CN115291535A - Camera simulation test method, device and equipment and readable storage medium - Google Patents
Camera simulation test method, device and equipment and readable storage mediumDownload PDFInfo
- Publication number
- CN115291535A CN115291535ACN202210783137.3ACN202210783137ACN115291535ACN 115291535 ACN115291535 ACN 115291535ACN 202210783137 ACN202210783137 ACN 202210783137ACN 115291535 ACN115291535 ACN 115291535A
- Authority
- CN
- China
- Prior art keywords
- camera
- tested
- pose
- simulation
- data
- 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.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Studio Devices (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明涉及仿真测试领域，尤其涉及一种摄像头仿真测试方法、装置、设备及可读存储介质。The invention relates to the field of simulation testing, in particular to a camera simulation testing method, device, equipment and a readable storage medium.
背景技术Background technique
在对车载智能摄像头进行的仿真测试中，目前使用较多的是视频暗箱和视频注入两种方案，这两种方案均是按照待测摄像头提供方提供的在实车上安装的X坐标、Y坐标、Z坐标、俯仰角、横摆角及横滚角，在仿真测试场景中对应的配置虚拟摄像头的安装位置和角度参数，然后启动仿真场景进行测试。然而，摄像头安装位姿的偏差会直接影响到车辆对外界环境的感知，进而影响到车辆自动驾驶系统的判断和决策，使用单一的安装位姿参数对摄像头进行仿真测试，不能对摄像头形成全面、客观的评价，从而减弱了仿真测试的优势。In the simulation test of the vehicle-mounted smart camera, the two schemes of video obscura and video injection are widely used at present. These two schemes are based on the X coordinates, Y Coordinates, Z coordinates, pitch angle, yaw angle and roll angle, correspondingly configure the installation position and angle parameters of the virtual camera in the simulation test scene, and then start the simulation scene for testing. However, the deviation of the installation pose of the camera will directly affect the vehicle's perception of the external environment, and further affect the judgment and decision-making of the vehicle's automatic driving system. Using a single installation pose parameter to simulate the camera cannot form a comprehensive, Objective evaluation, thus weakening the advantages of simulation testing.
发明内容Contents of the invention
本发明的主要目的在于提供一种摄像头仿真测试方法、装置、设备及可读存储介质，旨在解决采用单一安装位姿对摄像头进行仿真测试不够全面和客观，以及无法确定摄像头的最优安装位姿参数的技术问题。The main purpose of the present invention is to provide a camera simulation test method, device, equipment and readable storage medium, aiming to solve the problem that the simulation test of the camera using a single installation pose is not comprehensive and objective, and the optimal installation position of the camera cannot be determined. Technical issues of attitude parameters.
第一方面，本发明提供一种摄像头仿真测试方法，所述摄像头仿真测试方法包括：In a first aspect, the present invention provides a camera simulation test method, the camera simulation test method comprising:
在仿真测试环境中，根据待测试摄像头的安装位姿范围，设置虚拟摄像头的初始位姿；In the simulation test environment, set the initial pose of the virtual camera according to the installation pose range of the camera to be tested;
获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据；Obtain the simulation data for the virtual camera to identify the target in the simulation scene;
获取待测试摄像头对仿真场景中的目标物进行识别的测试数据；Obtain the test data that the camera to be tested recognizes the target in the simulation scene;
将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿的识别准确率；The simulation data is compared with the test data to obtain the recognition accuracy of the camera to be tested in the current pose;
按照预设步长和预设角度，调整虚拟摄像头的位姿，若未测试完待测试摄像头的安装位姿范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤；According to the preset step size and preset angle, adjust the pose of the virtual camera, if the installation pose range of the camera to be tested has not been tested, then return to execute the simulation data of obtaining the virtual camera to identify the target in the simulation scene A step of;
对待测试摄像头在各个位姿的识别准确率进行汇总，输出待测试摄像头在各个位姿的识别准确率的汇总报告。Summarize the recognition accuracy of the camera to be tested in each pose, and output a summary report of the recognition accuracy of the camera to be tested in each pose.
可选的，在所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据之前，包括：Optionally, before the acquisition of the simulation data of the virtual camera identifying the target in the simulation scene, including:
根据待测试摄像头的识别特性，从仿真场景库中选取仿真场景，所述识别特性包括天气条件、光照条件及目标物类型。According to the recognition characteristics of the camera to be tested, the simulation scene is selected from the simulation scene library, and the recognition characteristics include weather conditions, light conditions and target object types.
可选的，在所述获取待测试摄像头对仿真场景中的目标物进行识别的测试数据之前，包括：Optionally, before the acquisition of the test data that the camera to be tested recognizes the target in the simulation scene, it includes:
基于仿真测试台架的视频暗箱，设置待测试摄像头的安装位姿。Based on the video camera obscura of the simulation test bench, set the installation pose of the camera to be tested.
可选的，所述将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿的识别准确率包括：Optionally, comparing the simulation data with the test data to obtain the recognition accuracy of the camera to be tested in the current pose includes:
将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿对仿真场景中各个目标物的识别准确率；The simulation data is compared with the test data to obtain the recognition accuracy of the camera to be tested in the current pose to each target in the simulation scene;
对属于同一目标物类型的各个目标物的识别准确率取平均值，分别计算得到各个目标物类型的识别准确率；Take the average of the recognition accuracy rates of each target object belonging to the same target object type, and calculate the recognition accuracy rate of each target object type separately;
根据待测试摄像头的识别特性，为不同目标物类型的识别准确率分配不同的权重，计算得到待测试摄像头在当前位姿的识别准确率。According to the recognition characteristics of the camera to be tested, different weights are assigned to the recognition accuracy of different target types, and the recognition accuracy of the camera to be tested in the current pose is calculated.
可选的，所述位姿包括X坐标、Y坐标、Z坐标、横摆角、横滚角及俯仰角，所述按照预设步长和预设角度，调整虚拟摄像头的位姿包括：Optionally, the pose includes an X coordinate, a Y coordinate, a Z coordinate, a yaw angle, a roll angle, and a pitch angle, and adjusting the pose of the virtual camera according to a preset step size and a preset angle includes:
按照预设步长，分别调整虚拟摄像头的X坐标值、Y坐标值及Z坐标值；Adjust the X coordinate value, Y coordinate value and Z coordinate value of the virtual camera respectively according to the preset step size;
按照预设角度，分别调整虚拟摄像头的横摆角、横滚角及俯仰角的角度。Adjust the yaw angle, roll angle and pitch angle of the virtual camera respectively according to the preset angle.
可选的，在所述对待测试摄像头在各个位姿的识别准确率进行汇总，输出待测试摄像头在各个位姿的识别准确率的汇总报告之后，包括：Optionally, after summarizing the recognition accuracy of the camera to be tested in each pose, and outputting a summary report of the recognition accuracy of the camera to be tested in each pose, the method includes:
按照识别准确率从高到低的顺序，从对待测试摄像头在各个位姿的识别准确率进行汇总后的数据中，选取预设数量的位姿，作为对待测试摄像头进行新一轮测试的位姿数据集；According to the order of recognition accuracy from high to low, select a preset number of poses from the data after summarizing the recognition accuracy of each pose of the camera to be tested as the pose for a new round of testing of the camera to be tested data set;
若未测试完所述位姿数据集，则从所述位姿数据集中选取位姿作为待测试位姿；If the pose data set has not been tested, select the pose from the pose data set as the pose to be tested;
基于所述待测试位姿，按照新的预设步长和新的预设角度，调整虚拟摄像头的位姿，若未测试完所述待测试位姿的预设范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤，所述新的预设步长小于所述预设步长，所述新的预设角度小于所述预设角度。Based on the pose to be tested, adjust the pose of the virtual camera according to a new preset step size and a new preset angle, and if the preset range of the pose to be tested has not been tested, return to perform the acquisition In the step of identifying the simulation data of the target object in the simulation scene by the virtual camera, the new preset step size is smaller than the preset step size, and the new preset angle is smaller than the preset angle.
第二方面，本发明还提供一种摄像头仿真测试装置，所述摄像头仿真测试装置包括：In a second aspect, the present invention also provides a camera simulation test device, the camera simulation test device comprising:
设置模块，用于在仿真测试环境中，根据待测试摄像头的安装位姿范围，设置虚拟摄像头的初始位姿；The setting module is used to set the initial pose of the virtual camera according to the installation pose range of the camera to be tested in the simulation test environment;
第一获取模块，用于获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据；The first obtaining module is used to obtain the simulation data that the virtual camera recognizes the target in the simulation scene;
第二获取模块，用于获取待测试摄像头对仿真场景中的目标物进行识别的测试数据；The second obtaining module is used to obtain the test data that the camera to be tested recognizes the target in the simulation scene;
对比模块，用于将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿的识别准确率；Contrast module, is used for comparing described simulation data with described test data, obtains the recognition accuracy rate of camera to be tested in current pose;
调整模块，用于按照预设步长和预设角度，调整虚拟摄像头的位姿，若未测试完待测试摄像头的安装位姿范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤；The adjustment module is used to adjust the pose of the virtual camera according to the preset step size and preset angle. If the installation pose range of the camera to be tested has not been tested, return to the implementation of the acquisition of the virtual camera to the target object in the simulation scene. performing the step of simulating the identified data;
输出模块，用于对待测试摄像头在各个位姿的识别准确率进行汇总，输出待测试摄像头在各个位姿的识别准确率的汇总报告。The output module is configured to summarize the recognition accuracy of the camera to be tested in each pose, and output a summary report of the recognition accuracy of the camera to be tested in each pose.
可选的，所述对比模块，用于：Optionally, the comparison module is used for:
将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿对仿真场景中各个目标物的识别准确率；The simulation data is compared with the test data to obtain the recognition accuracy of the camera to be tested in the current pose to each target in the simulation scene;
对属于同一目标物类型的各个目标物的识别准确率取平均值，分别计算得到各个目标物类型的识别准确率；Take the average of the recognition accuracy rates of each target object belonging to the same target object type, and calculate the recognition accuracy rate of each target object type separately;
根据待测试摄像头的识别特性，为不同目标物类型的识别准确率分配不同的权重，计算得到待测试摄像头在当前位姿的识别准确率。According to the recognition characteristics of the camera to be tested, different weights are assigned to the recognition accuracy of different target types, and the recognition accuracy of the camera to be tested in the current pose is calculated.
第三方面，本发明还提供一种摄像头仿真测试设备，所述摄像头仿真测试设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的摄像头仿真测试程序，其中所述摄像头仿真测试程序被所述处理器执行时，实现如上述所述的摄像头仿真测试方法的步骤。In a third aspect, the present invention also provides a camera simulation test device, which includes a processor, a memory, and a camera simulation test program stored on the memory and executable by the processor, wherein the When the camera simulation test program is executed by the processor, the steps of the above-mentioned camera simulation test method are realized.
第四方面，本发明还提供一种可读存储介质，所述可读存储介质上存储有摄像头仿真测试程序，其中所述摄像头仿真测试程序被处理器执行时，实现如上述所述的摄像头仿真测试方法的步骤。In a fourth aspect, the present invention also provides a readable storage medium, on which a camera simulation test program is stored, wherein when the camera simulation test program is executed by a processor, the camera simulation as described above is realized. The steps of the test method.
本发明中，在仿真测试环境中，根据待测试摄像头的安装位姿范围，设置虚拟摄像头的初始位姿；获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据；获取待测试摄像头对仿真场景中的目标物进行识别的测试数据；将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿的识别准确率；按照预设步长和预设角度，调整虚拟摄像头的位姿，若未测试完待测试摄像头的安装位姿范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤；对待测试摄像头在各个位姿的识别准确率进行汇总，输出待测试摄像头在各个位姿的识别准确率的汇总报告。本发明通过，在仿真测试环境中，根据待测试摄像头的安装位姿范围，设置虚拟摄像头的初始位姿，摄像头的安装位姿范围通常由摄像头生产厂家提供，分别获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据和待测试摄像头对仿真场景中的目标物进行识别的测试数据，通常分别称其为“真值”和“测试值”，通过将“真值”和“测试值”进行对比，即能得到待测试摄像头在当前位姿对仿真场景中的目标物的识别准确率，然后按照预设步长和预设角度，调整虚拟摄像头的位姿，在安装位姿范围内对待测试摄像头进行遍历测试，从而可以得到待测试摄像头在各个位姿的识别准确率，然后进行汇总输出待测试摄像头在各个位姿的识别准确率的仿真测试汇总报告，通过本发明，可以高效的对摄像头在工作位姿范围内的各个位姿的识别准确率进行全面、客观的测试评价，可以得出摄像头最佳识别准确率的安装位姿，从而为摄像头生产厂家及相关方提供摄像头最佳安装位姿的参考建议，进一步提升摄像头的识别精度。In the present invention, in the simulation test environment, according to the installation pose range of the camera to be tested, the initial pose of the virtual camera is set; the simulation data that the virtual camera recognizes the target in the simulation scene is obtained; Test data for identifying objects in the scene; compare the simulation data with the test data to obtain the recognition accuracy of the camera to be tested in the current pose; adjust the virtual camera according to the preset step size and preset angle pose, if the installation pose range of the camera to be tested has not been tested, then return to perform the step of obtaining the simulation data that the virtual camera recognizes the target in the simulation scene; the recognition of the camera to be tested in each pose is accurate Rates are summarized, and a summary report of the recognition accuracy of the camera to be tested in each pose is output. According to the present invention, in the simulation test environment, according to the installation pose range of the camera to be tested, the initial pose of the virtual camera is set. The installation pose range of the camera is usually provided by the camera manufacturer, and the virtual camera pairs in the simulation scene are respectively obtained. The simulation data for identifying the target and the test data for identifying the target in the simulation scene by the camera to be tested are usually referred to as "true value" and "test value" respectively. By combining the "true value" and "test value" By comparison, the recognition accuracy of the target object in the simulation scene by the camera to be tested can be obtained in the current pose, and then the pose of the virtual camera is adjusted according to the preset step size and preset angle, and treated within the range of the installation pose The test camera carries out traversal test, so that the recognition accuracy rate of the camera to be tested in each pose can be obtained, and then the simulation test summary report of the recognition accuracy rate of the camera to be tested in each pose is summarized and output. Through the present invention, it is possible to efficiently A comprehensive and objective test and evaluation of the recognition accuracy of each pose of the camera within the range of working poses can obtain the installation pose with the best recognition accuracy of the camera, so as to provide the best installation of the camera for the camera manufacturer and related parties The reference suggestion of pose further improves the recognition accuracy of the camera.
附图说明Description of drawings
图1为本发明摄像头仿真测试设备一实施例的硬件结构示意图；Fig. 1 is the hardware structure schematic diagram of an embodiment of camera emulation test equipment of the present invention;
图2为本发明摄像头仿真测试方法一实施例的流程示意图；Fig. 2 is a schematic flow chart of an embodiment of the camera simulation testing method of the present invention;
图3为图2中步骤S40的细化流程示意图；FIG. 3 is a schematic diagram of a refinement process of step S40 in FIG. 2;
图4为本发明摄像头仿真测试方法一实施例中新一轮测试的流程示意图；Fig. 4 is a schematic flow chart of a new round of testing in an embodiment of the camera simulation testing method of the present invention;
图5为本发明摄像头仿真测试装置一实施例的功能模块示意图。FIG. 5 is a schematic diagram of functional modules of an embodiment of the camera simulation testing device of the present invention.
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。The realization of the purpose of the present invention, functional characteristics and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings.
具体实施方式Detailed ways
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
第一方面，本发明实施例提供一种摄像头仿真测试设备。In a first aspect, an embodiment of the present invention provides a camera simulation testing device.
参照图1，图1为本发明摄像头仿真测试设备一实施例的硬件结构示意图。本发明实施例中，摄像头仿真测试设备可以包括处理器1001(例如中央处理器CentralProcessing Unit，CPU)，通信总线1002，用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信；用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard)；网络接口1004可选的可以包括标准的有线接口、无线接口(如无线保真WIreless-FIdelity，WI-FI接口)；存储器1005可以是高速随机存取存储器(random access memory，RAM)，也可以是稳定的存储器(non-volatile memory)，例如磁盘存储器，存储器1005可选的还可以是独立于前述处理器1001的存储装置。本领域技术人员可以理解，图1中示出的硬件结构并不构成对本发明的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。Referring to FIG. 1 , FIG. 1 is a schematic diagram of the hardware structure of an embodiment of the camera simulation testing device of the present invention. In the embodiment of the present invention, the camera emulation testing device may include a processor 1001 (such as a Central Processing Unit, CPU), a
继续参照图1，图1中作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及摄像头仿真测试程序。其中，处理器1001可以调用存储器1005中存储的摄像头仿真测试程序，并执行本发明实施例提供的摄像头仿真测试方法。Continuing to refer to FIG. 1 , the
第二方面，本发明实施例提供了一种摄像头仿真测试方法。In a second aspect, an embodiment of the present invention provides a camera simulation testing method.
为了更清楚地展示本申请实施例提供的摄像头仿真测试方法，首先介绍一下本申请实施例提供的摄像头仿真测试方法的应用场景。In order to more clearly demonstrate the camera simulation test method provided in the embodiment of the present application, firstly, an application scenario of the camera simulation test method provided in the embodiment of the present application is introduced.
本申请实施例提供的摄像头仿真测试方法应用在通过仿真测试获得摄像头在各个安装位姿对不同类型目标物的识别准确率等测试数据，以对摄像头进行性能测试。The camera simulation test method provided in the embodiment of the present application is applied to obtain test data such as recognition accuracy of different types of targets in various installation poses of the camera through the simulation test, so as to test the performance of the camera.
一实施例中，参照图2，图2为本发明摄像头仿真测试方法一实施例的流程示意图，如图2所示，所述摄像头仿真测试方法包括：In an embodiment, referring to FIG. 2, FIG. 2 is a schematic flow chart of an embodiment of the camera simulation test method of the present invention. As shown in FIG. 2, the camera simulation test method includes:
步骤S10，在仿真测试环境中，根据待测试摄像头的安装位姿范围，设置虚拟摄像头的初始位姿。Step S10, in the simulation test environment, according to the installation pose range of the camera to be tested, the initial pose of the virtual camera is set.
本实施例中，仿真测试环境通常由仿真测试台架构成，仿真测试台架包括搭载虚拟仿真软件的图形工作站、上位机、下位机等，待测试摄像头的安装位姿范围通常由摄像头的生产厂家提供，其指定了适合摄像头工作的安装位姿范围，在待测试摄像头的安装位姿范围内，设置虚拟摄像头的初始位姿，在仿真环境中实现对待测试摄像头的性能测试。In this embodiment, the simulation test environment is usually composed of a simulation test bench. The simulation test bench includes a graphics workstation equipped with virtual simulation software, a host computer, and a lower computer. Provided, it specifies the installation pose range suitable for camera work, within the installation pose range of the camera to be tested, sets the initial pose of the virtual camera, and realizes the performance test of the camera to be tested in the simulation environment.
步骤S20，获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据。Step S20, acquiring simulation data of the virtual camera recognizing the target in the simulation scene.
本实施例中，通过仿真测试软件，获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据，仿真数据通常称之为“真值”。In this embodiment, the simulation data of the virtual camera recognizing the target in the simulation scene is obtained through the simulation test software, and the simulation data is usually called "true value".
步骤S30，获取待测试摄像头对仿真场景中的目标物进行识别的测试数据。Step S30, acquiring test data of the target object in the simulation scene recognized by the camera to be tested.
本实施例中，通过仿真测试软件，获取待测试摄像头对仿真场景中的目标物进行识别的测试数据，测试数据通常称之为“测试值”，可基于视频暗箱和视频注入的摄像头仿真测试方案，实现待测试摄像头和虚拟摄像头识别图像的同步，即实现待测试摄像头和虚拟摄像头实时识别相同的目标物场景图像。In this embodiment, through the simulation test software, the test data of identifying the target in the simulation scene by the camera to be tested is obtained. The test data is usually called "test value", which can be based on the camera simulation test scheme of the video camera obscura and video injection. , realize the synchronization of the recognition images of the camera to be tested and the virtual camera, that is, realize the recognition of the same target scene image by the camera to be tested and the virtual camera in real time.
步骤S40，将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿的识别准确率。Step S40, comparing the simulation data with the test data to obtain the recognition accuracy of the camera to be tested at the current pose.
本实施例中，将仿真数据和测试数据进行对比，即将“真值”和“测试值”进行对比，得到待测试摄像头在当前位姿的识别准确率，根据摄像头的识别特性以及进行仿真测试的具体需求，仿真数据和测试数据具体可以包括目标物相对摄像头的距离、目标物的宽度及目标物的类型等。In this embodiment, the simulation data is compared with the test data, that is, the "true value" and the "test value" are compared to obtain the recognition accuracy of the camera to be tested in the current pose. According to the recognition characteristics of the camera and the simulation test Specific requirements, simulation data and test data may specifically include the distance of the target from the camera, the width of the target, and the type of the target.
步骤S50，按照预设步长和预设角度，调整虚拟摄像头的位姿，若未测试完待测试摄像头的安装位姿范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤。Step S50, adjust the pose of the virtual camera according to the preset step size and preset angle, if the installation pose range of the camera to be tested has not been tested, return to execute the acquisition of the virtual camera to identify the target in the simulation scene The steps of the simulation data.
本实施例中，根据具体的测试需要来设定预设步长和预设角度的大小，在待测试摄像头的安装位姿范围内，以预设步长和预设角度来逐步的调整虚拟摄像头的位姿，对待测试摄像头进行遍历测试。In this embodiment, the preset step size and preset angle are set according to the specific test needs, and the virtual camera is gradually adjusted with the preset step size and preset angle within the installation pose range of the camera to be tested. The pose of the camera to be tested is traversed.
步骤S60，对待测试摄像头在各个位姿的识别准确率进行汇总，输出待测试摄像头在各个位姿的识别准确率的汇总报告。Step S60, summarizing the recognition accuracy rates of the cameras to be tested in each pose, and outputting a summary report of the recognition accuracy rates of the cameras to be tested in each pose.
本实施例中，对待测试摄像头在各个位姿的识别准确率进行汇总后，即可以得知待测试摄像头在各个位姿的识别准确率情况，输出待测试摄像头在各个位姿的识别准确率的汇总报告，可以为摄像头生产厂家及相关方提供摄像头最佳安装位姿的参考建议，高效的对摄像头在工作位姿范围内的各个位姿的识别准确率进行全面、客观的测试评价。In this embodiment, after summarizing the recognition accuracy of the camera to be tested in each pose, the recognition accuracy of the camera to be tested in each pose can be known, and output the recognition accuracy of the camera to be tested in each pose The summary report can provide camera manufacturers and related parties with reference suggestions for the best installation posture of the camera, and efficiently conduct a comprehensive and objective test and evaluation of the recognition accuracy of each posture of the camera within the range of working postures.
本实施例中，在待测试摄像头的安装位姿范围内，根据预设步长和预设角度，调整虚拟摄像头的位姿，对待测试摄像头进行遍历仿真测试，通过分别获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据和待测试摄像头对仿真场景中的目标物进行识别的测试数据，即“真值”和“测试值”，将“真值”和“测试值”进行对比，即得到待测试摄像头在当前位姿对仿真场景中的目标物的识别准确率，进一步得到待测试摄像头在各个位姿的识别准确率，实现了对摄像头在工作位姿范围内的各个位姿的识别准确率进行全面、客观的测试评价，可以得出摄像头最佳识别准确率的安装位姿，从而为摄像头生产厂家及相关方提供摄像头最佳安装位姿的参考建议，进一步提升摄像头的识别精度。In this embodiment, within the installation pose range of the camera to be tested, the pose of the virtual camera is adjusted according to the preset step length and the preset angle, and the camera to be tested is subjected to a traversal simulation test. The simulation data for identifying the target object and the test data for identifying the target object in the simulation scene by the camera to be tested, that is, "true value" and "test value", compare the "true value" and "test value", that is Obtain the recognition accuracy rate of the target object in the simulation scene in the current pose of the camera to be tested, further obtain the recognition accuracy rate of the camera to be tested in each pose, and realize the recognition of each pose of the camera within the working pose range A comprehensive and objective test and evaluation of the accuracy rate can obtain the installation pose of the camera with the best recognition accuracy, so as to provide reference suggestions for the best installation pose of the camera for camera manufacturers and related parties, and further improve the recognition accuracy of the camera.
进一步地，一实施例中，在步骤S20之前，包括：Further, in one embodiment, before step S20, include:
根据待测试摄像头的识别特性，从仿真场景库中选取仿真场景，所述识别特性包括天气条件、光照条件及目标物类型。According to the recognition characteristics of the camera to be tested, the simulation scene is selected from the simulation scene library, and the recognition characteristics include weather conditions, light conditions and target object types.
本实施例中，不同的摄像头擅于识别的天气条件、光照条件及目标物类型不同，例如，有的摄像头擅长识别车道线和车辆，在良好的天气条件下工作状态较好，因此，根据待测试摄像头对不同的天气条件、光照条件及目标物类型的识别情况，选择相应的仿真场景，以更好的针对性，实现待测试摄像头的仿真测试。In this embodiment, different cameras are good at recognizing different weather conditions, lighting conditions, and object types. For example, some cameras are good at recognizing lane lines and vehicles, and work better under good weather conditions. Therefore, according to the Test the camera's recognition of different weather conditions, lighting conditions and target types, select the corresponding simulation scene, and achieve the simulation test of the camera to be tested with better pertinence.
进一步地，一实施例中，在步骤S30之前，包括：Further, in one embodiment, before step S30, include:
基于仿真测试台架的视频暗箱，设置待测试摄像头的安装位姿。Based on the video camera obscura of the simulation test bench, set the installation pose of the camera to be tested.
本实施例中，通过视频暗箱实现待测试摄像头和虚拟摄像头所识别的仿真场景的同步，其原理为在仿真测试台架的视频暗箱中设置一显示屏幕，将待测试摄像头安装于显示屏幕前，使待测试摄像头的识别视野恰好与显示屏幕相重合，且使待测试摄像头的光轴与显示屏幕相垂直，通过仿真软件将虚拟摄像头所识别的仿真场景的图像实时同步到视频暗箱中的显示屏幕上，即每次在调整虚拟摄像头的位姿后，虚拟摄像头所识别的图像会实时同步到视频暗箱中的显示屏幕上，待测试摄像头对显示屏幕进行识别，从而实现待测试摄像头和虚拟摄像头所识别的仿真场景的同步。In this embodiment, the synchronization of the simulated scene identified by the camera to be tested and the virtual camera is realized by the video camera obscura. Its principle is to set a display screen in the video camera dark box of the simulation test bench, and the camera to be tested is installed in front of the display screen. Make the recognition field of view of the camera to be tested coincide with the display screen, and make the optical axis of the camera to be tested perpendicular to the display screen, and synchronize the image of the simulated scene recognized by the virtual camera to the display screen in the video obscura in real time through the simulation software In other words, each time after adjusting the pose of the virtual camera, the image recognized by the virtual camera will be synchronized to the display screen in the video camera obscura in real time, and the camera to be tested will recognize the display screen, so as to realize the Synchronization of identified simulation scenarios.
进一步地，一实施例中，参照图3，图3为图2中步骤S40的细化流程示意图，如图3所示，步骤S40包括：Further, in an embodiment, refer to FIG. 3 , which is a schematic diagram of a detailed flow chart of step S40 in FIG. 2 . As shown in FIG. 3 , step S40 includes:
步骤S401，将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿对仿真场景中各个目标物的识别准确率；Step S401, comparing the simulation data with the test data to obtain the recognition accuracy of each target in the simulation scene by the camera to be tested in the current pose;
步骤S402，对属于同一目标物类型的各个目标物的识别准确率取平均值，分别计算得到各个目标物类型的识别准确率；Step S402, taking the average of the recognition accuracy rates of each target object belonging to the same target object type, and calculating the recognition accuracy rates of each target object type respectively;
步骤S403，根据待测试摄像头的识别特性，为不同目标物类型的识别准确率分配不同的权重，计算得到待测试摄像头在当前位姿的识别准确率。Step S403, according to the recognition characteristics of the camera to be tested, assign different weights to the recognition accuracy of different object types, and calculate the recognition accuracy of the camera to be tested in the current pose.
本实施例中，在一个仿真场景中通常有多种类型的多个目标物，在将仿真数据和测试数据进行对比，得到仿真场景中多种类型的多个目标物的识别准确率后，将属于同一类型的各目标物的准确率进行取平均值计算，从而得到各个类型的识别准确率，然后根据待测试摄像头的识别特性，为不同目标物类型的识别准确率赋予不同的权重，经过计算得到待测试摄像头在当前位姿的对各种类型目标物的综合的识别准确率，例如，某待测试摄像头较多的用于对车道线的识别，则针对该待测试摄像头的目标物类型：车道线、车辆、行人，可以分别赋予相应的权重50％、30％、20％，可根据摄像头的识别特性和测试需求进行具体的权重设定。In this embodiment, there are usually multiple targets of various types in a simulation scene. After comparing the simulation data with the test data to obtain the recognition accuracy of multiple targets of various types in the simulation scene, the The accuracy of each object belonging to the same type is averaged to obtain the recognition accuracy of each type, and then according to the recognition characteristics of the camera to be tested, different weights are assigned to the recognition accuracy of different target types. After calculation Get the comprehensive recognition accuracy rate of various types of targets of the camera to be tested in the current pose. For example, if a camera to be tested is used to recognize lane lines with more cameras, then for the target type of the camera to be tested: Lane lines, vehicles, and pedestrians can be given corresponding weights of 50%, 30%, and 20%, respectively, and specific weight settings can be made according to the recognition characteristics of the camera and test requirements.
进一步地，一实施例中，所述位姿包括X坐标、Y坐标、Z坐标、横摆角、横滚角及俯仰角，所述按照预设步长和预设角度，调整虚拟摄像头的位姿包括：Further, in one embodiment, the pose includes X coordinate, Y coordinate, Z coordinate, yaw angle, roll angle and pitch angle, and the position of the virtual camera is adjusted according to the preset step size and preset angle. Poses include:
按照预设步长，分别调整虚拟摄像头的X坐标值、Y坐标值及Z坐标值；Adjust the X coordinate value, Y coordinate value and Z coordinate value of the virtual camera respectively according to the preset step size;
按照预设角度，分别调整虚拟摄像头的横摆角、横滚角及俯仰角的角度。Adjust the yaw angle, roll angle and pitch angle of the virtual camera respectively according to the preset angle.
本实施例中，摄像头的位姿包括X坐标、Y坐标、Z坐标、横摆角、横滚角及俯仰角，即六个自由度，在调整虚拟摄像头的位姿时，按照预设的步长，分别调整虚拟摄像头的X坐标值、Y坐标值及Z坐标值，按照预设的角度，分别调整虚拟摄像头的横摆角、横滚角及俯仰角的角度，以对待测试摄像头在安装位姿范围内的多个位姿进行测试。In this embodiment, the pose of the camera includes X coordinates, Y coordinates, Z coordinates, yaw angle, roll angle, and pitch angle, that is, six degrees of freedom. When adjusting the pose of the virtual camera, follow the preset steps Long, adjust the X coordinate value, Y coordinate value and Z coordinate value of the virtual camera respectively, according to the preset angle, adjust the yaw angle, roll angle and pitch angle of the virtual camera respectively, to treat the test camera in the installation position Multiple poses in the range of poses are tested.
进一步地，一实施例中，参照图4，图4为本发明摄像头仿真测试方法一实施例中新一轮测试的流程示意图，如图4所示，在步骤S60之后，还包括对待测试摄像头进行新一轮测试的步骤S70，步骤S70包括：Further, in an embodiment, referring to FIG. 4, FIG. 4 is a schematic flow chart of a new round of testing in an embodiment of the camera simulation test method of the present invention. As shown in FIG. 4, after step S60, it also includes performing The step S70 of new round of test, step S70 comprises:
步骤S701，按照识别准确率从高到低的顺序，从对待测试摄像头在各个位姿的识别准确率进行汇总后的数据中，选取预设数量的位姿，作为对待测试摄像头进行新一轮测试的位姿数据集；Step S701, according to the order of recognition accuracy from high to low, select a preset number of poses from the data after summarizing the recognition accuracy of each pose of the camera to be tested as a new round of testing for the camera to be tested pose data set;
步骤S702，若未测试完所述位姿数据集，则从所述位姿数据集中选取位姿作为待测试位姿；Step S702, if the pose data set has not been tested, select a pose from the pose data set as the pose to be tested;
步骤S703，基于所述待测试位姿，按照新的预设步长和新的预设角度，调整虚拟摄像头的位姿，若未测试完所述待测试位姿的预设范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤，所述新的预设步长小于所述预设步长，所述新的预设角度小于所述预设角度。Step S703, based on the pose to be tested, adjust the pose of the virtual camera according to the new preset step size and new preset angle, and return to execute if the preset range of the pose to be tested has not been tested In the step of acquiring the simulation data of the virtual camera recognizing the target in the simulation scene, the new preset step size is smaller than the preset step size, and the new preset angle is smaller than the preset angle.
本实施例中，考虑遍历测试的效率，在步骤S50中预设步长和预设角度，可能会设置的过大，因此，还可以进行进一步的测试以得到更精确的位姿，即相当于新一轮的测试，在各个位姿的识别准确率进行汇总后的数据中，按照识别准确率从高到低的顺序，选取一定数量的位姿，在所选取的待测试位姿的附近范围区域内，按照新的预设步长和新的预设角度，进行进一步的遍历测试，以得出识别准确率更佳的摄像头的位姿。In this embodiment, considering the efficiency of the traversal test, the preset step size and preset angle in step S50 may be set too large. Therefore, further tests can be performed to obtain a more accurate pose, which is equivalent to In the new round of testing, in the data after the recognition accuracy of each pose is summarized, a certain number of poses are selected in the order of recognition accuracy from high to low, and in the vicinity of the selected pose to be tested In the area, according to the new preset step size and new preset angle, a further traversal test is carried out to obtain the pose of the camera with better recognition accuracy.
第三方面，本发明实施例还提供一种摄像头仿真测试装置。In a third aspect, the embodiment of the present invention further provides a camera simulation testing device.
参照图5，图5为本发明摄像头仿真测试装置一实施例的功能模块示意图。Referring to FIG. 5 , FIG. 5 is a schematic diagram of functional modules of an embodiment of a camera simulation testing device according to the present invention.
本实施例中，所述摄像头仿真测试装置包括：In this embodiment, the camera simulation testing device includes:
设置模块10，用于在仿真测试环境中，根据待测试摄像头的安装位姿范围，设置虚拟摄像头的初始位姿；Setting
第一获取模块20，用于获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据；The first acquiring
第二获取模块30，用于获取待测试摄像头对仿真场景中的目标物进行识别的测试数据；The second obtaining
对比模块40，用于将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿的识别准确率；
调整模块50，用于按照预设步长和预设角度，调整虚拟摄像头的位姿，若未测试完待测试摄像头的安装位姿范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤；The
输出模块60，用于对待测试摄像头在各个位姿的识别准确率进行汇总，输出待测试摄像头在各个位姿的识别准确率的汇总报告。The
进一步地，一实施例中，所述摄像头仿真测试装置还包括选取模块，用于：Further, in one embodiment, the camera simulation test device also includes a selection module for:
根据待测试摄像头的识别特性，从仿真场景库中选取仿真场景，所述识别特性包括天气条件、光照条件及目标物类型。According to the recognition characteristics of the camera to be tested, the simulation scene is selected from the simulation scene library, and the recognition characteristics include weather conditions, light conditions and target object types.
进一步地，一实施例中，所述摄像头仿真测试装置还包括位姿设置模块，用于：Further, in one embodiment, the camera simulation test device also includes a pose setting module, used for:
基于仿真测试台架的视频暗箱，设置待测试摄像头的安装位姿。Based on the video camera obscura of the simulation test bench, set the installation pose of the camera to be tested.
进一步地，一实施例中，对比模块40，用于：Further, in one embodiment, the
将所述仿真数据和所述测试数据进行对比，得到待测试摄像头在当前位姿对仿真场景中各个目标物的识别准确率；The simulation data is compared with the test data to obtain the recognition accuracy of the camera to be tested in the current pose to each target in the simulation scene;
对属于同一目标物类型的各个目标物的识别准确率取平均值，分别计算得到各个目标物类型的识别准确率；Take the average of the recognition accuracy rates of each target object belonging to the same target object type, and calculate the recognition accuracy rate of each target object type separately;
根据待测试摄像头的识别特性，为不同目标物类型的识别准确率分配不同的权重，计算得到待测试摄像头在当前位姿的识别准确率。According to the recognition characteristics of the camera to be tested, different weights are assigned to the recognition accuracy of different target types, and the recognition accuracy of the camera to be tested in the current pose is calculated.
进一步地，一实施例中，调整模块50，用于：Further, in one embodiment, the
按照预设步长，分别调整虚拟摄像头的X坐标值、Y坐标值及Z坐标值；Adjust the X coordinate value, Y coordinate value and Z coordinate value of the virtual camera respectively according to the preset step size;
按照预设角度，分别调整虚拟摄像头的横摆角、横滚角及俯仰角的角度。Adjust the yaw angle, roll angle and pitch angle of the virtual camera respectively according to the preset angle.
进一步地，一实施例中，所述摄像头仿真测试装置还包括位姿调整模块，用于：Further, in one embodiment, the camera simulation test device also includes a pose adjustment module, used for:
按照识别准确率从高到低的顺序，从对待测试摄像头在各个位姿的识别准确率进行汇总后的数据中，选取预设数量的位姿，作为对待测试摄像头进行新一轮测试的位姿数据集；According to the order of recognition accuracy from high to low, select a preset number of poses from the data after summarizing the recognition accuracy of each pose of the camera to be tested as the pose for a new round of testing of the camera to be tested data set;
若未测试完所述位姿数据集，则从所述位姿数据集中选取位姿作为待测试位姿；If the pose data set has not been tested, select the pose from the pose data set as the pose to be tested;
基于所述待测试位姿，按照新的预设步长和新的预设角度，调整虚拟摄像头的位姿，若未测试完所述待测试位姿的预设范围，则返回执行所述获取虚拟摄像头对仿真场景中的目标物进行识别的仿真数据的步骤，所述新的预设步长小于所述预设步长，所述新的预设角度小于所述预设角度。Based on the pose to be tested, adjust the pose of the virtual camera according to a new preset step size and a new preset angle, if the preset range of the pose to be tested has not been tested, return to perform the acquisition In the step of identifying the simulation data of the target object in the simulation scene by the virtual camera, the new preset step size is smaller than the preset step size, and the new preset angle is smaller than the preset angle.
其中，上述摄像头仿真测试装置中各个模块的功能实现与上述摄像头仿真测试方法实施例中各步骤相对应，其功能和实现过程在此处不再一一赘述。Wherein, the function realization of each module in the above-mentioned camera simulation test device corresponds to each step in the above-mentioned camera simulation test method embodiment, and its functions and implementation processes will not be repeated here.
第四方面，本发明实施例还提供一种可读存储介质。In a fourth aspect, the embodiment of the present invention further provides a readable storage medium.
本发明可读存储介质上存储有摄像头仿真测试程序，其中所述摄像头仿真测试程序被处理器执行时，实现如上述的摄像头仿真测试方法的步骤。A camera simulation test program is stored on the readable storage medium of the present invention, wherein when the camera simulation test program is executed by a processor, the steps of the above-mentioned camera simulation test method are realized.
其中，摄像头仿真测试程序被执行时所实现的方法可参照本发明摄像头仿真测试方法的各个实施例，此处不再赘述。Wherein, the methods implemented when the camera simulation test program is executed can refer to the various embodiments of the camera simulation test method of the present invention, which will not be repeated here.
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。It should be noted that, as used herein, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备执行本发明各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM) , magnetic disk, optical disk), several instructions are included to make a terminal device execute the method described in each embodiment of the present invention.
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the description of the present invention and the contents of the accompanying drawings, or directly or indirectly used in other related technical fields , are all included in the scope of patent protection of the present invention in the same way.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210783137.3ACN115291535B (en) | 2022-06-27 | 2022-06-27 | Camera simulation test method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210783137.3ACN115291535B (en) | 2022-06-27 | 2022-06-27 | Camera simulation test method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115291535Atrue CN115291535A (en) | 2022-11-04 |
| CN115291535B CN115291535B (en) | 2025-02-18 |
Family
ID=83822714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210783137.3AActiveCN115291535B (en) | 2022-06-27 | 2022-06-27 | Camera simulation test method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115291535B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115824591A (en)* | 2022-12-09 | 2023-03-21 | 中国重汽集团济南动力有限公司 | Method and system for camera calibration and verification based on video obscura |
| CN115880569A (en)* | 2023-01-06 | 2023-03-31 | 宁波吉利汽车研究开发有限公司 | Virtual camera effectiveness detection method, device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080013825A1 (en)* | 2006-07-12 | 2008-01-17 | Fanuc Ltd | Simulation device of robot system |
| CN102736634A (en)* | 2012-07-10 | 2012-10-17 | 浙江捷尚视觉科技有限公司 | Camera angle regulation method for vehicle panorama |
| CN111275771A (en)* | 2020-02-19 | 2020-06-12 | 电子科技大学中山学院 | Camera calibration method and device, electronic equipment and storage medium |
| CN112750167A (en)* | 2020-12-30 | 2021-05-04 | 燕山大学 | Robot vision positioning simulation method and device based on virtual reality |
| CN112753047A (en)* | 2020-12-30 | 2021-05-04 | 华为技术有限公司 | Method and system for in-loop calibration and target point setting of hardware of camera and related equipment |
| CN112987593A (en)* | 2021-02-19 | 2021-06-18 | 中国第一汽车股份有限公司 | Visual positioning hardware-in-the-loop simulation platform and simulation method |
| CN113538590A (en)* | 2021-06-15 | 2021-10-22 | 深圳云天励飞技术股份有限公司 | Zoom camera calibration method and device, terminal equipment and storage medium |
| CN114299166A (en)* | 2022-01-04 | 2022-04-08 | 腾讯科技（深圳）有限公司 | Simulation camera verification method, device, equipment, storage medium, and program product |
- 2022
- 2022-06-27CNCN202210783137.3Apatent/CN115291535B/enactiveActive
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080013825A1 (en)* | 2006-07-12 | 2008-01-17 | Fanuc Ltd | Simulation device of robot system |
| CN102736634A (en)* | 2012-07-10 | 2012-10-17 | 浙江捷尚视觉科技有限公司 | Camera angle regulation method for vehicle panorama |
| CN111275771A (en)* | 2020-02-19 | 2020-06-12 | 电子科技大学中山学院 | Camera calibration method and device, electronic equipment and storage medium |
| CN112750167A (en)* | 2020-12-30 | 2021-05-04 | 燕山大学 | Robot vision positioning simulation method and device based on virtual reality |
| CN112753047A (en)* | 2020-12-30 | 2021-05-04 | 华为技术有限公司 | Method and system for in-loop calibration and target point setting of hardware of camera and related equipment |
| CN112987593A (en)* | 2021-02-19 | 2021-06-18 | 中国第一汽车股份有限公司 | Visual positioning hardware-in-the-loop simulation platform and simulation method |
| CN113538590A (en)* | 2021-06-15 | 2021-10-22 | 深圳云天励飞技术股份有限公司 | Zoom camera calibration method and device, terminal equipment and storage medium |
| CN114299166A (en)* | 2022-01-04 | 2022-04-08 | 腾讯科技（深圳）有限公司 | Simulation camera verification method, device, equipment, storage medium, and program product |
Non-Patent Citations (3)
| Title |
|---|
| 吴立香;栾铭湧;郭鹏;田磊;: "一种视频暗箱摄像头标定方法", 重型汽车, no. 02, 15 April 2020 (2020-04-15)* |
| 朱秋煜;朱鸣;赵保珠;: "获取摄像机安装高度及倾角的简易标定方法", 电视技术, no. 12, 17 December 2016 (2016-12-17)* |
| 赵兴涛;杜治国;洪卫军;: "监控摄像机效能三维仿真研究", 中国公共安全(学术版), no. 04, 15 December 2012 (2012-12-15)* |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115824591A (en)* | 2022-12-09 | 2023-03-21 | 中国重汽集团济南动力有限公司 | Method and system for camera calibration and verification based on video obscura |
| CN115880569A (en)* | 2023-01-06 | 2023-03-31 | 宁波吉利汽车研究开发有限公司 | Virtual camera effectiveness detection method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115291535B (en) | 2025-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114913506B (en) | A 3D object detection method and device based on multi-view fusion | |
| CN105608693B (en) | The calibration system and method that vehicle-mounted panoramic is looked around | |
| CN115291535A (en) | Camera simulation test method, device and equipment and readable storage medium | |
| JP2018063236A (en) | Method and apparatus for annotating point cloud data | |
| CN111766049B (en) | AR lens testing method, apparatus, equipment and computer-readable storage medium | |
| CN112419423B (en) | A calibration method, device, electronic device and storage medium | |
| CN111145271A (en) | Method and device for determining accuracy of camera parameters, storage medium and terminal | |
| CN111429521B (en) | External parameter calibration method, device, medium and electronic equipment for camera and laser radar | |
| CN109635639B (en) | Method, device, equipment and storage medium for detecting position of traffic sign | |
| US20250166228A1 (en) | Method, apparatus and device for collecting line-of-sight direction data, and storage medium | |
| WO2022089143A1 (en) | Method for generating analog image, and electronic device and storage medium | |
| WO2022217988A1 (en) | Sensor configuration scheme determination method and apparatus, computer device, storage medium, and program | |
| CN117094141A (en) | Automatic driving simulation test method, device, system, equipment and medium | |
| CN114170303A (en) | Combined calibration method, device, system, equipment and medium for radar and camera | |
| CN115891868A (en) | Fault detection method, device, electronic apparatus, and medium for autonomous vehicle | |
| CN110750094B (en) | Method, device and system for determining posture change information of movable device | |
| CN113066185B (en) | Scene data creating method, device, medium and equipment of mine simulation system | |
| CN115218919A (en) | Optimization method and system of air track line and display | |
| US20240221200A1 (en) | Method for identifying depths of images and related device | |
| CN112669388B (en) | Calibration method and device for laser radar and camera device and readable storage medium | |
| CN112749746A (en) | Method, system and device for iteratively updating defect sample | |
| CN113034585A (en) | Offset state test method, test device and storage medium | |
| CN116597246B (en) | Model training method, target detection method, electronic device and storage medium | |
| CN108519215B (en) | Pupil distance adaptability test system and method and test host | |
| CN112668596A (en) | Three-dimensional object recognition method and device and recognition model training method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |