method described in item.22.一种计算机可读存储介质,其上存储有计算机程序,所述程序被处理器执行时实现如权利要求1-10中任一项所述的方法。22. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of claims 1-10.
CN201911001867.8A2019-10-212019-10-21Method, device, equipment and storage medium for camera calibrationActiveCN110766760B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201911001867.8ACN110766760B (en)2019-10-212019-10-21Method, device, equipment and storage medium for camera calibration

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201911001867.8ACN110766760B (en)2019-10-212019-10-21Method, device, equipment and storage medium for camera calibration

Publications (2)

Publication NumberPublication Date
CN110766760A CN110766760A (en)2020-02-07
CN110766760Btrue CN110766760B (en)2022-08-02

Family

ID=69332809

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201911001867.8AActiveCN110766760B (en)2019-10-212019-10-21Method, device, equipment and storage medium for camera calibration

Country Status (1)

CountryLink
CN (1)CN110766760B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN111462251B (en)*2020-04-072021-05-11深圳金三立视频科技股份有限公司Camera calibration method and terminal
CN112771577A (en)*2020-05-282021-05-07深圳市大疆创新科技有限公司Camera parameter determination method, device and readable storage medium
CN112381876B (en)*2021-01-182021-04-16中智行科技有限公司Traffic sign marking method and device and computer equipment
CN113284194B (en)*2021-06-222024-06-11智道网联科技(北京)有限公司Calibration method, device and equipment of multiple RS equipment
CN113409405B (en)*2021-07-192024-07-05江苏普衡诺信息科技有限公司Method, device, equipment and storage medium for evaluating camera calibration position
CN117274392A (en)*2022-06-132023-12-22华为技术有限公司 Camera internal parameter calibration methods and related equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN107862719A (en)*2017-11-102018-03-30未来机器人(深圳)有限公司Scaling method, device, computer equipment and the storage medium of Camera extrinsic
CN109379521A (en)*2018-11-302019-02-22Oppo广东移动通信有限公司 Camera calibration method, device, computer equipment and storage medium
CN109523597A (en)*2017-09-182019-03-26百度在线网络技术(北京)有限公司The scaling method and device of Camera extrinsic
CN110135376A (en)*2019-05-212019-08-16北京百度网讯科技有限公司 Method, device and medium for determining coordinate system conversion parameters of image sensor

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US9930315B2 (en)*2015-04-292018-03-27Lucid VR, Inc.Stereoscopic 3D camera for virtual reality experience

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN109523597A (en)*2017-09-182019-03-26百度在线网络技术(北京)有限公司The scaling method and device of Camera extrinsic
CN107862719A (en)*2017-11-102018-03-30未来机器人(深圳)有限公司Scaling method, device, computer equipment and the storage medium of Camera extrinsic
CN109379521A (en)*2018-11-302019-02-22Oppo广东移动通信有限公司 Camera calibration method, device, computer equipment and storage medium
CN110135376A (en)*2019-05-212019-08-16北京百度网讯科技有限公司 Method, device and medium for determining coordinate system conversion parameters of image sensor

Also Published As

Publication numberPublication date
CN110766760A (en)2020-02-07

Similar Documents

PublicationPublication DateTitle
CN110766760B (en)Method, device, equipment and storage medium for camera calibration
CN110751693B (en)Method, apparatus, device and storage medium for camera calibration
CN110378965B (en)Method, device and equipment for determining coordinate system conversion parameters of road side imaging equipment
AU2018282302B2 (en)Integrated sensor calibration in natural scenes
TWI722355B (en)Systems and methods for correcting a high-definition map based on detection of obstructing objects
CN110766761B (en) Methods, devices, equipment and storage media for camera calibration
CN108692719B (en) Object detection device
CN110119698B (en) Method, apparatus, device and storage medium for determining the state of an object
JP5588812B2 (en) Image processing apparatus and imaging apparatus using the same
CN110148185A (en)Determine method, apparatus, electronic equipment and the storage medium of coordinate system conversion parameter
CN108802785A (en)Vehicle method for self-locating based on High-precision Vector map and monocular vision sensor
US10996337B2 (en)Systems and methods for constructing a high-definition map based on landmarks
CN110147382A (en)Lane line update method, device, equipment, system and readable storage medium storing program for executing
CN110728720B (en)Method, apparatus, device and storage medium for camera calibration
CN112700486B (en)Method and device for estimating depth of road surface lane line in image
CN114140533B (en) Camera extrinsic parameter calibration method and device
CN116403186B (en)FPN Swin Transformer and Pointnet ++ based automatic driving three-dimensional target detection method
JP2017181476A (en) Vehicle position detection device, vehicle position detection method, and computer program for vehicle position detection
KR20240022986A (en)METHODS AND APPARATUS FOR ESTIMATION OF THE DISTANCE OF THE OBJECTS IN EUCLIDEAN SPACE USING FUSION OF CAMERA POSE INFORMATION and SCENE PRIOR INFORMATION'S AND THEREOF
CN109949355A (en) A Method of Establishing Half-sector Isometric Line Model in Monocular Vision Pedestrian Distance Estimation
WO2022133986A1 (en)Accuracy estimation method and system
CN115597498A (en) A Method for Positioning and Velocity Estimation of Unmanned Aerial Vehicle
CN116358499A (en)Vehicle positioning system
CN117953046A (en)Data processing method, device, controller, vehicle and storage medium

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp