CN111967384A - Vehicle information processing method, device, equipment and computer readable storage medium - Google Patents
Vehicle information processing method, device, equipment and computer readable storage mediumDownload PDFInfo
- Publication number
- CN111967384A CN111967384ACN202010823943.XACN202010823943ACN111967384ACN 111967384 ACN111967384 ACN 111967384ACN 202010823943 ACN202010823943 ACN 202010823943ACN 111967384 ACN111967384 ACN 111967384A
- Authority
- CN
- China
- Prior art keywords
- road
- target vehicle
- information
- vehicle
- center point
- 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.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本公开涉及智慧交通领域，尤其涉及一种车辆信息处理方法、装置、设备及计算机可读存储介质。The present disclosure relates to the field of intelligent transportation, and in particular, to a vehicle information processing method, apparatus, device, and computer-readable storage medium.
背景技术Background technique
随着交通的不断发展，路面上车辆越来越多，因此，如何确保交通安全也变成了亟待解决的问题。With the continuous development of traffic, there are more and more vehicles on the road. Therefore, how to ensure traffic safety has become an urgent problem to be solved.
为了实现对路面上车辆是否正常行驶进行判断，现有技术中，深度学习技术已广泛应用在交通领域，例如通过目标检测、道路分割等方式对实际的路口场景进行识别，根据路口场景中的道路标志线、交通信号灯等信息辅助判断车辆是否存在违法驾驶的行为。In order to judge whether the vehicle on the road is driving normally, in the prior art, deep learning technology has been widely used in the field of transportation, for example, the actual intersection scene is identified through object detection, road segmentation, etc., according to the road in the intersection scene. Information such as sign lines, traffic lights and other information assists in judging whether the vehicle has illegal driving behavior.
但是，采用上述方法进行车辆信息处理时，由于往往需要道路标志线、交通信号灯等信息进行辅助判断，因此，往往仅适用于城镇街道路口。而对于未设置有上述交通信息的单一道路的交通场景，上述方法无法准确地对车辆是否存在违法驾驶行为进行判断，进而无法保证单一道路的交通场景的交通安全。However, when the above method is used for vehicle information processing, information such as road markings and traffic lights are often required to assist judgment, so it is often only applicable to urban street intersections. However, for the traffic scene of a single road without the above-mentioned traffic information, the above method cannot accurately judge whether the vehicle has illegal driving behavior, and thus cannot guarantee the traffic safety of the traffic scene of a single road.
发明内容SUMMARY OF THE INVENTION
本公开提供一种车辆信息处理方法、装置、设备及计算机可读存储介质，用于解决现有技术无法准确地对车辆是否存在违法驾驶行为进行判断，进而无法保证单一道路的交通场景的交通安全的技术问题。The present disclosure provides a vehicle information processing method, device, device, and computer-readable storage medium, which are used to solve the problem that the prior art cannot accurately determine whether a vehicle has illegal driving behavior, and thus cannot guarantee the traffic safety of a single road traffic scene technical issues.
本公开的第一个方面是提供一种车辆信息处理方法，包括：A first aspect of the present disclosure is to provide a vehicle information processing method, including:
获取图像采集装置采集到的路面图像；Acquiring the road surface image collected by the image collecting device;
识别所述路面图像中的道路信息；identifying road information in the road surface image;
在所述道路信息中识别目标车辆，并确定各所述目标车辆对应的中心点信息；Identify target vehicles in the road information, and determine center point information corresponding to each of the target vehicles;
根据所述中心点信息以及安全行驶区域，判断所述目标车辆是否安全行驶，获得判断结果，其中，所述安全行驶区域是根据所述道路信息的中心线以及预设的范围阈值确定的。According to the center point information and the safe driving area, it is judged whether the target vehicle is driving safely, and a judgment result is obtained, wherein the safe driving area is determined according to the center line of the road information and a preset range threshold.
本公开的第二个方面是提供一种车辆信息处理装置，包括：A second aspect of the present disclosure is to provide a vehicle information processing device, including:
获取模块，用于获取图像采集装置采集到的路面图像；an acquisition module, used for acquiring the road surface image collected by the image collection device;
识别模块，用于识别所述路面图像中的道路信息；an identification module for identifying road information in the road surface image;
确定模块，用于在所述道路信息中识别目标车辆，并确定各所述目标车辆对应的中心点信息；a determination module, used for identifying target vehicles in the road information, and determining the center point information corresponding to each of the target vehicles;
判断模块，用于根据所述中心点信息以及安全行驶区域，判断所述目标车辆是否安全行驶，获得判断结果，其中，所述安全行驶区域是根据所述道路信息的中心线以及预设的范围阈值确定的。a judging module for judging whether the target vehicle is driving safely according to the center point information and the safe driving area, and obtaining a judgment result, wherein the safe driving area is a center line and a preset range according to the road information Threshold is determined.
本公开的第三个方面是提供一种车辆信息处理设备，包括：存储器，处理器；A third aspect of the present disclosure is to provide a vehicle information processing device, including: a memory, and a processor;
存储器；用于存储所述处理器可执行指令的存储器；memory; memory for storing instructions executable by the processor;
其中，所述处理器被配置为由所述处理器执行如第一方面所述的车辆信息处理方法。Wherein, the processor is configured to execute the vehicle information processing method according to the first aspect by the processor.
本公开的第四个方面是提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，所述计算机执行指令被处理器执行时用于实现如第一方面所述的车辆信息处理方法。A fourth aspect of the present disclosure is to provide a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, are used to implement the first aspect The vehicle information processing method.
本公开提供的车辆信息处理方法、装置、设备及计算机可读存储介质，通过在获取到路面图像之后，对路面图像进行图像处理操作，以确定该路面中目标车辆的中心点信息。进而可以根据该中心点信息以及预设的安全行驶区域，确定当前目标车辆是否安全行驶，其中，该安全行驶区域是根据识别到的道路信息的中心线以及预设的范围阈值确定的。上述方法无需采用其他道路中的交通要素，例如道路标志线、交通信号灯等，进行辅助计算，从而能够适用于各种道路的交通场景，有效地时限了对单一道路的交通场景下车辆是否安全行驶的识别操作，保证了单一道路的交通场景的交通安全。The vehicle information processing method, device, device, and computer-readable storage medium provided by the present disclosure determine center point information of a target vehicle on the road surface by performing image processing operations on the road surface image after acquiring the road surface image. Further, it can be determined whether the current target vehicle is driving safely according to the center point information and a preset safe driving area, wherein the safe driving area is determined according to the center line of the identified road information and a preset range threshold. The above method does not need to use traffic elements in other roads, such as road signs, traffic lights, etc., for auxiliary calculation, so that it can be applied to various road traffic scenarios, and effectively time limit whether the vehicle is safe to drive in a single road traffic scenario. The identification operation ensures the traffic safety of the traffic scene of a single road.
附图说明Description of drawings
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本公开的一些实施例，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。In order to explain the embodiments of the present disclosure or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are For some embodiments of the present disclosure, those of ordinary skill in the art can also obtain other drawings according to these drawings.
图1为本公开基于的网络架构示意图；1 is a schematic diagram of a network architecture on which the present disclosure is based;
图2为本公开实施例一提供的车辆信息处理方法的流程示意图；2 is a schematic flowchart of a vehicle information processing method provided in Embodiment 1 of the present disclosure;
图3为本公开实施例提供的场景示意图；FIG. 3 is a schematic diagram of a scenario provided by an embodiment of the present disclosure;
图4为本公开实施例二提供的车辆信息处理方法的流程示意图；4 is a schematic flowchart of a vehicle information processing method provided in
图5为本公开实施例三提供的车辆信息处理方法的流程示意图；5 is a schematic flowchart of a vehicle information processing method provided in
图6为本公开实施例提供的中心点示意图；FIG. 6 is a schematic diagram of a center point provided by an embodiment of the present disclosure;
图7为本公开实施例四提供的车辆信息处理方法的流程示意图；FIG. 7 is a schematic flowchart of a vehicle information processing method provided in Embodiment 4 of the present disclosure;
图8为本公开实施例五提供的车辆信息处理装置的结构示意图；FIG. 8 is a schematic structural diagram of a vehicle information processing device provided in Embodiment 5 of the present disclosure;
图9为本公开实施例六提供的车辆信息处理装置的结构示意图；FIG. 9 is a schematic structural diagram of a vehicle information processing device according to Embodiment 6 of the present disclosure;
图10为本公开实施例七提供的车辆信息处理装置的结构示意图；FIG. 10 is a schematic structural diagram of a vehicle information processing device provided in Embodiment 7 of the present disclosure;
图11为本公开实施例八提供的车辆信息处理装置的结构示意图；FIG. 11 is a schematic structural diagram of a vehicle information processing device provided in Embodiment 8 of the present disclosure;
图12为本公开实施例九提供的车辆信息处理设备的结构示意图。FIG. 12 is a schematic structural diagram of a vehicle information processing device according to Embodiment 9 of the present disclosure.
具体实施方式Detailed ways
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例所获得的所有其他实施例，都属于本公开保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments These are some, but not all, embodiments of the present disclosure. All other embodiments obtained based on the embodiments in the present disclosure fall within the protection scope of the present disclosure.
针对上述提及的现有技术无法准确地对车辆是否存在违法驾驶行为进行判断，进而无法保证单一道路的交通场景的交通安全的技术问题，本公开提供了一种车辆信息处理方法、装置、设备及计算机可读存储介质。In view of the above-mentioned technical problem that the prior art cannot accurately judge whether the vehicle has illegal driving behavior, and thus cannot guarantee the traffic safety of the traffic scene of a single road, the present disclosure provides a vehicle information processing method, device and equipment and computer-readable storage media.
需要说明的是，本公开提供车辆信息处理方法、装置、设备及计算机可读存储介质可运用在各种路况下对车辆行驶状态判断的场景中。It should be noted that the present disclosure provides a vehicle information processing method, apparatus, device, and computer-readable storage medium, which can be used in scenarios of judging the driving state of a vehicle under various road conditions.
为了实现对道路中的车辆是否安全行驶的识别，现有技术中在获取到路面图像之后，一般都需要额外采用道路中的道路标志线、交通信号灯等交通元素作为辅助实现识别操作。但是，上述方法仅适用于设置有道路标志线、交通信号灯的城镇街路口，而未设置有道路标志线、交通信号灯的单一道路，上述方法则无法进行准确地识别。In order to realize the identification of whether the vehicle on the road is driving safely, in the prior art, after the road surface image is acquired, it is generally necessary to additionally use traffic elements such as road markings and traffic lights in the road as an auxiliary to realize the identification operation. However, the above method is only applicable to urban street intersections with road markings and traffic lights, and a single road without road markings and traffic lights, so the above methods cannot accurately identify.
在解决上述技术问题的过程中，发明人通过研究发现，在获取到图像采集装置采集到的路面图像之后，可以对该路面图像进行图像处理操作，确定路面中的目标车辆的中心点信息。从而后续可以根据该中心点信息以及安全行驶区域判断目标车辆是否在安全行驶区域内安全行驶，无需采用其他交通要素作为辅助计算，适用于各种交通场景。In the process of solving the above technical problems, the inventor found through research that after acquiring the road surface image collected by the image acquisition device, image processing operations can be performed on the road surface image to determine the center point information of the target vehicle on the road surface. Therefore, it can be determined whether the target vehicle is driving safely in the safe driving area according to the center point information and the safe driving area in the future, without using other traffic elements as auxiliary calculation, which is suitable for various traffic scenarios.
图1为本公开基于的网络架构示意图，如图1所示，本公开基于的网络架构至少包括：图像采集装置1以及服务器2，其中，服务器2中设置有车辆信息处理装置。该车辆信息装置采用C/C++、Java、Shell或Python等语言编写；图像采集装置1则可以为相机、监控设备等任意一种能够实现图像采集的装置。该图像采集装置1与服务器2通信连接，从而二者能够进行信息交互。FIG. 1 is a schematic diagram of the network architecture on which the present disclosure is based. As shown in FIG. 1 , the network architecture on which the present disclosure is based at least includes: an image acquisition device 1 and a
图2为本公开实施例一提供的车辆信息处理方法的流程示意图，如图2所示，该方法包括：FIG. 2 is a schematic flowchart of a vehicle information processing method provided in Embodiment 1 of the present disclosure. As shown in FIG. 2 , the method includes:
步骤101、获取图像采集装置采集到的路面图像。Step 101: Acquire a road surface image collected by an image collection device.
本实施例的执行主体为车辆信息处理装置，该车辆信息处理装置可耦合于服务器中。该服务器与图像采集装置通信连接，从而能够与图像采集装置进行信息交互。The execution body of this embodiment is a vehicle information processing apparatus, and the vehicle information processing apparatus may be coupled to the server. The server is connected in communication with the image acquisition device, so that information can be exchanged with the image acquisition device.
在本实施例中，车辆信息处理装置可以获取图像采集装置采集到的路面图像。其中，该图像采集装置具体可以为相机、监控等任意一种设置在路面上，能够拍摄到路面图像的图像采集装置。相应地，该路面图像可以为监控设备采集到的路面上的图像。In this embodiment, the vehicle information processing apparatus may acquire the road surface image collected by the image collection apparatus. Wherein, the image acquisition device may specifically be an image acquisition device that is installed on the road surface, such as a camera, a monitor, etc., and can capture images of the road surface. Correspondingly, the road surface image may be an image on the road surface collected by the monitoring device.
该图像采集装置可以实时采集路面图像并传输，也可以按照预设的时间阈值进行路面图像的采集，本公开对此不做限制。The image acquisition device can collect road images in real time and transmit them, and can also collect road images according to a preset time threshold, which is not limited in the present disclosure.
进一步地，在实施例一的基础上，步骤101之后，还包括：Further, on the basis of Embodiment 1, after
对所述路面图像进行尺寸重塑操作和/或灰度归一化和/或亮度归一化处理。Resize and/or grayscale normalization and/or brightness normalization are performed on the road image.
在本实施方式中，由于不同路段上设置的图像采集装置可能存在差异，因此，在获取到路面图像之后，为了提高后续图像处理的效率以及精度，可以对该路面图像进行尺寸重塑操作，使得每一个图像采集装置采集到的路面图像均具有相同的尺寸。此外，还可以对路面图像进行灰度归一化、亮度归一化等操作。上述三种不同的预处理方法可以单独实施，也可以结合实施，本公开对此不做限制。In this embodiment, since there may be differences in the image acquisition devices set on different road sections, after the road image is acquired, in order to improve the efficiency and accuracy of subsequent image processing, the road image may be resized so that the road image can be resized. The road images collected by each image collection device have the same size. In addition, operations such as grayscale normalization and brightness normalization can also be performed on the road image. The above three different preprocessing methods can be implemented independently or in combination, which is not limited in the present disclosure.
步骤102、识别所述路面图像中的道路信息。Step 102: Identify road information in the road surface image.
在本实施方式中，图像采集装置采集到的路面图像中可能包含有很多信息，例如可能包括路侧的树木、房屋等信息。但是上述信息往往作用不大。因此，在获取到路面图像之后，可以识别该路面图像中的道路信息。In this embodiment, the road image collected by the image collection device may contain a lot of information, for example, information such as trees and houses on the roadside may be included. But the above information is often of little use. Therefore, after the road surface image is acquired, the road information in the road surface image can be recognized.
步骤103、在所述道路信息中识别目标车辆，并确定各所述目标车辆对应的中心点信息。Step 103: Identify target vehicles in the road information, and determine center point information corresponding to each of the target vehicles.
在本实施方式中，识别到路面图像中的道路信息之后，可以进一步地识别在该道路上行驶的目标车辆。此外，为了便于后续目标车辆位置的确定，在确定目标车辆之后，还可以分别确定各目标车辆对应的中心点信息，该中心点可以表征目标车辆的位置信息。In this embodiment, after the road information in the road surface image is recognized, the target vehicle traveling on the road can be further recognized. In addition, in order to facilitate the subsequent determination of the position of the target vehicle, after the target vehicle is determined, center point information corresponding to each target vehicle may be determined respectively, and the center point may represent the position information of the target vehicle.
步骤104、根据所述中心点信息以及安全行驶区域，判断所述目标车辆是否安全行驶，获得判断结果，其中，所述安全行驶区域是根据所述道路信息的中心线以及预设的范围阈值确定的。Step 104: Determine whether the target vehicle is driving safely according to the center point information and the safe driving area, and obtain a judgment result, wherein the safe driving area is determined according to the center line of the road information and a preset range threshold of.
在本实施方式中，由于中心点信息能够精准地表征目标车辆的位置信息，因此，可以根据该中心点信息以及安全行驶区域，来判断当前目标车辆是否安全行驶，获得判断结果。In this embodiment, since the center point information can accurately represent the position information of the target vehicle, it can be judged whether the current target vehicle is driving safely according to the center point information and the safe driving area, and the judgment result can be obtained.
需要说明的是，该安全行驶区域是根据道路信息的中心线以及预设的范围阈值确定的。该预设的范围阈值可以为中心线左右各1/2车道的范围。It should be noted that the safe driving area is determined according to the center line of the road information and a preset range threshold. The preset range threshold may be the range of 1/2 lanes on the left and right of the center line.
图3为本公开实施例提供的场景示意图，如图3所示，目标车辆在道路上行驶，可以根据中心点1以及安全行驶区域2确定车辆是否安全行驶。其中，该安全行驶区域2是根据道路的中心线3以及预设的范围阈值确定的。FIG. 3 is a schematic diagram of a scenario provided by an embodiment of the present disclosure. As shown in FIG. 3 , the target vehicle is driving on the road, and whether the vehicle is driving safely can be determined according to the center point 1 and the
具体地，在实施例一的基础上，步骤104具体包括：Specifically, on the basis of Embodiment 1, step 104 specifically includes:
若所述中心点信息在所述安全行驶区域内，则判定所述目标车辆安全行驶；If the center point information is within the safe driving area, determine that the target vehicle is driving safely;
若所述中心点信息不在所述安全行驶区域内，则判定所述目标车辆危险驾驶。If the center point information is not within the safe driving area, it is determined that the target vehicle is driving dangerously.
在本实施例中，若检测到中心点在安全行驶区域内，则可以判定目标车辆当前安全行驶。反之，若检测到中心点未在安全行驶区域内，则可以判定目标车辆当前未安全行驶。In this embodiment, if it is detected that the center point is within the safe driving area, it can be determined that the target vehicle is currently driving safely. On the contrary, if it is detected that the center point is not within the safe driving area, it can be determined that the target vehicle is not currently driving safely.
进一步地，在实施例一的基础上，步骤104之后，还包括：Further, on the basis of Embodiment 1, after
若所述目标车辆未安全行驶，则向执法机构发送报警信息，和/或，控制所述目标车辆进行危险驾驶的提醒。If the target vehicle does not drive safely, send an alarm message to a law enforcement agency, and/or control the target vehicle to remind the target vehicle to drive dangerously.
在本实施例中，为了保证交通安全，当检测到目标车辆未安全行驶时，需要向执法机构发送报警信息，或者可以控制目标车辆进行危险驾驶的提醒，以使司机及时进行驾驶模式的调整。In this embodiment, in order to ensure traffic safety, when it is detected that the target vehicle is not driving safely, an alarm message needs to be sent to the law enforcement agency, or the target vehicle can be controlled to warn of dangerous driving, so that the driver can adjust the driving mode in time.
本实施例提供的车辆信息处理方法，通过在获取到路面图像之后，对路面图像进行图像处理操作，以确定该路面中目标车辆的中心点信息。进而可以根据该中心点信息以及预设的安全行驶区域，确定当前目标车辆是否安全行驶，其中，该安全行驶区域是根据识别到的道路信息的中心线以及预设的范围阈值确定的。上述方法无需采用其他道路中的交通要素，例如道路标志线、交通信号灯等，进行辅助计算，从而能够适用于各种道路的交通场景，有效地时限了对单一道路的交通场景下车辆是否安全行驶的识别操作，保证了单一道路的交通场景的交通安全。The vehicle information processing method provided in this embodiment determines the center point information of the target vehicle on the road surface by performing an image processing operation on the road surface image after acquiring the road surface image. Further, it can be determined whether the current target vehicle is driving safely according to the center point information and a preset safe driving area, wherein the safe driving area is determined according to the center line of the identified road information and a preset range threshold. The above method does not need to use traffic elements in other roads, such as road signs, traffic lights, etc., for auxiliary calculation, so that it can be applied to various road traffic scenarios, and effectively time limit whether the vehicle is safe to drive in a single road traffic scenario. The identification operation ensures the traffic safety of the traffic scene of a single road.
图4为本公开实施例二提供的车辆信息处理方法的流程示意图，在实施例一的基础上，如图4所示，步骤102具体包括：FIG. 4 is a schematic flowchart of the vehicle information processing method provided in the second embodiment of the present disclosure. On the basis of the first embodiment, as shown in FIG. 4 , step 102 specifically includes:
步骤201、通过预设的分割网络识别所述路面图像中的道路区域。Step 201: Identify the road area in the road surface image through a preset segmentation network.
步骤202、对所述道路区域中进行像素连通区域检测操作，获得所述道路区域对应的边界信息。Step 202: Perform pixel connected area detection operation on the road area to obtain boundary information corresponding to the road area.
步骤203、采用线条对所述边界信息进行拟合操作，获得所述道路信息。
在本实施例中，为了实现对道路信息的识别，首先可以采用预设的分割网络识别路面图像中的道路区域。其中，该分割网络具体可以为pspnet、deeplab等任意一种能够实现交通场景分割的模型，本公开对此不作限制。In this embodiment, in order to realize the identification of road information, a preset segmentation network may be used to identify the road area in the road surface image first. Wherein, the segmentation network may specifically be any model capable of realizing traffic scene segmentation, such as pspnet and deeplab, which is not limited in the present disclosure.
进一步地，考虑到单纯的分割网络在分割结果中容易出现不连续的现象。因此，可以对道路区域进行像素联通区域检测操作，获得道路区域对应的边界信息。进而可以采用线条对边界信息进行拟合操作，获得道路信息。Further, considering that a pure segmentation network is prone to discontinuity in the segmentation results. Therefore, the pixel-connected area detection operation can be performed on the road area to obtain boundary information corresponding to the road area. Furthermore, lines can be used to fit the boundary information to obtain road information.
本实施例提供的车辆信息处理方法，通过分割网络识别道路区域，并对道路区域的边界进行处理，从而能够精准地识别出路面图像中的道路信息，为后续目标车辆是否安全行驶的识别提供了基础。The vehicle information processing method provided in this embodiment identifies the road area by segmenting the network, and processes the boundary of the road area, so that the road information in the road surface image can be accurately identified, and the subsequent identification of whether the target vehicle is safe to drive is provided. Base.
进一步地，在上述任一实施例的基础上，步骤103中识别所述路面图像中的道路信息具体包括：Further, on the basis of any of the above embodiments, identifying the road information in the road surface image in
通过预设的目标检测模型，检测所述道路信息中的全部车辆；Detect all vehicles in the road information through a preset target detection model;
通过预设的车辆类型识别模型，在所述全部车辆中识别全部机动车辆作为所述目标车辆。All motor vehicles are identified as the target vehicle among all the vehicles through a preset vehicle type identification model.
在本实施例中，由于乡村道路中经常会出现类似三轮车、两轮车当非机动车辆，因此，还需要对识别到的车辆信息进行进一步地的筛选操作。In this embodiment, since non-motor vehicles such as tricycles and two-wheelers often appear on rural roads, further screening operations need to be performed on the identified vehicle information.
具体地，首先可以采用目标检测模型，检测道路信息中的全部车辆。进一步地，可以采用车辆类型识别模型对全部车辆中的机动车辆进行识别，获得目标车辆。Specifically, first, a target detection model can be used to detect all vehicles in the road information. Further, the vehicle type identification model can be used to identify motor vehicles in all vehicles to obtain the target vehicle.
图5为本公开实施例三提供的车辆信息处理方法的流程示意图，在上述任一实施例的基础上，如图5所示，步骤103中确定各所述目标车辆对应的中心点信息，包括：FIG. 5 is a schematic flowchart of the vehicle information processing method provided in the third embodiment of the present disclosure. On the basis of any of the above embodiments, as shown in FIG. 5 , in
步骤301、通过预设的关键点检测模型，检测各所述目标车辆对应的预设数量个关键点信息。Step 301: Detect a preset number of key point information corresponding to each target vehicle by using a preset key point detection model.
步骤302、按照预设的连接规则对所述关键点信息进行连接，获得至少两条连接线信息，将所述至少两条连接线的交点作为所述中心点信息。Step 302: Connect the key point information according to a preset connection rule, obtain at least two connection line information, and use the intersection of the at least two connection lines as the center point information.
在本实施例中，在识别到目标车辆之后，还需要确定目标车辆对应的中心点信息。具体地，首先可以通过预设的关键点检测模型检测各目标车辆对应的预设数量个关键点信息。其中，该关键点可以为车辆轮廓上的关键点，例如车辆轮胎、底盘、车顶上的点灯。可以按照预设的连接规则对关键点进行连接操作，获得至少两条连接线信息，将连接线的交点作为中心点。In this embodiment, after the target vehicle is identified, the center point information corresponding to the target vehicle also needs to be determined. Specifically, firstly, a preset number of key point information corresponding to each target vehicle may be detected through a preset key point detection model. The key point may be a key point on the vehicle contour, such as vehicle tires, chassis, and lights on the roof. The key points can be connected according to the preset connection rules, and the information of at least two connecting lines can be obtained, and the intersection of the connecting lines can be regarded as the center point.
图6为本公开实施例提供的中心点示意图，如图6所示，该关键点具体可以为目标车辆的四个车顶点。分别连接车辆的对角线，获得连接线的交点，即中心点。FIG. 6 is a schematic diagram of a center point provided by an embodiment of the present disclosure. As shown in FIG. 6 , the key point may specifically be four vehicle vertices of the target vehicle. Connect the diagonal lines of the vehicles respectively, and obtain the intersection of the connecting lines, that is, the center point.
本实施例提供的车辆信息处理方法，通过识别目标车辆的关键点，并构建连接线，从而能够精准地确定能够用于表征目标车辆位置的中心点信息。The vehicle information processing method provided in this embodiment can accurately determine center point information that can be used to characterize the position of the target vehicle by identifying key points of the target vehicle and constructing connecting lines.
图7为本公开实施例四提供的车辆信息处理方法的流程示意图，在上述任一实施例的基础上，如图7所示，步骤103之后，还包括：FIG. 7 is a schematic flowchart of the vehicle information processing method provided in Embodiment 4 of the present disclosure. On the basis of any of the above embodiments, as shown in FIG. 7 , after
步骤401、针对每一目标车辆，分别确定所述目标车辆前一时刻对应的第一坐标，以及当前时刻对应的第二坐标。Step 401: For each target vehicle, determine the first coordinate corresponding to the target vehicle at the previous moment and the second coordinate corresponding to the current moment, respectively.
步骤402、根据所述第一坐标、第二坐标以及所述前一时刻与当前时刻的时间间隔，计算所述目标车辆的行驶速度。Step 402: Calculate the running speed of the target vehicle according to the first coordinate, the second coordinate, and the time interval between the previous moment and the current moment.
步骤403、根据所述行驶速度判断所述目标车辆是否超速驾驶。Step 403: Determine whether the target vehicle is overspeeding according to the driving speed.
在本实施例中，由于图像采集装置可以按照预设的时间间隔发送路面图像，而两个不同时刻下，同一个目标车辆在路面图像中的位置也会发生变化，因此，可以根据不同的位置信息以及预设的时间间隔来计算目标车辆的车速。In this embodiment, since the image acquisition device can send road images at preset time intervals, the position of the same target vehicle in the road image will also change at two different times. information and a preset time interval to calculate the speed of the target vehicle.
具体地，针对每一个目标车辆，可以分别确定该目标车辆在前一时刻对应的第一坐标(x0，y0)以及当前时刻的第二坐标(x1，y1)。根据第一坐标、第二坐标以及前一时刻与当前时刻的时间间隔，计算目标车辆的行驶速度。其中，行驶速度的计算公式可如公式1所示：Specifically, for each target vehicle, the first coordinate (x0 , y0 ) corresponding to the target vehicle at the previous moment and the second coordinate (x1 , y1 ) at the current moment may be determined respectively. According to the first coordinate, the second coordinate and the time interval between the previous time and the current time, the running speed of the target vehicle is calculated. Among them, the calculation formula of the driving speed can be shown in formula 1:
V＝{【[x0-x1]2+[y0-y1]2】0.5}*R/tV={[[x0 -x1 ]2 +[y0 -y1 ]2]0.5 }*R/t
其中，V为目标车辆的行驶速度，(x0，y0)为第一坐标，(x1，y1)为第二坐标，R为监控路口区域内设置的比例尺，t为预设的时间间隔。Among them, V is the running speed of the target vehicle, (x0 , y0 ) is the first coordinate, (x1 , y1 ) is the second coordinate, R is the scale set in the monitoring intersection area, and t is the preset time. interval.
进而可以根据该行驶速度来检测目标车辆是否超速行驶。具体地，可以将行驶速度与预设的速度阈值进行比对，若超过预设的速度阈值，则表征目标车辆超速行驶，反之，则表征目标车辆安全行驶。其中，该速度阈值可以根据具体的位置进行设置，本公开对此不做限制。Further, whether the target vehicle is overspeeding can be detected according to the traveling speed. Specifically, the traveling speed may be compared with a preset speed threshold. If the preset speed threshold is exceeded, it indicates that the target vehicle is overspeeding; otherwise, it indicates that the target vehicle is traveling safely. The speed threshold may be set according to a specific position, which is not limited in the present disclosure.
进一步地，若所述目标车辆未安全行驶，则向执法机构发送报警信息，和/或，控制所述目标车辆进行危险驾驶的提醒。Further, if the target vehicle does not drive safely, send an alarm message to a law enforcement agency, and/or control the target vehicle to warn of dangerous driving.
本实施例提供的车辆信息处理方法，通过根据目标的中心点以及预设的时间间隔对目标车辆的行驶速度进行计算，从而能够在不需要其他交通元素的辅助的基础上，精准地确定目标车辆是否超速行驶，保证了交通安全。In the vehicle information processing method provided in this embodiment, the running speed of the target vehicle is calculated according to the center point of the target and a preset time interval, so that the target vehicle can be accurately determined without the assistance of other traffic elements. Whether speeding, to ensure traffic safety.
图8为本公开实施例五提供的车辆信息处理装置的结构示意图，如图9所示，该装置包括：获取模块51、识别模块52、确定模块53以及判断模块54，其中，获取模块51，用于获取图像采集装置采集到的路面图像。识别模块52，用于识别所述路面图像中的道路信息。确定模块53，用于在所述道路信息中识别目标车辆，并确定各所述目标车辆对应的中心点信息。判断模块54，用于根据所述中心点信息以及安全行驶区域，判断所述目标车辆是否安全行驶，获得判断结果，其中，所述安全行驶区域是根据所述道路信息的中心线以及预设的范围阈值确定的。FIG. 8 is a schematic structural diagram of a vehicle information processing device provided in Embodiment 5 of the present disclosure. As shown in FIG. 9 , the device includes: an
进一步地，所述判断模块用于：若所述中心点信息在所述安全行驶区域内，则判定所述目标车辆安全行驶；若所述中心点信息不在所述安全行驶区域内，则判定所述目标车辆危险驾驶。Further, the judging module is configured to: if the center point information is within the safe driving area, determine that the target vehicle is driving safely; if the center point information is not within the safe driving area, determine that the target vehicle is traveling safely. Dangerous driving of the target vehicle.
进一步地，所述装置还包括：预处理模块，用于对所述路面图像进行尺寸重塑操作和/或灰度归一化和/或亮度归一化处理。Further, the apparatus further includes: a preprocessing module, configured to perform a size reshaping operation and/or grayscale normalization and/or brightness normalization processing on the road image.
进一步地，所述装置还包括：处理模块，用于若所述目标车辆未安全行驶，则向执法机构发送报警信息，和/或，控制所述目标车辆进行危险驾驶的提醒。Further, the device further includes: a processing module, configured to send alarm information to a law enforcement agency if the target vehicle does not drive safely, and/or control the target vehicle to remind the target vehicle to perform dangerous driving.
本实施例提供的车辆信息处理装置，通过在获取到路面图像之后，对路面图像进行图像处理操作，以确定该路面中目标车辆的中心点信息。进而可以根据该中心点信息以及预设的安全行驶区域，确定当前目标车辆是否安全行驶，其中，该安全行驶区域是根据识别到的道路信息的中心线以及预设的范围阈值确定的。上述方法无需采用其他道路中的交通要素，例如道路标志线、交通信号灯等，进行辅助计算，从而能够适用于各种道路的交通场景，有效地时限了对单一道路的交通场景下车辆是否安全行驶的识别操作，保证了单一道路的交通场景的交通安全。The vehicle information processing apparatus provided in this embodiment determines the center point information of the target vehicle on the road surface by performing an image processing operation on the road surface image after acquiring the road surface image. Further, it can be determined whether the current target vehicle is driving safely according to the center point information and a preset safe driving area, wherein the safe driving area is determined according to the center line of the identified road information and a preset range threshold. The above method does not need to use traffic elements in other roads, such as road signs, traffic lights, etc., for auxiliary calculation, so that it can be applied to various road traffic scenarios, and effectively time limit whether the vehicle is safe to drive in a single road traffic scenario. The identification operation ensures the traffic safety of the traffic scene of a single road.
图9为本公开实施例六提供的车辆信息处理装置的结构示意图，在实施例五的基础上，如图9所示，识别模块具体包括：识别单元61、检测单元62以及拟合单元63，其中，识别单元61，用于通过预设的分割网络识别所述路面图像中的道路区域。检测单元62，用于对所述道路区域中进行像素连通区域检测操作，获得所述道路区域对应的边界信息。拟合单元63，用于采用线条对所述边界信息进行拟合操作，获得所述道路信息。FIG. 9 is a schematic structural diagram of the vehicle information processing device provided in Embodiment 6 of the present disclosure. On the basis of Embodiment 5, as shown in FIG. 9 , the identification module specifically includes: an
进一步地，在上述任一实施例的基础上，确定模块包括：车辆检测单元以及目标车辆识别单元，其中，车辆检测单元，用于通过预设的目标检测模型，检测所述道路信息中的全部车辆；目标车辆识别单元，用于通过预设的车辆类型识别模型，在所述全部车辆中识别全部机动车辆作为所述目标车辆。Further, on the basis of any of the above embodiments, the determination module includes: a vehicle detection unit and a target vehicle identification unit, wherein the vehicle detection unit is used to detect all the road information through a preset target detection model a vehicle; a target vehicle identification unit, configured to identify all motor vehicles as the target vehicle from among all the vehicles through a preset vehicle type identification model.
图10为本公开实施例七提供的车辆信息处理装置的结构示意图，在上述任一实施例的基础上，如图10所示，所述确定模块包括：关键点检测单元71以及中心点确定单元72，其中，关键点检测单元71，用于通过预设的关键点检测模型，检测各所述目标车辆对应的预设数量个关键点信息；中心点确定单元72，用于按照预设的连接规则对所述关键点信息进行连接，获得至少两条连接线信息，将所述至少两条连接线的交点作为所述中心点信息。FIG. 10 is a schematic structural diagram of a vehicle information processing device provided in Embodiment 7 of the present disclosure. On the basis of any of the above embodiments, as shown in FIG. 10 , the determination module includes: a key
图11为本公开实施例八提供的车辆信息处理装置的结构示意图，在上述任一实施例的基础上，如图11所示，所述装置还包括：坐标确定模块81、计算模块82以及超速判断模块83，其中，坐标确定模块81，用于针对每一目标车辆，分别确定所述目标车辆前一时刻对应的第一坐标，以及当前时刻对应的第二坐标；计算模块82，用于根据所述第一坐标、第二坐标以及所述前一时刻与当前时刻的时间间隔，计算所述目标车辆的行驶速度；超速判断模块83，用于根据所述行驶速度判断所述目标车辆是否超速驾驶。FIG. 11 is a schematic structural diagram of the vehicle information processing device provided in the eighth embodiment of the present disclosure. On the basis of any of the above embodiments, as shown in FIG. 11 , the device further includes: a coordinate
图12为本公开实施例九提供的车辆信息处理设备的结构示意图，如图12所示，该设备包括：存储器91，处理器92；FIG. 12 is a schematic structural diagram of a vehicle information processing device provided in Embodiment 9 of the present disclosure. As shown in FIG. 12 , the device includes: a
存储器91；用于存储所述处理器92可执行指令的存储器91；
其中，所述处理器92被配置为由所述处理器92执行如上述任一实施例所述的车辆信息处理方法。Wherein, the
存储器91，用于存放程序。具体地，程序可以包括程序代码，所述程序代码包括计算机操作指令。存储器91可能包含高速RAM存储器，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。The
其中，处理器92可能是一个中央处理器(Central Processing Unit，简称为CPU)，或者是特定集成电路(Application Specific Integrated Circuit，简称为ASIC)，或者是被配置成实施本公开实施例的一个或多个集成电路。The
可选的，在具体实现上，如果存储器91和处理器92独立实现，则存储器91和处理器92可以通过总线相互连接并完成相互间的通信。所述总线可以是工业标准体系结构(Industry Standard Architecture，简称为ISA)总线、外部设备互连(PeripheralComponent，简称为PCI)总线或扩展工业标准体系结构(Extended Industry StandardArchitecture，简称为EISA)总线等。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图3中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。Optionally, in terms of specific implementation, if the
可选的，在具体实现上，如果存储器91和处理器92集成在一块芯片上实现，则存储器91和处理器92可以通过内部接口完成相同间的通信。Optionally, in terms of specific implementation, if the
本公开又一实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，所述计算机执行指令被处理器执行时用于实现如上述任一实施例所述的车辆信息处理方法。Yet another embodiment of the present disclosure further provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions are used to implement any of the foregoing embodiments The described vehicle information processing method.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here.
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps including the above method embodiments are executed; and the foregoing storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.
最后应说明的是：以上各实施例仅用以说明本公开的技术方案，而非对其限制；尽管参照前述各实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本公开各实施例技术方案的范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, but not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present disclosure. scope.
Claims (18)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010823943.XACN111967384A (en) | 2020-08-17 | 2020-08-17 | Vehicle information processing method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010823943.XACN111967384A (en) | 2020-08-17 | 2020-08-17 | Vehicle information processing method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111967384Atrue CN111967384A (en) | 2020-11-20 |
Family
ID=73389592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010823943.XAPendingCN111967384A (en) | 2020-08-17 | 2020-08-17 | Vehicle information processing method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967384A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732859A (en)* | 2021-01-25 | 2021-04-30 | 腾讯科技（深圳）有限公司 | Prompt information generation method and device, electronic equipment and storage medium |
| CN112990114A (en)* | 2021-04-21 | 2021-06-18 | 四川见山科技有限责任公司 | Traffic data visualization simulation method and system based on AI identification |
| CN113968229A (en)* | 2021-11-30 | 2022-01-25 | 广州文远知行科技有限公司 | Road area determination method and device and electronic equipment |
| CN114580505A (en)* | 2022-02-17 | 2022-06-03 | 中汽创智科技有限公司 | A vehicle wheel point detection method, device, device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102295004A (en)* | 2011-06-09 | 2011-12-28 | 中国人民解放军国防科学技术大学 | Lane departure warning method |
| CN103971521A (en)* | 2014-05-19 | 2014-08-06 | 清华大学 | Method and device for detecting road traffic abnormal events in real time |
| KR20150018988A (en)* | 2013-08-12 | 2015-02-25 | 현대모비스 주식회사 | Apparatus for monitoring state of road and system for providing safe driving service with the said apparatus |
| CN104778444A (en)* | 2015-03-10 | 2015-07-15 | 公安部交通管理科学研究所 | Method for analyzing apparent characteristic of vehicle image in road scene |
| CN107031623A (en)* | 2017-03-16 | 2017-08-11 | 浙江零跑科技有限公司 | A kind of road method for early warning based on vehicle-mounted blind area camera |
| CN108216242A (en)* | 2016-12-14 | 2018-06-29 | 现代自动车株式会社 | For the device and method that the limited road of vehicle is controlled to travel |
| CN110136254A (en)* | 2019-06-13 | 2019-08-16 | 吉林大学 | Driving assistance information display method based on dynamic probabilistic driving map |
| CN111540237A (en)* | 2020-05-19 | 2020-08-14 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
- 2020
- 2020-08-17CNCN202010823943.XApatent/CN111967384A/enactivePending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102295004A (en)* | 2011-06-09 | 2011-12-28 | 中国人民解放军国防科学技术大学 | Lane departure warning method |
| KR20150018988A (en)* | 2013-08-12 | 2015-02-25 | 현대모비스 주식회사 | Apparatus for monitoring state of road and system for providing safe driving service with the said apparatus |
| CN103971521A (en)* | 2014-05-19 | 2014-08-06 | 清华大学 | Method and device for detecting road traffic abnormal events in real time |
| CN104778444A (en)* | 2015-03-10 | 2015-07-15 | 公安部交通管理科学研究所 | Method for analyzing apparent characteristic of vehicle image in road scene |
| CN108216242A (en)* | 2016-12-14 | 2018-06-29 | 现代自动车株式会社 | For the device and method that the limited road of vehicle is controlled to travel |
| CN107031623A (en)* | 2017-03-16 | 2017-08-11 | 浙江零跑科技有限公司 | A kind of road method for early warning based on vehicle-mounted blind area camera |
| CN110136254A (en)* | 2019-06-13 | 2019-08-16 | 吉林大学 | Driving assistance information display method based on dynamic probabilistic driving map |
| CN111540237A (en)* | 2020-05-19 | 2020-08-14 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732859A (en)* | 2021-01-25 | 2021-04-30 | 腾讯科技（深圳）有限公司 | Prompt information generation method and device, electronic equipment and storage medium |
| CN112732859B (en)* | 2021-01-25 | 2022-05-06 | 腾讯科技（深圳）有限公司 | Prompt information generation method and device, electronic equipment and storage medium |
| CN112990114A (en)* | 2021-04-21 | 2021-06-18 | 四川见山科技有限责任公司 | Traffic data visualization simulation method and system based on AI identification |
| CN113968229A (en)* | 2021-11-30 | 2022-01-25 | 广州文远知行科技有限公司 | Road area determination method and device and electronic equipment |
| CN114580505A (en)* | 2022-02-17 | 2022-06-03 | 中汽创智科技有限公司 | A vehicle wheel point detection method, device, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112163543B (en) | A detection method and system for vehicles illegally occupying the road | |
| CN111967384A (en) | Vehicle information processing method, device, equipment and computer readable storage medium | |
| CN111212772B (en) | Method and apparatus for determining a driving strategy of a vehicle | |
| CN110619279B (en) | Road traffic sign instance segmentation method based on tracking | |
| CN108520634A (en) | High-speed ramp speed limit recognition method, device and electronic equipment | |
| CN111815959A (en) | Vehicle violation detection method and device and computer readable storage medium | |
| CN113469115B (en) | Method and device for outputting information | |
| WO2019223655A1 (en) | Detection of non-motor vehicle carrying passenger | |
| CN108133484B (en) | Automatic driving processing method and device based on scene segmentation and computing equipment | |
| CN104376297A (en) | Detection method and device for linear indication signs on road | |
| CN201825037U (en) | Lane departure alarm device for vehicles on highway | |
| CN110458050B (en) | Vehicle cut-in detection method and device based on vehicle-mounted video | |
| CN114693722B (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
| CN111985373A (en) | Safety warning method, device and electronic device based on traffic intersection recognition | |
| CN117237882A (en) | Identification methods and related equipment for moving vehicles | |
| CN115019263A (en) | Establishment method of traffic supervision model, traffic supervision system and method | |
| CN115690716A (en) | Lane change detection method and device, electronic equipment and storage medium | |
| CN111967377A (en) | Method, device and equipment for identifying state of engineering vehicle and storage medium | |
| WO2024098992A1 (en) | Vehicle reversing detection method and apparatus | |
| CN111383248A (en) | A method, device and electronic device for judging pedestrians running a red light | |
| CN112699773A (en) | Traffic light identification method and device and electronic equipment | |
| CN110634324A (en) | Vehicle-mounted terminal based reminding method and system for courtesy pedestrians and vehicle-mounted terminal | |
| CN114998863A (en) | Target road identification method, target road identification device, electronic equipment and storage medium | |
| CN113297939A (en) | Obstacle detection method, system, terminal device and storage medium | |
| CN115439811B (en) | A vehicle crossing detection method based on AI technology in complex scenarios |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |