Visual inspection software testing method and device, electronic equipment and storage medium

By generating test configuration files and simulated target testing environments, the visual detection software is automatically tested, which solves the problems of low testing efficiency and manual error in the existing technology, and realizes efficient and accurate visual detection software testing.

CN119088694APending Publication Date: 2024-12-06CHONGQING CHANGAN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411182515.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, the testing efficiency of vision detection software is low, and developers need to conduct testing manually, which has problems with manual error and efficiency.

Method used

By generating test configuration files, simulating the target test environment, and automatically testing visual detection software, using the information in the configuration files to obtain the identification, test data and physical parameters of the software to be tested, conducting simulation tests and comparing them with the true value data. Achieve automation and accuracy.

Benefits of technology

It improves the testing efficiency of visual detection software, reduces subjective errors in manual testing, achieves more accurate test results, and simplifies the operation process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088694A_ABST
    Figure CN119088694A_ABST
Patent Text Reader

Abstract

The invention relates to a testing method and device for visual inspection software, electronic equipment and a storage medium, and relates to the technical field of software testing. The method comprises the following steps: acquiring a test configuration file under the condition of detecting that an unprocessed test configuration file exists; the test configuration file is used for simulating a target test environment of the to-be-tested visual detection software; the target test environment is an environment in which the to-be-tested visual software interacts with an image acquisition device on the vehicle to complete image detection; and testing the to-be-tested visual inspection software based on the test configuration file to obtain a test result. According to the method and the device, the to-be-tested visual inspection software can be automatically tested according to the test configuration file, so that the software development test efficiency is effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of software testing technology, in particular to the field of visual inspection software testing technology, and specifically to a visual inspection software testing method, device, electronic device and storage medium. Background Art

[0002] With the continuous progress and expansion of the automotive technology field, autonomous driving technology has emerged and is showing an increasingly vigorous development trend. In the field of autonomous driving technology, visual perception and recognition technology, as the "eyes" of the autonomous driving system, is a relatively important part of the autonomous driving system. In order to ensure the correctness of visual perception and recognition technology, the testing link in its development process is extremely important.

[0003] In the related technologies, the testing of visual software and algorithms suitable for autonomous driving systems often requires developers to perform it themselves. They need to test the visual software or algorithms they developed or modified through a large amount of data from different scenarios, and observe and compare the processing results of the visual software or algorithms for a long time, so as to realize the testing of the visual software or algorithms. Such testing methods are inefficient. Summary of the invention

[0004] The present application provides a method, device, electronic device and storage medium for testing visual inspection software, so as to at least solve the technical problem of poor testing efficiency of visual inspection software in the prior art. The technical solution of the present application is as follows:

[0005] According to the first aspect provided by the present application, a testing method for visual inspection software is provided, the method comprising: obtaining a test configuration file, the test configuration file being used to simulate a target test environment for the visual inspection software to be tested; the target test environment being an environment in which the visual inspection software to be tested completes image detection by interacting with an image acquisition device on a vehicle; based on the test configuration file, testing the visual inspection software to be tested to obtain a test result.

[0006] According to the above-mentioned technical means, when the existence of an unprocessed configuration file is detected, the present application simulates the target test environment of the visual inspection software to be tested according to the recorded contents in the configuration file and performs a simulation test on the visual inspection software to be tested, thereby obtaining the detection data of the visual inspection software to be tested in the real environment and comparing it with the corresponding true value data. This avoids manual testing by developers while ensuring the accuracy of the test, improves the testing efficiency of the visual inspection software, and can also avoid errors caused by human subjectivity during manual testing.

[0007] In a possible implementation, the test configuration file includes: identification information of the visual inspection software to be tested, path information of the test data, physical parameters of the image acquisition device, and path information of the processing parameters.

[0008] According to the above-mentioned technical means, the present application configures the configuration file so that the visual inspection software to be tested, the test data, the physical parameters of the image acquisition device and the processing parameters can be automatically obtained according to the identification information of the visual inspection software to be tested, the path information of the test data and the path information of the physical parameters and processing parameters of the image acquisition device recorded in the configuration file, and the visual inspection software to be tested can be tested.

[0009] In a possible implementation, based on the test configuration file, the visual inspection software to be tested is tested to obtain the test results, including: obtaining the visual inspection software to be tested according to the identification information of the visual inspection software to be tested, and obtaining the test data according to the path information of the test data; wherein the test data includes original data and true value data corresponding to the original data; obtaining the test data by processing the original data, the physical parameters of the image acquisition device and the processing parameters through the visual inspection software to be tested; and obtaining the test results by comparing the test data with the corresponding true value data.

[0010] According to the above technical means, the present application can accurately compare the visual processing accuracy of the visual inspection software to be tested by comparing the inspection data obtained by processing the original data with the corresponding true value data.

[0011] In a possible implementation, the test configuration file also includes path information of a first test case; the first test case includes at least one type of vehicle environment information; the original data, physical parameters of the image acquisition device, and processing parameters are processed by the visual detection software to be tested to obtain detection data, including: obtaining the first test case according to the path information of the first test case; according to the first test case, filtering out target original data including at least one type of vehicle environment information from the original data; and obtaining the detection data by processing the target original data, physical parameters of the image acquisition device, and processing parameters by the visual detection software to be tested.

[0012] According to the above-mentioned technical means, the present application realizes the screening of the original data input into the visual inspection software to be tested by setting the test cases, and then realizes the testing of different modules of the visual inspection software to be tested by controlling the input data, thereby making the software testing process more targeted and further improving the efficiency of software testing.

[0013] In one possible implementation, the test configuration file also includes path information of a second test case; the detection data includes a detection object identified by the visual detection software to be tested based on the original data and the motion parameters of the detection object; the second test case includes range information of at least one motion parameter of the object; the detection data is compared with the corresponding true value data to obtain a test result, including: obtaining the second test case based on the path information of the second test case; determining target detection data based on the range information of at least one motion parameter of the second test case; wherein the motion parameters of the detection object in the target detection data are within the range of at least one motion parameter of the second test case; and the target detection data is compared with the corresponding true value data to obtain a test result.

[0014] According to the above-mentioned technical means, the present application realizes automatic screening of detection data of the visual inspection software to be tested by setting test cases, so that targeted comparison can be made on the detection capability of the visual inspection software to be tested for certain specific objects or specific physical motion parameters, thereby further improving the efficiency of software testing.

[0015] In one possible implementation, the method is applied to a test device, and the test device and at least one visual inspection software development device are located in the same local area network; wherein the development device is used to generate a test configuration file and send the test configuration file to a configuration file directory of the test device via the local area network.

[0016] According to the above technical means, this application deploys the development equipment and the automated visual inspection software testing equipment in a local area network, making the debugging of the testing equipment convenient and improving the operating efficiency. On the other hand, the constructed local area network does not generate additional connections with the external network, ensuring the security during the development and testing process. The development equipment sends the configured test configuration file to the test equipment through the local area network, and the configuration file can be detected and automatically processed by the test equipment, which also improves the degree of automation in the test process and simplifies the operation method.

[0017] According to a second aspect provided by the present application, a testing device for visual inspection software is provided, and the testing device for visual inspection software includes an acquisition unit and a test unit. The acquisition unit is used to acquire a test configuration file, and the test configuration file is used to simulate a target test environment of the visual inspection software to be tested; the target test environment is an environment in which the visual software to be tested completes image detection by interacting with an image acquisition device on a vehicle; the test unit is used to test the visual inspection software to be tested based on the test configuration file to obtain a test result.

[0018] In a possible implementation, the test configuration file includes: identification information of the visual inspection software to be tested, path information of the test data, physical parameters of the image acquisition device, and path information of the processing parameters.

[0019] In a possible implementation, the testing unit is specifically used to: obtain the visual inspection software to be tested according to the identification information of the visual inspection software to be tested, and obtain the test data according to the path information of the test data; wherein the test data includes original data and true value data corresponding to the original data; obtain the inspection data by processing the original data, the physical parameters of the image acquisition device and the processing parameters through the visual inspection software to be tested; and obtain the test results by comparing the inspection data with the corresponding true value data.

[0020] In a possible implementation, the test configuration file also includes path information of a first test case; the first test case includes at least one type of vehicle environment information; the test unit is specifically used to: obtain the first test case according to the path information of the first test case; according to the first test case, filter out target raw data including the at least one type of vehicle environment information from the raw data; and obtain detection data by processing the target raw data, physical parameters of the image acquisition device, and processing parameters through the visual detection software to be tested.

[0021] In one possible implementation, the test configuration file also includes path information of a second test case; the detection data includes a detection object identified by the visual detection software to be tested based on the original data and motion parameters of the detection object; the second test case includes range information of at least one motion parameter of the object; the test unit is specifically used to: obtain the second test case based on the path information of the second test case; determine target detection data based on the range information of at least one motion parameter of the second test case; wherein the motion parameters of the detection object in the target detection data are within the range of at least one motion parameter of the second test case; and compare the target detection data with the corresponding true value data to obtain a test result.

[0022] In one possible implementation, the apparatus is applied to a test device, and the test device and at least one visual inspection software development device are located in the same local area network; wherein the development device is used to generate a test configuration file and send the test configuration file to a configuration file directory of the test device via the local area network.

[0023] According to a third aspect provided by the present application, an electronic device is provided, comprising: a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the method of the first aspect and any possible implementation method thereof.

[0024] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method of the above-mentioned first aspect and any possible implementation method thereof.

[0025] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0026] Therefore, the above technical features of the present application have the following beneficial effects:

[0027] (1) According to the above-mentioned technical means, when the presence of an unprocessed configuration file is detected, the present application simulates the target test environment of the visual inspection software to be tested according to the recorded contents in the configuration file and performs a simulation test on the visual inspection software to be tested, thereby obtaining the detection data of the visual inspection software to be tested in the real environment and comparing it with the corresponding true value data. This avoids manual testing by developers while ensuring the accuracy of the test, improves the testing efficiency of the visual inspection software, and can also avoid errors caused by human subjectivity during manual testing.

[0028] (2) The present application configures the configuration file so that the visual inspection software to be tested, the test data, the physical parameters of the image acquisition device and the processing parameters can be automatically obtained according to the identification information of the visual inspection software to be tested, the path information of the test data and the path information of the physical parameters and processing parameters of the image acquisition device recorded in the configuration file, and the visual inspection software to be tested can be tested.

[0029] (3) The present application can accurately compare the visual processing accuracy of the visual inspection software to be tested by comparing the inspection data obtained by processing the original data with the corresponding true value data.

[0030] (4) The present application realizes the screening of the original data input into the visual inspection software to be tested by setting up test cases, and then realizes the testing of different modules of the visual inspection software to be tested by controlling the input data, thereby making the software testing process more targeted and further improving the efficiency of software testing.

[0031] (5) The present application realizes the screening of the detection data participating in the true value comparison in the detection data of the visual detection software to be tested by setting up test cases, so that the detection ability of the visual detection software to be tested for certain specific objects or the physical motion parameters of the objects can be compared in a targeted manner, thereby further improving the efficiency of software testing.

[0032] (6) This application arranges the development equipment and the automated visual inspection software testing equipment in a local area network, which makes the debugging of the testing equipment convenient and improves the operating efficiency. On the other hand, the constructed local area network does not generate additional connections with the external network, ensuring the security of the development and testing process. The development equipment sends the configured test configuration file to the test equipment through the local area network, and the test equipment can detect the configuration file and automatically process it, which also improves the degree of automation in the test process and simplifies the operation method.

[0033] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0036] Figure 1 is a structural diagram of a visual inspection software development and testing system according to an exemplary embodiment;

[0037] Figure 2 is a flow chart of a method for testing visual inspection software according to an exemplary embodiment;

[0038] Figure 3 is a flow chart of a method for testing visual inspection software according to an exemplary embodiment;

[0039] Figure 4 is a schematic diagram of a different test module according to an exemplary embodiment;

[0040] Figure 5 is a flow chart of another method for testing visual inspection software according to an exemplary embodiment;

[0041] Figure 6 is a flow chart of another method for testing visual inspection software according to an exemplary embodiment;

[0042] Figure 7 is a flow chart showing a method of obtaining detection data by processing according to a configuration file according to an exemplary embodiment;

[0043] Figure 8is a flow chart of another method for testing visual inspection software according to an exemplary embodiment;

[0044] Fig. 9 is a flow chart of another method for testing visual inspection software according to an exemplary embodiment;

[0045] Fig.10 is a flow chart of another method for testing visual inspection software according to an exemplary embodiment;

[0046] Fig.11 is a flow chart of another method for testing visual inspection software according to an exemplary embodiment;

[0047] Fig.12 is a block diagram of a testing device for visual inspection software according to an exemplary embodiment;

[0048] Fig.13 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0049] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0050] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0051] Before introducing in detail the testing method of the visual inspection software provided by the present application, a brief introduction to the prior art related to the present application is first given.

[0052] Microsoft Windows operating system (Microsoft Windows, Windows): Microsoft Windows is an operating system developed by Microsoft Corporation of the United States based on a graphical user interface. It is mainly used in computers, smart phones and other devices. There are sub-series such as the general version, server version (Windows Server), mobile version (Windows Phone, etc.), and embedded version (Windows CE, etc.). It is one of the most widely used operating systems in the world.

[0053] Unix: Unix is ​​an operating system that appeared in the early 1970s. In addition to being a network operating system, it can also be used as a stand-alone operating system. Unix has gained widespread use as a development platform and desktop operating system, mainly in engineering applications and scientific computing.

[0054] Linux (linux is not unix): Linux is a UNIX-like operating system.

[0055] Secure Shell Protocol (SSH): Secure Shell Protocol is an encrypted network transmission protocol that provides a secure transmission environment for network services in an insecure network. SSH establishes a secure tunnel in the network to connect the SSH client and the server. The most common use of SSH is to log in to the system remotely. People usually use SSH to transmit the command line interface and remotely execute commands. SSH is most frequently used in Unix-like systems, but Windows operating systems can also use SSH to a limited extent.

[0056] Windows Subsystem for Linux (WSL): WSL is a compatibility layer that can run native Linux binary executable files (ELF format) on Windows 10\11. Through WSL, developers can access the powerful features of Windows and Linux on Windows computers at the same time. Developers can install the Linux subsystem on the Windows system and use Linux applications, utilities and command-line tools directly on Windows without making any modifications or incurring the cost of traditional virtual machines or dual-boot settings.

[0057] YAML (Yaml ain't a markup language): YAML is a highly readable format for expressing data serialization.

[0058] cp command: cp command is a command used to copy files in Linux, which can be followed by options and parameters. The cp command can copy files from multiple source paths to a target path. Multiple source paths are separated by spaces, and the target path is placed at the end.

[0059] Command prompt (cmd): Command prompt is a working prompt in the operating system that prompts for command input. The command prompt is different in different operating system environments. In the Windows environment, the command line program is cmd.exe, which is a 32-bit command line program. The Microsoft Windows system is based on the command interpreter on Windows, similar to Microsoft's DOS operating system.

[0060] zeromq: also known as ZMQ, is a series of interfaces similar to sockets.

[0061] With the continuous progress and expansion of the automotive technology field, autonomous driving technology has emerged and is showing an increasingly vigorous development trend. In the field of autonomous driving technology, visual perception and recognition technology, as the "eyes" of the autonomous driving system, is a relatively important part of the autonomous driving system. In order to ensure the correctness of visual perception and recognition technology, the testing link in its development process is extremely important.

[0062] In the related technologies, the testing of visual software and algorithms suitable for autonomous driving systems often requires developers to perform it themselves. They need to test the visual software or algorithms they developed or modified through a large amount of data from different scenarios, and observe and compare the processing results of the visual software or algorithms for a long time, so as to realize the testing of the visual software or algorithms. Such testing methods are inefficient.

[0063] In response to the above technical problems, the present application provides a testing method for visual inspection software, the idea of ​​which is to identify and process the configuration file that records the identification of the visual inspection software to be tested, the path information of the test data, and the simulation environment for simulating the visual inspection software to be tested, thereby realizing automated testing of the visual inspection software and improving the efficiency of software development and testing.

[0064] Before introducing in detail the testing method of the visual inspection software provided in this application, a brief introduction to the implementation environment (implementation architecture) involved in this application is first given.

[0065] Figure 1 The figure shows a schematic diagram of the structure of a visual inspection software development and testing system. Figure 1 As shown, the visual inspection software development and testing system includes several development devices, a switch 20 and a testing device 30. For several development devices, Figure 1 The development device 11, the development device 12 and the development device 13 are used as examples for illustration. For other possible development devices, reference may be made to the description of the development device 11, the development device 12 and the development device 13.

[0066] The development device 11 , the development device 12 and the development device 13 are connected to the test device 30 via the switch 20 .

[0067] As a possible implementation method, the test device 30 is connected to the network interface of the switch 20 via a network cable; the network segment of the Internet Protocol (IP) address of the network interface is determined, and the network segment is set as the network segment of the development device 11, the development device 12 and the development device 13, and then the switch 20 is respectively connected to the development device 11, the development device 12 and the development device 13 via the network cable, thereby realizing the physical network connection between the development device 11, the development device 12 and the development device 13 and the test device 30.

[0068] As an example of a connection at the physical level, the network cable may be a common network cable such as a twisted pair cable, a coaxial cable, or a fiber optic cable, or other physical transmission media.

[0069] As an example of connection at the software level, the development device 11 , the development device 12 , and the development device 13 are connected to the test device 30 by establishing an SSH connection.

[0070] As an example of the device body of development device 11, development device 12 and development device 13, development device 11, development device 12 and development device 13 can be a personal computer (PC), a desktop, laptop, handheld computer, notebook computer, or other electronic device that has at least software development capabilities.

[0071] As an example of the device body of the test device 30, the test device 30 may be a personal computer (PC), a desktop, a laptop, a handheld computer, a notebook computer, or other electronic device that at least has the ability to run software programs. In order to meet the functional requirements of connecting more development devices in the local area network to the test device 30 at the same time and possibly performing software testing at the same time.

[0072] As an example of the hardware parameters of the test device 30, in order to meet the functional requirements of connecting more development devices in the local area network to the test device 30 at the same time and performing software testing at the same time, the hard disk capacity and running memory capacity of the test device 30 should be greater than the preset capacity. Taking the test scenario of the dual forward-looking algorithm project as an example, when there are a certain number of development devices in the local area network and they are testing different dual forward-looking algorithm projects developed by each of them in the test device 30 at the same time, it should be ensured that the test device 30 has at least 30TB of available hard disk space and more than 16GB of available memory space.

[0073] As an example of the software environment of the test device 30, in order to ensure that the test device 30 can automatically detect the test configuration files received from the development device 11, the development device 12 and the development device 13 through a preset script or program, and test the visual detection software to be tested according to the content in the test configuration file, the test device 30 needs to be installed with an operating environment for running or executing the aforementioned preset script or program, such as a Python environment. In addition, since the autonomous driving system in the relevant prior art is often established based on the Linux system and runs in an on-board embedded development board, the test device 30 needs to have the function of simulating the Linux environment and running the visual detection software to be tested in this environment, such as installing a WSL virtual machine and installing the functional running mirror environment corresponding to the visual detection software in the WSL virtual machine for running the visual detection software to be tested.

[0074] In some embodiments, the development device 11, the development device 12 or the development device 13 is used to develop and update the visual inspection software to be tested by submitting the code to a code repository.

[0075] In some embodiments, the development device 11 , the development device 12 , or the development device 13 is used to generate a test configuration file, and send the test configuration file to the test device 30 through the switch 20 .

[0076] In some embodiments, the testing device 30 is used to receive a test configuration file sent by the development device 11, the development device 12 or the development device 13, and test the visual inspection software to be tested according to the identification information of the visual inspection software to be tested, the path information of the test data, the physical parameters of the image acquisition device, and the path information of the processing parameters recorded in the test configuration file.

[0077] For ease of understanding, the testing method of the visual inspection software provided in this application is specifically introduced below in conjunction with the accompanying drawings.

[0078] Figure 2 FIG. 1 is a flow chart of a method for testing visual inspection software according to an exemplary embodiment. The method for testing visual inspection software can be applied to Figure 1 The test equipment 30 shown. Figure 2 As shown, the testing method of the visual inspection software includes the following steps:

[0079] S101. When it is detected that there is an unprocessed configuration file, obtain a test configuration file.

[0080] The test configuration file is used to simulate the target test environment of the visual inspection software to be tested. The target test environment is the environment in which the visual inspection software to be tested completes image detection by interacting with the image acquisition device on the vehicle. For example, the test configuration file may include information on the number of image acquisition devices of the test data source, which is used to indicate the number of groups of data input during the test, thereby simulating the environment of the visual inspection software to be tested when it is applied to an autonomous driving system with multiple image acquisition devices.

[0081] As a possible implementation method, the test device is pre-installed with a script or program for automatically detecting test configuration files, and continuously detects the directory or folder in the test device for storing test configuration files. If there is an unprocessed test configuration file, the unprocessed test configuration file is automatically obtained and processed, and the test configuration file is marked as processed, or the test configuration file is obtained by cutting when obtaining it, so as to prevent repeated processing of the same test configuration file.

[0082] As an example of a test configuration file, the test configuration file may be a configuration file in a YAML format.

[0083] In some embodiments, the test configuration file is connected to the development device through SSH software by a development device located in the same local area network, enters the task directory or folder to be tested of the development device, and copies the pre-established test configuration file to the task directory or folder to be tested of the test device.

[0084] As a possible implementation method, the development device is connected to the Windows system of the test device through SSH software, enters the task directory or folder to be tested under the system, and copies the pre-established test configuration file to the task directory or folder to be tested of the test device. Afterwards, the test configuration file is detected by the script or program for automatically detecting the test configuration file pre-installed in the Windows system of the test device, and the script or program processes the test configuration file.

[0085] As another possible implementation method, the development device is connected to the Linux system of the WSL virtual machine of the test device through SSH software, enters the task directory or folder to be tested under the Linux system, and copies the pre-established test configuration file to the task directory or folder to be tested under the Windows system of the test device. Afterwards, the test configuration file is detected as an unprocessed test configuration file by the script or program pre-installed in the Linux system for automatically detecting the test configuration file through traversal, and these scripts or programs mark the test configuration file and send it to the Windows system for processing, or cut it to the Windows system for processing.

[0086] An example, Figure 3 is a flow chart of a method for testing visual inspection software according to an exemplary embodiment; Figure 3 As shown, under the Linux system of the WSL virtual machine of the test device, the test configuration file is copied to the task directory or folder to be tested under the Windows system of the test device through the cp command of the Linux system, and the copied test configuration file is marked as "processed".

[0087] S102: Based on the test configuration file, the visual inspection software to be tested is tested to obtain a test result.

[0088] As a possible implementation method, the script or program for automatically detecting the test configuration file under the Windows system of the test equipment is detected, and these scripts or programs input the pre-prepared original data and the corresponding true value data into the visual inspection software to be tested based on the test configuration file. The visual inspection software to be tested processes the input original data to obtain output data, and obtains the test result by comparing the output data with the corresponding true value data.

[0089] As another possible implementation method, a script or program for detecting whether there is an unprocessed test configuration file from the WSL virtual machine is pre-installed in the Windows system of the test device. When the existence of an unprocessed test configuration file from the WSL virtual machine is detected, based on the test configuration file, pre-prepared original data and corresponding true value data are input into the visual inspection software to be tested. The visual inspection software to be tested processes the input original data to obtain output data, and obtains the test result by comparing the output data with the corresponding true value data.

[0090] It can be understood that when the presence of an unprocessed configuration file is detected, the present application simulates the target test environment of the visual inspection software to be tested according to the recorded contents in the configuration file and performs a simulation test on the visual inspection software to be tested, thereby avoiding manual testing by developers, improving the testing efficiency of the visual inspection software, and avoiding errors caused by human subjectivity during manual testing.

[0091] In some embodiments, the test configuration file includes: identification information of the visual inspection software to be tested, path information of the test data, physical parameters of the image acquisition device, and path information of the processing parameters.

[0092] The test data includes original data and corresponding true value data, and the path information of the test data includes the path information of the original data and the path information of the corresponding true value data. The physical parameters of the image acquisition device include the physical characteristic information of the image acquisition device, such as the installation angle, the rotation angle and other information. The processing parameters of the image acquisition device include the parameters required for processing the source data acquired by the image acquisition device, such as the preset RT matrix, which is used to convert the source data into the target coordinate system.

[0093] As a possible implementation manner, the test configuration file includes path information of a calibration file, and the calibration file includes physical parameters and processing parameters of the image acquisition device.

[0094] In some embodiments, the test configuration file also includes target test module information, storage path information of output detection data, storage path information of test results, network configuration information of a development device for receiving test results, and a task name string for this test.

[0095] Among them, the target test module information is used to indicate the modules involved in the test of the visual inspection software to be tested; the network configuration information of the development device used to receive the test results is used to indicate the network identification of the development device that receives the test results; the task name string of this test is used to name the data or files generated during the test to distinguish them from files generated during other tests.

[0096] For example, Figure 4 is a schematic diagram of a different test module according to an exemplary embodiment; Figure 4 As shown, the target test module information may include specific dynamic object detection modules and static object detection modules. Dynamic objects include moving pedestrian detection modules, moving two-wheel vehicle detection modules, and moving four-wheel vehicle detection modules; static objects include lane line detection modules, traffic light detection modules, sidewalk detection modules, and cone barrel detection modules.

[0097] It can be understood that when the presence of an unprocessed configuration file is detected, the present application simulates the target test environment of the visual inspection software to be tested according to the recorded contents in the configuration file and performs a simulation test on the visual inspection software to be tested, thereby obtaining the detection data of the visual inspection software to be tested in the real environment and comparing it with the corresponding true value data. This avoids manual testing by developers while ensuring the accuracy of the test, improves the testing efficiency of the visual inspection software, and can also avoid errors caused by human subjectivity during manual testing.

[0098] In some embodiments, Figure 5 As shown, S102 can be specifically implemented as follows:

[0099] S201 . Obtain the visual inspection software to be tested according to the identification information of the visual inspection software to be tested, and obtain the test data according to the path information of the test data.

[0100] The test data includes original data and true value data corresponding to the original data.

[0101] As a possible implementation, S201 may be specifically implemented as follows:

[0102] S2011. Connect the Windows system of the test device to the Linux environment.

[0103] Specifically, the Windows system of the test device initializes the SSH communication method, sets the IP and communication port information of the Linux environment created by the WSL virtual machine, and thus connects to the Linux environment created by the WSL virtual machine, so as to continuously send the data or instructions required for the test to the Linux environment created by the WSL virtual machine during the test.

[0104] S2012. The Windows system of the test device parses the test configuration file and sends the relevant data indicated by the path information in the test configuration file to the Linux environment.

[0105] Specifically, the Windows system of the test device parses the test configuration file, obtains the test data and calibration file according to the path information of the test data and calibration file in the test configuration file, and sends the identification information of the visual inspection software to be tested, the original data in the test data, and the calibration file to the Linux environment. The calibration file includes the physical parameters and processing parameters of the image acquisition device.

[0106] As a possible implementation method, a script or program pre-installed in the Windows system of the test device for automatically sending raw data to the Linux environment is controlled to send raw data to the Linux environment by using the function of the os.system third-party library of Python and inputting the parameter of cmd.

[0107] S202, processing the original data, the physical parameters of the image acquisition device and the processing parameters through the visual inspection software to be tested to obtain the inspection data.

[0108] As another implementation method of the test device in the Linux environment, S202 may include:

[0109] S2021. Receive instructions and data from the Windows system of the test device.

[0110] The data from the Windows system of the test equipment includes the original data and calibration files in the test data; the instructions from the Window system of the test equipment are used to control the following functions in the Linux environment:

[0111] Get the visual inspection software to be tested.

[0112] The test data is obtained by processing the original data, the physical parameters of the image acquisition device and the processing parameters through the visual inspection software to be tested.

[0113] According to the instruction from the Windows system of the test device, the detection data is sent to the receiving port set by the instruction, so that the detection data is sent back to the Windows system of the test device.

[0114] Stop processing.

[0115] S2022. Obtain the visual inspection software to be tested according to the identification information of the visual inspection software to be tested.

[0116] As a possible implementation method, according to the identification information of the visual software to be tested, the code corresponding to the visual software to be tested is pulled from the local code repository of the WSL virtual machine and compiled to a preset compilation path to obtain the executable file of the visual software to be tested.

[0117] S2023. Process the original data, the physical parameters of the image acquisition device, and the processing parameters through the visual inspection software to be tested to obtain inspection data.

[0118] S2024. Send the detection data to the Windows system of the test device through the receiving port of the Windows system of the test device.

[0119] In some embodiments, after receiving the test data, the Windows system of the test device organizes the test data in a proto file format and stores it into a test data file in a pack format for comparison with the corresponding true value data to obtain the test results.

[0120] S203: Compare the test data with the corresponding true value data to obtain the test result.

[0121] As a possible implementation, Figure 6 As shown, S203 may include:

[0122] S2031. Create a test folder for storing test-related data according to the task name character string of this test in the test configuration file.

[0123] The name of the test folder is the content of the task name string of this test.

[0124] S2032. Save the test data and detection data of this test into the test folder.

[0125] As a possible implementation method, the detection data of this test and the true value data in the format of the gt file are saved in the test folder.

[0126] S2033. Compare the test data with the corresponding true value data to obtain the test result.

[0127] The test result includes a report file, which includes the task name, test time, test module of the visual inspection software to be tested, identification name of the test data, and pass rate of the test.

[0128] Figure 7 is a flowchart showing a method of obtaining detection data by processing a configuration file according to an exemplary embodiment. Figure 7 The steps shown include Figure 5 The complete process of one implementation of the illustrated embodiment includes:

[0129] S301. The Windows system of the test device reads a configuration file to obtain information of each path.

[0130] The path information includes path information of test data and path information of calibration data.

[0131] S302. The Windows system of the test device is connected to the WSL virtual machine.

[0132] S303, sending original data to the Linux environment through an instruction control script or program.

[0133] S304, controlling the Linux environment through instructions to process the raw data through the visual detection algorithm to be tested, obtaining detection data and sending it to the Windows system.

[0134] As a possible implementation method in the Linux environment of the test equipment, according to the preset compilation path of the visual inspection software to be tested in the Linux environment and the ssh_conn.exec_cmd function, the Linux environment is controlled to process the raw data through the visual inspection algorithm to be tested, obtain the inspection data and send it to the designated port of the Windows system.

[0135] As a possible implementation method of the test device in the Windows environment, the detection data sent by the Linux environment is received through a pre-installed script or program for receiving the detection data sent by the Linux environment through the zmq+queue method.

[0136] S305. When the detection data is sent, the Linux environment is controlled by instructions to end the operation of the visual detection software to be tested.

[0137] As a possible implementation manner, an instruction for instructing to end the running of the visual inspection software to be tested is sent to the Linux environment through the ssh_conn_exec_cmd function.

[0138] S306. When all test tasks are completed, close the connection with the WSL virtual machine.

[0139] It can be understood that the present application can accurately compare the visual processing accuracy of the visual inspection software to be tested by comparing the inspection data obtained by processing the original data with the corresponding true value data.

[0140] In some embodiments, Figure 8 As shown, before S201, the method may further include:

[0141] S401. The Windows system of the test device traverses the test configuration files in the task directory or folder to be tested.

[0142] S402: When there is a test configuration file not recorded in the task list under the task directory or folder to be tested, add the path of the not recorded test configuration file to the task list.

[0143] The task list is used to record the test configuration files being processed.

[0144] S403. According to the path of the test configuration file in the task list, access the test configuration file and obtain at least the identification information of the visual inspection software to be tested and the path information of the test data in the test configuration file.

[0145] In some embodiments, the test configuration file further includes path information of a first test case; the first test case includes at least one vehicle environment information. Fig. 9 As shown, S202 can be specifically implemented as follows:

[0146] S501. Obtain a first test case according to path information of the first test case.

[0147] The first test case includes at least one type of vehicle environment information, and each type of vehicle environment information includes a type identifier of the vehicle environment information and specific content of the type of vehicle environment information.

[0148] Exemplarily, some examples of vehicle environment information are listed below. The specific content corresponding to the type identification "scene" of the vehicle environment information may include at least one of the following: "urban area, expressway, underground garage, rural road, ramp, tunnel, construction section, toll station, winding mountain road"; the specific content corresponding to the type identification "road surface" of the vehicle environment information may include at least one of the following: "dry, wet, waterlogged, muddy, potholes, snow, unpaved road surface, paved road surface"; the specific content corresponding to the type identification "weather" of the vehicle environment information may include at least one of the following: "cloudy, sunny, heavy rain, light rain, snow, fog, dust"; the specific content corresponding to the type identification "time" of the vehicle environment information may include at least one of the following: "daytime, night, evening"; the specific content corresponding to the type identification "image quality" of the vehicle environment information may include at least one of the following: "normal, blurred, glare, occlusion"; the specific content corresponding to the type identification "road type" of the vehicle environment information may include at least one of the following: "straight road, curve, ramp, T-junction, intersection, roundabout, U-turn, uphill and downhill, bumpy".

[0149] S502: According to the first test case, target original data including at least one type of vehicle environment information is screened out from the original data.

[0150] The vehicle environment information reflected by the target original data includes at least one type of vehicle environment information.

[0151] As a possible implementation method, the original data includes image data, and each image data in the original data includes an image and a description of vehicle environment information of the image. The target original data is determined based on the description of the vehicle environment information of the image and at least one vehicle environment information in the first test case.

[0152] S503 , processing the target original data, the physical parameters of the image acquisition device and the processing parameters through the visual inspection software to be tested to obtain the inspection data.

[0153] It can be understood that the present application realizes the screening of the original data input into the visual inspection software to be tested by setting up test cases, and then realizes the testing of different modules of the visual inspection software to be tested by controlling the input data, thereby making the software testing process more targeted and further improving the efficiency of software testing.

[0154] In some embodiments, the test configuration file further includes path information of a second test case; the detection data includes the detection object identified by the visual detection software to be tested according to the original data and the motion parameters of the detection object; the second test case includes range information of at least one motion parameter of the object; Fig.10 As shown, S203 can be specifically implemented as follows:

[0155] S601. Obtain a second test case according to path information of the second test case.

[0156] The second test case includes range information of at least one motion parameter of the object, and the range information of each motion parameter includes a type identifier of the motion parameter and a restricted range thereof.

[0157] Exemplarily, some motion parameters with continuous values ​​are listed below: target lateral distance, target longitudinal distance, target speed, target heading angle, vehicle speed, vehicle acceleration, and vehicle angular velocity. Some motion parameters with discrete values: the range corresponding to the motion parameters whose type of motion parameters is identified as "target behavior intention" includes at least one of the following: "cut in, cut out, lane keeping, unprotected left turn, right turn, reversing, crossing zebra crossing, crossing, walking, running, and standing still"; the range corresponding to the motion parameters whose type of motion parameters is identified as "vehicle driving behavior" includes at least one of the following: "following the vehicle, changing lanes, cruising, turning left, turning right, reversing, merging in, and merging out".

[0158] S602: Determine target detection data according to range information of at least one motion parameter of the second test case.

[0159] The motion parameter of the detection object in the target detection data is within the range of at least one motion parameter of the second test case.

[0160] As a possible implementation, Fig.11 As shown, the detection data is parsed into a CSV file based on the parsing method of the proto library and the comma-separated values ​​(CSV) library, and the target detection data in the CSV file format is determined according to the range information of at least one motion parameter of the second test case. The target detection data in the CSV file format is used to compare with the corresponding true value data to obtain the test result.

[0161] S603: Compare the target detection data with the corresponding true value data to obtain a test result.

[0162] As a possible implementation, the second test case also includes a pass condition for the test. The pass condition for the test states that a certain data in the test data obtained by the visual inspection software to be tested from processing the original data is greater than or less than a preset threshold value. Only when the test data of the data satisfies the pass condition for the test, the visual inspection software to be tested is considered to have passed the test of the second test case.

[0163] It can be understood that the present application realizes the screening of detection data participating in true value comparison in the detection data of the visual detection software to be tested through the setting of test cases, so that targeted comparison can be made on the detection ability of the visual detection software to be tested for certain specific objects or the physical motion parameters of objects, thereby further improving the efficiency of software testing.

[0164] In some embodiments, the method is applied to a test device, and the test device and at least one visual inspection software development device are located in the same local area network; wherein the development device is used to generate a test configuration file and send the test configuration file to a configuration file directory of the test device via the local area network.

[0165] It is understandable that the present application arranges the development equipment and the automated visual inspection software test equipment in a local area network, making the debugging of the test equipment convenient and improving the operation efficiency. On the other hand, the constructed local area network does not generate additional connections with the external network, ensuring the security during the development and testing process. The development equipment sends the configured test configuration file to the test equipment through the local area network, and the configuration file can be detected and automatically processed by the test equipment, which also improves the degree of automation in the test process and simplifies the operation method.

[0166] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the test device or electronic device of the visual inspection software includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0167] The embodiment of the present application can exemplarily divide the functional modules of the test device or electronic device of the visual detection software according to the above method. For example, the test device or electronic device of the visual detection software may include various functional modules corresponding to the various functional divisions, or two or more functions may be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0168] Fig.12is a block diagram of a testing device for visual inspection software according to an exemplary embodiment. Fig.12 The testing device 700 of the visual inspection software includes an acquisition unit 701 and a testing unit 702 .

[0169] The acquisition unit 701 is used to acquire a test configuration file.

[0170] Among them, the test configuration file is used to simulate the target test environment of the visual inspection software to be tested; the target test environment is an environment in which the visual software to be tested completes image detection by interacting with the image acquisition device on the vehicle.

[0171] The testing unit 702 is used to test the visual inspection software to be tested based on the test configuration file to obtain the test result.

[0172] Optionally, the test configuration file includes: identification information of the visual inspection software to be tested, path information of the test data, physical parameters of the image acquisition device, and path information of the processing parameters.

[0173] Optionally, the test unit 702 is specifically used to obtain the visual inspection software to be tested according to the identification information of the visual inspection software to be tested, and to obtain the test data according to the path information of the test data; wherein the test data includes original data and true value data corresponding to the original data; the original data, the physical parameters of the image acquisition device and the processing parameters are processed by the visual inspection software to be tested to obtain the inspection data; the inspection data is compared with the corresponding true value data to obtain the test result.

[0174] Optionally, the test configuration file also includes path information of the first test case; the first test case includes at least one vehicle environment information; the test unit 702 is specifically used to: obtain the first test case according to the path information of the first test case; according to the first test case, filter out target original data including at least one vehicle environment information from the original data; process the target original data, physical parameters of the image acquisition device and processing parameters through the visual inspection software to be tested to obtain the inspection data.

[0175] Optionally, the test configuration file also includes path information of a second test case; the detection data includes the detection object identified by the visual detection software to be tested based on the original data and the motion parameters of the detection object; the second test case includes range information of at least one motion parameter of the object; the test unit 702 is specifically used to: obtain the second test case based on the path information of the second test case; determine the target detection data based on the range information of at least one motion parameter of the second test case; wherein the motion parameters of the detection object in the target detection data are within the range of at least one motion parameter of the second test case; compare the target detection data with the corresponding true value data to obtain the test result.

[0176] Optionally, the testing device 700 for visual inspection software is applied to a testing device, and the testing device and at least one development device for visual inspection software are located in the same local area network; wherein the development device is used to generate a test configuration file and send the test configuration file to a configuration file directory of the testing device via the local area network.

[0177] Fig.13 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Fig.13 As shown, the electronic device 800 includes but is not limited to: a processor 801 and a memory 802 .

[0178] The memory 802 is used to store executable instructions of the processor 801. It can be understood that the processor 801 is configured to execute instructions to implement the test method of the visual inspection software in the above embodiment.

[0179] It should be noted that those skilled in the art can understand that Fig.13 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Fig.13 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0180] The processor 801 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 802, and calling data stored in the memory 802, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 801 may include one or more processing units. Optionally, the processor 801 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 801.

[0181] The memory 802 can be used to store software programs and various data. The memory 802 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application program required by at least one functional module (such as the acquisition unit 701 and the test unit 702), etc. In addition, the memory 802 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0182] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 802 including instructions, and the above instructions can be executed by a processor 801 of an electronic device 800 to implement the test method of the visual inspection software in the above embodiment.

[0183] In actual implementation, Fig.12 The functions of the acquisition unit 701 and the test unit 702 in the embodiment can be represented by Fig.13 The processor 801 in the embodiment calls the computer program stored in the memory 802. The specific execution process can refer to the description of the test method of the visual inspection software in the above embodiment, which will not be repeated here.

[0184] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0185] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, which can be executed by a processor of an electronic device to complete the testing method of the visual inspection software in the above embodiment.

[0186] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the embodiment of the testing method of the above-mentioned visual inspection software are implemented, and the same technical effect as the testing method of the above-mentioned visual inspection software can be achieved. In order to avoid repetition, they will not be repeated here.

[0187] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0188] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0189] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0190] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0191] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0192] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A testing method for visual inspection software, It is characterized in that The method comprises: In the case where an unprocessed test configuration file is detected, a test configuration file is obtained; the test configuration file is used to simulate a target test environment of the visual inspection software to be tested; the target test environment is an environment in which the visual inspection software to be tested completes image detection by interacting with an image acquisition device on a vehicle; Based on the test configuration file, the visual inspection software to be tested is tested to obtain a test result.

2. The method according to claim 1, It is characterized in that The test configuration file includes: identification information of the visual inspection software to be tested, path information of test data, physical parameters of the image acquisition device, and path information of processing parameters.

3. The method according to claim 2, It is characterized in that The testing of the visual inspection software to be tested based on the test configuration file to obtain a test result includes: Acquire the visual inspection software to be tested according to the identification information of the visual inspection software to be tested, and acquire the test data according to the path information of the test data; wherein the test data includes original data and true value data corresponding to the original data; Processing the raw data, the physical parameters of the image acquisition device and the processing parameters through the visual inspection software to be tested to obtain inspection data; The detection data is compared with the corresponding true value data to obtain a test result.

4. The method according to claim 3, It is characterized in that The test configuration file further includes path information of a first test case; the first test case includes at least one vehicle environment information; The step of processing the raw data, the physical parameters of the image acquisition device and the processing parameters by the visual inspection software to be tested to obtain the inspection data includes: Acquire the first test case according to the path information of the first test case; According to the first test case, selecting target original data including the at least one vehicle environment information from the original data; The target original data, the physical parameters of the image acquisition device and the processing parameters are processed by the visual inspection software to be tested to obtain the inspection data.

5. The method according to claim 3, It is characterized in that The test configuration file also includes path information of a second test case; the detection data includes a detection object identified by the visual detection software to be tested according to the original data and motion parameters of the detection object; the second test case includes range information of at least one motion parameter of the object; The step of comparing the detection data with the corresponding true value data to obtain a test result includes: Acquire the second test case according to the path information of the second test case; Determining target detection data according to the range information of at least one motion parameter of the second test case; wherein the motion parameter of the detection object of the target detection data is within the range of at least one motion parameter of the second test case; The target detection data is compared with the corresponding true value data to obtain a test result.

6. The method according to any one of claims 1 to 5, It is characterized in that The method is applied to a test device, which is located in the same local area network as at least one visual inspection software development device; wherein the development device is used to generate the test configuration file and send the test configuration file to the configuration file directory of the test device through the local area network.

7. A test device for visual inspection software, It is characterized in that The device comprises: an acquisition unit and a testing unit; The acquisition unit is used to acquire a test configuration file, wherein the test configuration file is used to simulate a target test environment of the visual detection software to be tested; the target test environment is an environment in which the visual software to be tested completes image detection by interacting with an image acquisition device on a vehicle; The testing unit is used to test the visual inspection software to be tested based on the test configuration file to obtain a test result.

8. An electronic device, It is characterized in that include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, It is characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method as claimed in any one of claims 1 to 6.

10. A computer program product, It is characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed on an electronic device, the electronic device performs the method according to any one of claims 1 to 6.