Testing method of image testing device and image testing device

Abstract

The invention provides a testing method of an image testing device and the image testing device. The testing method of the image testing device comprises the following steps: arranging a sensor to be tested at a first position to acquire a first image; obtaining a second position according to the first image, and moving the sensor to be tested to the second position to collect a second image; obtaining a correction coefficient through the first image and the second image; acquiring a first evaluation image at the first position through the to-be-tested sensor, acquiring a second original evaluation image at the second position through the comparison sensor, and obtaining a second evaluation image through the correction coefficient and the second original evaluation image; and obtaining a performance test result of the to-be-tested sensor through the first evaluation image and the second evaluation image. According to the invention, space errors caused by different positions of shooting objects are reduced, and errors caused by shooting angles are reduced.

Description

Technical Field

[0001] The present invention relates to the field of image technology, and in particular, to a test method for an image test device and an image test device. Background Art

[0002] For the field of images, a primary goal is to improve the quality of the processed images. In fact, whether it is an image signal processing module (ISP) or an image sensor, after being modularized, image quality assessment is required. Image quality assessment includes subjective assessment and objective assessment. During testing, the sensor to be tested is generally set at different positions to capture images of the target object at different positions for image quality assessment. Moreover, the assessment objects include not only the sensor to be tested but also some comparison sensors for comparison. During the test, the sensor to be tested generally needs to be moved to the position of the comparison sensor to capture images of the target object at different positions. The above test methods have the following problems:

[0003] (1) If the sensor to be tested is directly fixed at different positions, it is easy to introduce spatial errors due to photographing the object at different positions;

[0004] (2) Although the photographed target object is the same, due to the influence of parameters such as sensor coordinates and brightness, additional errors will be introduced;

[0005] (3) If the sensor is moved manually during the test, such as manually replacing the comparison sensor with the sensor to be tested and manually aligning with the target, it is not only time-consuming and laborious but also introduces errors caused by human intervention, reducing the test efficiency and test accuracy.

[0006] Therefore, it is necessary to provide a new test method for an image test device and an image test device to solve the above problems existing in the prior art. Summary of the Invention

[0007] The purpose of the present invention is to provide a test method for an image test device and an image test device, so as to reduce the spatial errors caused by different positions of the photographed object, reduce the errors caused by the shooting angle, and improve the test efficiency and test accuracy.

[0008] To achieve the above purpose, the test method for the image test device of the present invention includes the following steps:

[0009] S1. Set the sensor to be tested at a first position to capture a first image;

[0010] S2. Obtain a second position based on the first image, and move the sensor to be tested to the second position to capture a second image;

[0011] S3. Obtain a correction coefficient from the first image and the second image;

[0012] S4. Collect a first evaluation image at the first position by the to-be-tested sensor, collect a second original evaluation image at the second position by the comparison sensor, and obtain a second evaluation image from the correction coefficient and the second original evaluation image;

[0013] S5. Obtain a performance test result of the to-be-tested sensor from the first evaluation image and the second evaluation image.

[0014] The beneficial effect of the test method of the image test device of the present invention is that: through step S2, obtaining the second position according to the first image reduces the spatial error caused by different positions of the photographed object; through step S3, obtaining a correction coefficient from the first image and the second image, and obtaining a second evaluation image from the correction coefficient and the second original evaluation image, which can reduce the error caused by the shooting angle and improve the test efficiency and test accuracy.

[0015] Preferably, in step S2, the step of obtaining the second position according to the first image includes: collecting a third image by the comparison sensor, and comparing and analyzing the target object in the third image with the target object in the first image to obtain the second position. The beneficial effect is that: when the comparison sensor performs position self-correction, the target object in the first image collected by the to-be-tested sensor at the first position is used as the correction reference, which is beneficial to improving the accuracy of the position correction of the comparison sensor and reducing the spatial error caused by different positions of the photographed object.

[0016] Preferably, in step S2, the step of collecting a third image by the comparison sensor and comparing and analyzing the target object in the third image with the target object in the first image to obtain the second position includes:

[0017] S21. Collect the third image by the comparison sensor and detect a first quantity of the target object in the third image;

[0018] S22. Compare and analyze the first quantity of the target object in the third image with a second quantity of the target object in the first image;

[0019] S23. When the first quantity is not equal to the second quantity, adjust the position of the comparison sensor, and repeat steps S21 and S22 until the first quantity is equal to the second quantity;

[0020] S24. Detect the geometric center coordinates of each target object in the third image;

[0021] S25. Compare the geometric center coordinates of each target object in the third image with the geometric center coordinates of each target object in the first image to obtain the difference in the geometric center coordinates of each target object;

[0022] S26. When the difference in the geometric center coordinates of each target object is greater than or equal to a preset threshold, adjust the position of the comparison sensor, and repeat the steps from S21 to S25 until the difference in the geometric center coordinates of each target object is less than the preset threshold to obtain the second position. The beneficial effect is that if the number of target objects is inconsistent, the content clearly captured by the comparison sensor and the test sensor will be inconsistent. Therefore, first performing a comparative analysis of the number of target objects is beneficial for saving computing time and reducing the workload. At the same time, adding constraints on the geometric center coordinates of each target object is more helpful for automatically correcting the position of the comparison sensor, which is beneficial for reducing the spatial error caused by different positions of the photographed objects and improving the test accuracy.

[0023] Preferably, in step S3, the step of obtaining the calibration coefficient through the first image and the second image includes:

[0024] Compare and analyze the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generate a brightness calibration coefficient and a perspective transformation matrix. The beneficial effect is that it performs brightness compensation and geometric compensation on the second original evaluation image collected by the comparison sensor, which can reduce the error introduced by using the test tooling and effectively reduce the error caused by different shooting angles.

[0025] Preferably, in step S3, the step of comparing and analyzing the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating a brightness calibration coefficient and a perspective transformation matrix includes:

[0026] S311. Statistically analyze the first brightness data of the first image and the second brightness data of the second image, and analyze and calculate the first brightness data and the second brightness data to obtain the brightness error between the first image and the second image;

[0027] S312. Statistically analyze pixel information based on the brightness error to obtain the brightness calibration coefficient. The beneficial effect is that it is beneficial for performing more accurate brightness compensation on the second original evaluation image collected by the comparison sensor, thereby reducing the error caused by different shooting angles.

[0028] Preferably, in step S3, the step of comparing and analyzing the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating a brightness correction coefficient and a perspective transformation matrix includes:

[0029] S321. Detect a first coordinate space of the target object in the first image and a second coordinate space of the target object in the second image;

[0030] S322. Calculate the perspective transformation matrix according to the first coordinate space and the second coordinate space. The beneficial effect is that it is beneficial to perform more accurate geometric compensation on the second original evaluation image collected by the comparison sensor, thereby reducing the error caused by different shooting angles.

[0031] Preferably, in step S4, the step of obtaining a second evaluation image by using the correction coefficient and the second original evaluation image includes: performing brightness compensation and geometric compensation on the second original evaluation image by using the brightness correction coefficient and the perspective transformation matrix to obtain the second evaluation image. The beneficial effect is that, that is, performing brightness compensation and geometric compensation on the second original evaluation image collected by the comparison sensor can reduce the error introduced by using the test tooling and effectively reduce the error caused by different shooting angles.

[0032] The image testing device of the present invention includes:

[0033] A sensor to be tested, which is used to collect a first image and a first evaluation image at a first position;

[0034] A comparison sensor, which is used to collect a second original evaluation image;

[0035] A position adjustment module, which is respectively connected to the sensor to be tested and the comparison sensor. The position adjustment module is used to obtain a second position according to the first image, so that the comparison sensor collects the second original evaluation image at the second position, and move the sensor to be tested to the second position to collect a second image;

[0036] A correction module, which is respectively connected to the sensor to be tested and the comparison sensor. The correction module is used to obtain a correction coefficient through the first image and the second image, and obtain a second evaluation image through the correction coefficient and the second original evaluation image;

[0037] A processing module, which is respectively connected to the sensor to be tested and the correction module. The processing module is used to obtain a performance test result of the sensor to be tested through the first evaluation image and the second evaluation image.

[0038] The beneficial effects of the image testing device of the present invention are as follows: By connecting the position adjustment module to the sensor to be tested and the comparison sensor respectively, the position adjustment module is used to obtain a second position according to the first image, so as to reduce the spatial error caused by the different positions of the photographed object. By connecting the calibration module to the sensor to be tested and the comparison sensor respectively, the calibration module is used to obtain a calibration coefficient through the first image and the second image, and to obtain a second evaluation image through the calibration coefficient and the second original evaluation image, so as to reduce the error caused by the shooting angle.

[0039] Preferably, the image testing device further includes a test fixture. The test fixture includes a driving member, a sensor fixing member, and a test bracket disposed in the test scene. The sensor fixing member is used to fix the sensor to be tested and the comparison sensor in the test bracket. The driving member is respectively connected to the sensor fixing member and the position adjustment module; the driving member is used to drive the sensor fixing member to move according to the adjustment instruction sent by the position adjustment module, so as to drive the sensor to be tested and the comparison sensor to move in the test bracket. The beneficial effects are as follows: The driving member adjusts and drives the comparison sensor and the sensor to be tested to automatically move in the test bracket according to the instruction, so that not only the error introduced by human intervention can be reduced, but also more test data can be obtained within a certain time compared with manual operation, greatly improving the test efficiency and test accuracy.

[0040] Preferably, the image testing device further includes a processor, and the processor is used to load and execute the instructions of the test method of the image testing device. Description of the Drawings

[0041] Figure 1 It is a schematic diagram of the frame structure of the image testing device according to an embodiment of the present invention;

[0042] Figure 2 It is a schematic diagram of the flow of the test method of the image testing device according to an embodiment of the present invention;

[0043] Figure 3 It is a schematic diagram of the flow of the position correction of the comparison sensor in an embodiment of the present invention. Detailed Embodiments

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely below. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein shall have the ordinary meanings as understood by those of ordinary skill in the art to which the present invention pertains. The words such as "including" used herein are intended to mean that the elements or items appearing before this word cover the elements or items listed after this word and their equivalents, without excluding other elements or items.

[0045] To overcome the problems existing in the prior art, the embodiments of the present invention provide a test method and an image test device for an image test device, so as to reduce the spatial error caused by different positions of the photographed object and reduce the error caused by the shooting angle, thereby improving the accuracy of image quality evaluation.

[0046] Figure 1 It is a schematic diagram of the frame structure of the image test device according to the embodiment of the present invention.

[0047] In some embodiments of the present invention, with reference to Figure 1, the described image testing device includes a sensor 1 to be tested, a comparison sensor 2, a processing module 3, a position adjustment module 4, and a calibration module 5. The sensor 1 to be tested is respectively connected to the processing module 3, the position adjustment module 4, and the calibration module 5. The comparison sensor 2 is respectively connected to the position adjustment module 4 and the calibration module 5. The calibration module 5 is connected to the processing module 3. The sensor 1 to be tested is used to collect a first image and a first evaluation image at a first position. Among them, the sensor 1 to be tested is further used to send the first image to the position adjustment module 4 and the calibration module 5, and send the first evaluation image to the processing module 3. The comparison sensor 2 is used to collect a second original evaluation image and send the second original evaluation image to the calibration module 5. The position adjustment module 4 is used to obtain a second position according to the first image, so that the comparison sensor 2 collects the second original evaluation image at the second position, and move the sensor 1 to be tested to the second position to collect the second image. The sensor 1 to be tested sends the second image to the calibration module 5. The calibration module 5 is used to obtain a calibration coefficient through the first image and the second image, and obtain a second evaluation image through the calibration coefficient and the second original evaluation image, and send the second evaluation image to the processing module 3. The processing module 3 is used to obtain the performance test result of the sensor 1 to be tested through the first evaluation image and the second evaluation image.

[0048] Specifically, by connecting the position adjustment module to the sensor 1 to be tested and the comparison sensor respectively, the position adjustment module is used to obtain a second position according to the first image, so as to reduce the spatial error caused by different positions of the photographed object. By connecting the calibration module to the sensor 1 to be tested and the comparison sensor respectively, the calibration module is used to obtain a calibration coefficient through the first image and the second image, and obtain a second evaluation image through the calibration coefficient and the second original evaluation image, so as to reduce the error caused by the shooting angle, thereby improving the accuracy of image quality evaluation.

[0049] In some embodiments of the present invention, the image testing device further includes a parameter setting module 6. The parameter setting module 6 is respectively connected to the sensor 1 to be tested and the comparison sensor 2. The parameter setting module 6 is used to configure user parameters and build a test scenario.

[0050] In some embodiments of the present invention, the image testing device further includes a testing tooling. The testing tooling includes a driving member, a sensor fixing member, and a testing bracket disposed in the testing scenario. The sensor fixing member is used to fix the sensor to be tested and the comparison sensor in the testing bracket. Refer to Figure 1 , the driving member 7 is respectively connected to the sensor fixing member and the position adjustment module 4; the driving member 7 is configured to drive the sensor fixing member to move according to the adjustment instruction sent by the position adjustment module 4, so as to drive the sensor to be tested 1 and the comparison sensor 2 to move in the testing bracket. The driving member 7 drives the comparison sensor 2 and the sensor to be tested 1 to automatically move in the testing bracket, so that not only can the error introduced by human intervention be reduced, but also more test data can be obtained within a certain period of time compared with manual operation, greatly improving the test efficiency and test accuracy.

[0051] Specifically, the position adjustment module 4 is configured to send an adjustment instruction to the driving member 7. The adjustment instruction includes a position correction instruction and a position movement instruction. The driving member 7 drives the sensor fixing member to move according to the position correction instruction to drive the comparison sensor 2 to move in the testing bracket, so as to automatically correct the position of the comparison sensor 2 to obtain the second position; the driving member 7 drives the sensor fixing member to move according to the position movement instruction to drive the sensor to be tested 1 to move from the first position of the testing bracket to the second position, so as to collect the second image.

[0052] In some embodiments of the present invention, refer to Figure 1 , the position adjustment module 4 includes a correction unit 41. The correction unit 41 is respectively connected to the driving member 7, the sensor to be tested 1, and the comparison sensor 2. The comparison sensor 2 is configured to collect a third image and send it to the correction unit 41. The sensor to be tested 1 sends the collected first image to the correction unit 41. The correction unit 41 is configured to compare and analyze the target object in the third image and the target object in the first image, and send a position correction instruction to the driving member 7 according to the result of the comparison and analysis, so as to automatically correct the position of the comparison sensor 2 to obtain the second position. When the comparison sensor 2 performs position self-correction, the target object in the first image collected by the sensor to be tested 1 at the first position is used as the correction reference, which is beneficial to improving the accuracy of the position correction of the comparison sensor 2 and reducing the spatial error caused by the different positions of the shooting objects.

[0053] In some embodiments of the present invention, refer to Figure 1, the position adjustment module 4 further includes an adjustment unit 42 connected to the correction unit 41, and the adjustment unit 42 is connected to the driving member 7. After the correction unit 41 performs position self-correction on the comparison sensor 2, it sends correction end information to the adjustment unit 42. After receiving the correction end information, the adjustment unit 42 sends a position movement instruction to the driving member 7, so that the sensor 1 to be tested moves from the first position of the test bracket to the second position.

[0054] In some embodiments of the present invention, refer to Figure 1 , the calibration module 5 includes a calibration coefficient acquisition unit 51 and a compensation unit 52 connected to each other. The calibration coefficient acquisition unit 51 is connected to the sensor 1 to be tested, and the compensation unit 52 is connected to the comparison sensor 2 and the processing module 3 respectively. The calibration coefficient acquisition unit 51 is used to compare and analyze the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object to obtain a brightness calibration coefficient and a perspective transformation matrix and send them to the compensation unit 52; the compensation unit 52 is used to perform brightness compensation and geometric compensation on the second original evaluation image by using the brightness calibration coefficient and the perspective transformation matrix to obtain a second evaluation image, and send the second evaluation image to the processing module 3. Performing brightness compensation and geometric compensation on the sensor 1 to be tested can reduce the error introduced by using the test tooling, and can effectively reduce the error caused by different shooting angles of the sensor 1 to be tested.

[0055] In some embodiments of the present invention, the image testing device further includes a processor, and the processor is used to load and execute the instructions of the testing method of the image testing device.

[0056] Figure 2 It is a schematic flow chart of the testing method of the image testing device according to the embodiments of the present invention.

[0057] In some embodiments of the present invention, refer to Figure 2 , the testing method of the image testing device includes the following steps:

[0058] S1. Set the sensor to be tested at the first position to collect a first image;

[0059] S2. Obtain a second position according to the first image, and move the sensor to be tested to the second position to collect a second image;

[0060] S3. Obtain a calibration coefficient through the first image and the second image;

[0061] S4. Collect a first evaluation image at the first position through the sensor to be tested, collect a second original evaluation image at the second position through the comparison sensor, and obtain a second evaluation image by using the correction coefficient and the second original evaluation image;

[0062] S5. Obtain a performance test result of the sensor to be tested by using the first evaluation image and the second evaluation image.

[0063] Specifically, through step S2, obtaining the second position according to the first image reduces the spatial error caused by different positions of the photographed object. Through step S3, obtaining the correction coefficient by using the first image and the second image, and obtaining the second evaluation image by using the correction coefficient and the second original evaluation image reduces the error caused by the shooting angle, thereby improving the test efficiency and test accuracy.

[0064] In some embodiments of the present invention, in a test scenario without change, such as a static test scenario, the first image can be directly used as the first evaluation image.

[0065] In some embodiments of the present invention, in a test scenario with change, such as a dynamic test scenario, when collecting the evaluation image, the sensor to be tested needs to be moved back from the second position to the first position. At the same time, collect the first evaluation image at the first position through the sensor to be tested, and collect the second original evaluation image at the second position through the comparison sensor, so there is no time delay and the error caused by the shooting time is reduced.

[0066] In some embodiments of the present invention, before step S1 is executed, the following steps are further included: S0. Configure user parameters and build a test scenario.

[0067] In some embodiments of the present invention, in step S0, the step of configuring user parameters includes: configuring and loading the parameters of the sensor to be tested and the comparison sensor, and performing global data interaction configuration to enable the sensor to be tested and the comparison sensor to establish a mapping relationship. So that the sensor to be tested and the comparison sensor can perform global data interaction in the shared area.

[0068] In some embodiments of the present invention, before step S1 is executed, the following steps are further included: fixing the sensor to be tested and the comparison sensor in a test fixture.

[0069] In some embodiments of the present invention, in step S2, the step of obtaining a second position based on the first image and moving the sensor to be tested to the second position to collect a second image includes: driving the comparison sensor to move in the test fixture to automatically correct the position of the comparison sensor to obtain the second position; driving the sensor to be tested to move from the first position of the test fixture to the second position to collect the second image. The comparison sensor and the sensor to be tested automatically move in the test fixture according to instructions, which can not only reduce the errors introduced by human intervention, but also obtain more test data within a certain period of time compared with manual operation, greatly improving the test efficiency and test accuracy.

[0070] In some embodiments of the present invention, in step S1, the step of setting the sensor to be tested at a first position to collect a first image includes: setting the sensor to be tested at the first position and aligning the sensor to be tested with the target object in the test scene, and then collecting the first image through the sensor to be tested.

[0071] In some embodiments of the present invention, in step S2, the step of obtaining a second position based on the first image includes: collecting a third image through the comparison sensor, and comparing and analyzing the target object in the third image with the target object in the first image to obtain the second position. When the comparison sensor performs position self-correction, using the target object in the first image collected by the sensor to be tested at the first position as the correction reference is beneficial to improving the accuracy of the position correction of the comparison sensor, reducing the spatial error caused by the different positions of the photographed objects.

[0072] Figure 3 It is a schematic flow diagram of the position correction of the comparison sensor in the embodiments of the present invention.

[0073] In some embodiments of the present invention, in step S2, the step of collecting a third image through the comparison sensor and comparing and analyzing the target object in the third image with the target object in the first image to obtain the second position includes:

[0074] S21. Collect the third image through the comparison sensor and detect the first quantity of the target object in the third image;

[0075] S22. Compare and analyze the first quantity of the target object in the third image with the second quantity of the target object in the first image;

[0076] S23. When the first quantity is not equal to the second quantity, adjust the position of the comparison sensor, and repeat step S21 and step S22 until the first quantity is equal to the second quantity;

[0077] S24. Detect the geometric center coordinates of each target object in the third image;

[0078] S25. Compare the geometric center coordinates of each target object in the third image with the geometric center coordinates of each target object in the first image to obtain the geometric center coordinate difference of each target object;

[0079] S26. When the geometric center coordinate difference of each target object is greater than or equal to a preset threshold, adjust the position of the comparison sensor, and repeat the steps from step S21 to step S25 until the geometric center coordinate difference of each target object is less than the preset threshold to obtain the second position. If the number of target objects is inconsistent, the content captured by the comparison sensor and the test sensor is significantly different. Therefore, performing the consistency analysis of the number of target objects first helps to save the operation time and reduce the workload; at the same time, adding the constraint of the geometric center coordinates of each target object is more conducive to automatically correcting the position of the comparison sensor, which helps to reduce the spatial error caused by the different positions of the photographed objects and improve the test accuracy.

[0080] In some embodiments of the present invention, before performing step S21, the following steps are further included: detecting the second quantity of target objects in the first image.

[0081] In some embodiments of the present invention, if there are multiple comparison sensors, after performing step S26, the following steps are further included: sequentially correcting the positions of the multiple comparison sensors according to the steps from step S21 to step S26.

[0082] In some embodiments of the present invention, several target objects may be detected during the automatic detection process. The more the number of target objects, the more it is equivalent to increasing the constraint on the geometric center of the target object, which is more conducive to automatically correcting the position of the comparison sensor.

[0083] In some embodiments of the present invention, in the step S25, it further includes: performing consistency analysis on the relative positions between the geometric center coordinates of each target object in the third image and the relative positions between the geometric center coordinates of each target object in the first image. When the difference between the geometric center coordinates of each target object is less than a preset threshold, that is, the geometric center coordinates of each target object in the third image are basically the same as the geometric center coordinates of each target object in the first image, the relative positions between the geometric center coordinates of each target object in the third image and the relative positions between the geometric center coordinates of each target object in the first image are basically consistent.

[0084] In some embodiments of the present invention, in the step S3, the step of obtaining the correction coefficient by using the first image and the second image includes: comparing and analyzing the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating a brightness correction coefficient and a perspective transformation matrix. That is, performing brightness compensation and geometric compensation on the second original evaluation image collected by the comparison sensor can reduce the error introduced by using the test tooling and effectively reduce the error caused by different shooting angles.

[0085] In some embodiments of the present invention, in the step S3, the step of comparing and analyzing the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating a brightness correction coefficient and a perspective transformation matrix includes:

[0086] S311. Statistically analyze the first brightness data of the first image and the second brightness data of the second image, and analyze and calculate the first brightness data and the second brightness data to obtain the brightness error between the first image and the second image;

[0087] S312. Statistically analyze the pixel information according to the brightness error to obtain the brightness correction coefficient. This is beneficial for performing more accurate brightness compensation on the second original evaluation image collected by the comparison sensor, thereby reducing the error caused by different shooting angles.

[0088] In some embodiments of the present invention, in the step S3, the step of comparing and analyzing the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating a brightness correction coefficient and a perspective transformation matrix includes:

[0089] S321. Detect the first coordinate space of the target object in the first image and the second coordinate space of the target object in the second image;

[0090] S322. Calculate the perspective transformation matrix based on the first coordinate space and the second coordinate space. This is beneficial for performing more accurate geometric compensation on the second original evaluation image collected by the comparison sensor, thereby reducing the error caused by different shooting angles.

[0091] In some embodiments of the present invention, in the step S4, the step of obtaining the second evaluation image by using the correction coefficient and the second original evaluation image includes: performing brightness compensation and geometric compensation on the second original evaluation image by using the brightness correction coefficient and the perspective transformation matrix to obtain the second evaluation image. That is, performing brightness compensation and geometric compensation on the second original evaluation image collected by the comparison sensor can reduce the error introduced by using the test fixture and effectively reduce the error caused by different shooting angles.

[0092] In some embodiments of the present invention, in the step S5, the step of obtaining the performance test result of the sensor to be tested by using the first evaluation image and the second evaluation image includes: evaluating the image quality of the first evaluation image and the second evaluation image to obtain the performance test result of the sensor to be tested.

[0093] Although the embodiments of the present invention have been described in detail above, it is obvious to those skilled in the art that various modifications and changes can be made to these embodiments. However, it should be understood that such modifications and changes are all within the scope and spirit of the present invention described in the claims. Moreover, the present invention described herein can have other embodiments and can be implemented or realized in various ways.

Claims

1. A testing method for an image testing device, characterized in that, Including the following steps: S1. Set the sensor to be tested at the first position to collect the first image; S2. Obtain the second position based on the first image, and move the sensor to be tested to the second position to collect the second image; S3. Obtain a correction coefficient based on the first image and the second image; S4. Collect a first evaluation image at the first position by the sensor to be tested, collect a second original evaluation image at the second position by the comparison sensor, and obtain a second evaluation image based on the correction coefficient and the second original evaluation image; S5. Obtain the performance test result of the sensor to be tested based on the first evaluation image and the second evaluation image.

2. The testing method of the image testing device according to claim 1, characterized in that, In step S2, the step of obtaining the second position based on the first image includes: Collect a third image by the comparison sensor, and perform comparison and analysis on the target object in the third image and the target object in the first image to obtain the second position.

3. The testing method of the image testing device according to claim 3, characterized in that, In step S2, the step of collecting a third image by the comparison sensor and performing comparison and analysis on the target object in the third image and the target object in the first image to obtain the second position includes: S21. Collect the third image by the comparison sensor, and detect the first quantity of the target object in the third image; S22. Perform comparison and analysis on the first quantity of the target object in the third image and the second quantity of the target object in the first image; S23. When the first quantity is not equal to the second quantity, adjust the position of the comparison sensor, and repeat steps S21 and S22 until the first quantity is equal to the second quantity; S24. Detect the geometric center coordinates of each target object in the third image; S25. Perform comparison on the geometric center coordinates of each target object in the third image and the geometric center coordinates of each target object in the first image to obtain the geometric center coordinate difference of each target object; S26. When the geometric center coordinate difference of each target object is greater than or equal to a preset threshold, adjust the position of the comparison sensor, and repeat steps S21 to S25 until the geometric center coordinate difference of each target object is less than the preset threshold to obtain the second position.

4. The testing method of the image testing device according to claim 1, characterized in that, In step S3, the step of obtaining a correction coefficient based on the first image and the second image includes: Perform comparison and analysis on the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generate a brightness correction coefficient and a perspective transformation matrix.

5. The testing method of the image testing device according to claim 4, wherein, In step S3, the step of performing comparison and analysis on the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating a brightness correction coefficient and a perspective transformation matrix includes: S311. Statistically analyze the first brightness data of the first image and the second brightness data of the second image, and analyze and calculate the first brightness data and the second brightness data to obtain the brightness error between the first image and the second image; S312. Statistically analyze the pixel information according to the brightness error to obtain the brightness correction coefficient.

6. The testing method of the image testing device according to claim 4, characterized in that, In the step S3, the steps of comparing and analyzing the brightness error between the first image and the second image and the spatial error of the geometric center coordinates of the target object, and generating the brightness correction coefficient and the perspective transformation matrix include: S321. Detect the first coordinate space of the target object in the first image and the second coordinate space of the target object in the second image; S322. Calculate the perspective transformation matrix according to the first coordinate space and the second coordinate space.

7. The testing method of the image testing device according to claim 4, characterized in that In the step S4, the steps of obtaining the second evaluation image through the correction coefficient and the second original evaluation image include: Perform brightness compensation and geometric compensation on the second original evaluation image by using the brightness correction coefficient and the perspective transformation matrix to obtain the second evaluation image.

8. An image testing device, characterized in that, including: A sensor to be tested, configured to collect a first image and a first evaluation image at a first position; A comparison sensor, configured to collect a second original evaluation image; A position adjustment module, respectively connected to the sensor to be tested and the comparison sensor. The position adjustment module is configured to obtain a second position according to the first image, so that the comparison sensor collects the second original evaluation image at the second position, and move the sensor to be tested to the second position to collect the second image; A correction module, respectively connected to the sensor to be tested and the comparison sensor. The correction module is configured to obtain a correction coefficient through the first image and the second image, and obtain a second evaluation image through the correction coefficient and the second original evaluation image; A processing module, respectively connected to the sensor to be tested and the correction module. The processing module is configured to obtain a performance test result of the sensor to be tested through the first evaluation image and the second evaluation image.

9. The image testing device according to claim 8, wherein, Further included is a test tooling, which includes a driving member, a sensor fixing member, and a test bracket disposed in the test scenario. The sensor fixing member is configured to fix the sensor to be tested and the comparison sensor in the test bracket. The driving member is respectively connected to the sensor fixing member and the position adjustment module; the driving member is configured to drive the sensor fixing member to move according to an adjustment instruction sent by the position adjustment module, so as to drive the sensor to be tested and the comparison sensor to move in the test bracket.

10. The image testing device according to claim 8, characterized in that, Further included is a processor, which is configured to load and execute instructions of the test method of the image test device.

Images