A method and system for testing the aiming accuracy of optoelectronic devices
By performing threshold segmentation and connected component analysis on multiple frames of images acquired by optoelectronic devices, calculating the jitter difference between frames, and evaluating the aiming accuracy of optoelectronic devices, the problem of dynamic interference in complex environments is solved, and more accurate aiming accuracy testing is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AUBO (BEIJING) ROBOTICS TECH CO LTD
- Filing Date
- 2026-04-21
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies fail to effectively consider the impact of dynamic interference on inter-frame jitter in complex environments during the aiming accuracy test of optoelectronic equipment, resulting in insufficient test accuracy.
By acquiring multiple frames of images, threshold segmentation and connected component analysis are performed to obtain local regions. The inter-frame jitter difference is calculated by using pixel grayscale change features and centroid coordinate deviation. Combined with dynamic interference difference values, a fused image is obtained to evaluate aiming accuracy.
It improves the accuracy of aiming precision testing for optoelectronic equipment, effectively suppresses inter-frame jitter interference, and enhances the reliability of testing.
Smart Images
Figure CN122089715B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of optoelectronic aiming testing technology, specifically to a method and system for testing the aiming accuracy of optoelectronic devices. Background Technology
[0002] During optoelectronic aiming operations, the aiming accuracy of optoelectronic equipment directly determines the target recognition capability, effective range, tracking stability, and laser processing accuracy of the optoelectronic aiming system. Therefore, the aiming accuracy of optoelectronic equipment must be tested during the production, assembly, and factory inspection stages to effectively detect the working performance of the optoelectronic aiming system, avoid insufficient aiming accuracy caused by manufacturing defects, and improve the reliability and stability of the optoelectronic aiming system in complex environments.
[0003] Existing technologies typically employ static testing methods to assess aiming accuracy. However, the actual application environment of optoelectronic devices is quite complex. Static testing methods neglect the impact of inter-frame jitter caused by dynamic interference in complex environments on the assessment of optoelectronic device aiming accuracy, resulting in insufficient accuracy in testing the aiming accuracy of optoelectronic devices. Summary of the Invention
[0004] In view of the above, it is necessary to provide a method and system for testing the aiming accuracy of optoelectronic devices, which improves the accuracy of optoelectronic device aiming accuracy testing compared to traditional methods.
[0005] In a first aspect, embodiments of this application provide a method for testing the aiming accuracy of an optoelectronic device, the method comprising the following steps:
[0006] Collect multiple frames of various images during the aiming accuracy test of the optoelectronic equipment, and collect the original data of the aiming line and the position data of the reference target.
[0007] For a single image, threshold segmentation and connected component analysis are performed on each frame to obtain local regions in each frame. By analyzing the temporal variation characteristics of pixel grayscale, matching local regions in other frames are obtained for each local region in each frame. By comparing the pixel grayscale distribution and number of pixels in each local region with its matching local regions, the inter-frame jitter difference of each local region in each frame is obtained. Combined with the degree of deviation of the centroid coordinates between each local region and its matching local regions, the dynamic interference difference value of each local region in each frame is obtained. Based on the dynamic interference difference value, the weight of each frame is obtained when fusing the single image, thus obtaining the fused image of the single image.
[0008] By using the fused image, along with the original aiming line data and the reference target position data, various errors in the aiming accuracy test process of the optoelectronic device are obtained, including: laser pointing error, visual positioning error, and optical axis parallelism error, thereby evaluating the pass / fail status of the aiming accuracy of the optoelectronic device.
[0009] In one embodiment, the process of obtaining the inter-frame jitter difference is as follows:
[0010] Perform probability statistics on the grayscale values of pixels in each local region;
[0011] Measure the dissimilarity of each local region in each frame of an image between its probability statistics and its matching local regions;
[0012] Measure the difference in the number of pixels between each local region and its matching local regions in each frame of an image;
[0013] The inter-frame jitter difference is obtained by combining the dissimilarity measurement result and the difference measurement result.
[0014] In one embodiment, the calculation process for the inter-frame jitter difference is as follows:
[0015] Calculate the product of the dissimilarity measure and the difference measure;
[0016] The inter-frame jitter difference is obtained by the product of each local region in each frame and all its matching local regions, and the inter-frame jitter difference is positively correlated with the product.
[0017] In one embodiment, the process of obtaining the dynamic interference difference value is as follows:
[0018] Calculate the mean coordinates of the centroids of each local region and all its matching local regions in each frame of the image;
[0019] The distance from the centroid coordinates of each local region in each frame of the image to the mean of the coordinates is calculated, and the maximum value among the distances from the centroid coordinates of all matching local regions in each frame of the image to the mean of the coordinates is calculated.
[0020] The inter-frame jitter deviation of each local region in each frame image is obtained by using the distance from the centroid coordinates of each local region to the mean of the coordinates, and the maximum value of the coordinates.
[0021] The dynamic interference difference value is positively correlated with the inter-frame jitter difference degree and the inter-frame jitter deviation degree, respectively.
[0022] In one embodiment, the inter-frame jitter deviation is the ratio of the distance from the centroid coordinates of each local region in each frame to the mean of the coordinates to the maximum value.
[0023] In one embodiment, the method for obtaining the weights is as follows:
[0024] Calculate the average value of the dynamic interference difference values of all local regions in each frame of the image; calculate the difference between 1 and the normalized value of the average value;
[0025] The weights are positively correlated with the differences.
[0026] In one embodiment, the weight is the percentage of the difference of each frame image in the total difference of all frames of the same image category.
[0027] In one embodiment, the process of evaluating the aiming accuracy of the optoelectronic device is as follows:
[0028] Calculate the difference between 1 and the normalized values of various errors, and combine the differences of all kinds of errors to obtain the comprehensive score result in the aiming accuracy test of the optoelectronic equipment.
[0029] The aiming accuracy of the optoelectronic device is evaluated by comparing the comprehensive score with a preset pass threshold.
[0030] In one embodiment, the overall score is a weighted sum of the differences in all types of errors.
[0031] Secondly, embodiments of this application also provide a photoelectric device aiming accuracy testing system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described photoelectric device aiming accuracy testing methods.
[0032] This application has at least the following beneficial effects:
[0033] This application divides the entire image into multiple local regions to achieve refined analysis of image content, providing basic units for subsequent inter-frame matching and jitter analysis. By quantifying the impact of dynamic interference in complex environments from two aspects—pixel grayscale distribution and region size—it accurately reflects the degree of influence of inter-frame jitter on pixel distribution within local regions. Furthermore, it introduces spatial position offset to comprehensively characterize the degree of influence of dynamic interference on a single frame image, providing a precise basis for subsequent calculation of image fusion weights.
[0034] Furthermore, by adaptively determining the inter-frame fusion weights based on the degree of dynamic interference, images less affected by inter-frame jitter are assigned higher weights, and vice versa. This effectively suppresses inter-frame jitter interference, improves image quality, and provides a more reliable basis for subsequent aiming accuracy evaluation. In this way, the impact of dynamic interference on the aiming accuracy evaluation of optoelectronic equipment is reduced, and the accuracy of optoelectronic equipment aiming accuracy testing is improved. Attached Figure Description
[0035] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0036] Figure 1 A flowchart illustrating the steps of a method for testing the aiming accuracy of an optoelectronic device, as provided in one embodiment of this application;
[0037] Figure 2 This is a schematic diagram illustrating the process of obtaining dynamic interference difference values;
[0038] Figure 3 This is a schematic diagram of the process for acquiring fused images. Detailed Implementation
[0039] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.
[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It should be understood that, unless otherwise stated, " / " in this application means "or".
[0041] It should also be noted that the terms "first" and "second" in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.
[0042] The following description, in conjunction with the accompanying drawings, details the specific scheme of the optoelectronic device aiming accuracy testing method and system provided in this application.
[0043] Please see Figure 1The diagram illustrates a flowchart of a method for testing the aiming accuracy of an optoelectronic device according to an embodiment of this application. The method includes the following steps:
[0044] Step 1: Collect multiple frames of images during the aiming accuracy test of the optoelectronic equipment, and collect the original data of the aiming line and the position data of the reference target.
[0045] To accurately evaluate the aiming accuracy of optoelectronic equipment, during the aiming accuracy test of the optoelectronic equipment, the test output images and data are collected simultaneously, including: images, raw data of the aiming line, and data of the reference target position.
[0046] In this embodiment, images are acquired via an image acquisition card. Specifically, these images include: target image output by the optoelectronic device, laser spot image, and real-time sensor imaging image. These images are used to extract the target center coordinates, spot centroid position, and actual target center position information, respectively. The real-time sensor imaging image includes visible light imaging and infrared imaging. Raw aiming line data is acquired via the optoelectronic device's data communication interface. This raw aiming line data specifically includes: aiming pointing angle, theoretical aiming coordinates, optical axis control quantity, and laser emission command data calculated and output by the optoelectronic device. This data characterizes the theoretical target position that the optoelectronic aiming system expects to point to, serving as a control benchmark for accuracy evaluation. Reference target position data is acquired via a collimator calibration unit. This reference target position data consists of the theoretical center coordinates, spatial position parameters, and infinite distance target reference pointing information of a high-precision standard target, providing a stable and unified test benchmark.
[0047] It should be added that when the photoelectric device is aimed at the target position, it begins to acquire images. All images are acquired in 100 consecutive frames. The 100 frames are only one embodiment of this application. The implementer can set the specific value according to the actual situation. This application does not impose any special restrictions.
[0048] Step 2: For a single image, obtain each local region in each frame; obtain the matching local regions of each local region in each frame in the other frames; obtain the inter-frame jitter difference and dynamic interference difference value of each local region in each frame; and obtain the fused image of the single image.
[0049] In the aiming accuracy test of optoelectronic equipment, in order to accurately reflect the accuracy of optoelectronic equipment in actual application, a combination of static and dynamic testing is used. This allows for accurate testing of the aiming accuracy of optoelectronic equipment in complex environments, avoiding situations where the actual aiming accuracy of optoelectronic equipment differs significantly from the expected aiming accuracy in actual application, thus affecting the application effect of the optoelectronic equipment.
[0050] Step 2.1: For a single type of image, perform threshold segmentation and connected component analysis on each frame of the image to obtain each local region in each frame of the image; and obtain the matching local regions of each local region in each frame of the image in the other frames of the image by using the temporal variation characteristics of pixel grayscale.
[0051] Considering the interference from stray light and background noise during the aiming accuracy test of optoelectronic equipment, various images are filtered using a filtering algorithm to reduce the impact of complex environmental interference on the aiming accuracy evaluation of optoelectronic equipment. Furthermore, to improve the accuracy of image analysis, image enhancement processing is performed on the filtered images to highlight the contrast between different regions in the image.
[0052] In this embodiment, a median filtering algorithm is used to filter the image, and an adaptive histogram equalization method is used to enhance the filtered image. Both the median filtering algorithm and the adaptive histogram equalization method are well-known technologies and will not be described in detail here. As other implementation methods, based on the ability to filter the image, the implementer may choose other existing feasible technologies, and this application does not impose any special restrictions. Similarly, based on the ability to enhance the image, the implementer may choose other existing feasible technologies, and this application does not impose any special restrictions.
[0053] Furthermore, in order to accurately evaluate the aiming accuracy of optoelectronic devices in real complex environments and avoid accuracy deviations caused by differences between the test environment and actual application scenarios, this application conducts dynamic testing on optoelectronic devices by simulating complex environments to solve the problem that traditional static testing methods cannot reflect actual dynamic interference.
[0054] Step 2.2: By comparing the pixel grayscale distribution and pixel count of each local region in each frame image with its matching local regions, the inter-frame jitter difference of each local region in each frame image is obtained. Combined with the degree of deviation of the centroid coordinates between each local region in each frame image and its matching local regions, the dynamic interference difference value of each local region in each frame image is obtained.
[0055] In the aiming accuracy test of optoelectronic equipment, complex environmental interference not only causes the laser beam path to deviate, resulting in a shift in the laser's landing point, but also severely affects the image acquisition quality. Specifically, there is a dynamic interference feature called inter-frame jitter during image acquisition, which reduces the accuracy of aiming accuracy assessment based on images. Therefore, it is necessary to analyze the inter-frame dynamic interference features of the actual acquired images and then suppress the image jitter interference features to improve the quality of images used for aiming accuracy assessment.
[0056] Based on the above analysis, taking the j-th type of image as an example, threshold segmentation and connected component analysis are performed on each frame of the image to obtain each local region in each frame of the image.
[0057] In this embodiment, the Otsu threshold segmentation algorithm is used to perform threshold segmentation on the pixels in each frame of the image, and connected component analysis is performed on the threshold-segmented pixels. Each obtained connected component is taken as a local region. The Otsu threshold segmentation algorithm and connected component analysis are well-known technologies, and will not be described in detail in this application. As other implementation methods, based on the ability to perform threshold segmentation on the pixels in each frame of the image, the implementer may use other existing feasible technologies, such as global threshold segmentation, iterative threshold segmentation, etc. This application does not impose any special restrictions.
[0058] Furthermore, by leveraging the temporal variation characteristics of pixel grayscale, matching local regions in each frame of the image are obtained for each local region in the remaining frames. The specific process is as follows:
[0059] By using a method combining corner detection and optical flow, local regions of all frames are matched to obtain the matching local regions of each local region in each frame in the other frames. This is used to analyze the jitter differences of local regions between frames during continuous acquisition.
[0060] In this embodiment, the Shi-Tomasi corner detection method combined with the LK (Lucas Kanade) optical flow method is used to match local regions of all frame images. The Shi-Tomasi corner detection and the inter-frame matching process based on the corner detection results using the LK optical flow method are both well-known technologies and will not be described in detail here. As other implementation methods, based on the ability to match local regions by analyzing the grayscale changes of pixels in consecutive image frames, implementers may use other existing feasible technologies, and this application does not impose any special restrictions.
[0061] Furthermore, due to dynamic interference in complex environments, inter-frame jitter occurs during image acquisition, leading to differences in the grayscale distribution of pixels in the same local region across different frames. The greater the impact of dynamic interference, the greater the difference in grayscale distribution of pixels in the same local region across different frames. Moreover, inter-frame jitter causes changes in the size of the same local region across different frames. Therefore, by comparing the grayscale distribution and number of pixels of each local region with its matching local regions in each frame, the inter-frame jitter difference of each local region in each frame is obtained. The specific process is as follows:
[0062] Perform probability statistics on the grayscale values of pixels in each local region; measure the dissimilarity of the probability statistics results between each local region and its matching local regions in each frame of the image;
[0063] Measure the difference in the number of pixels between each local region and its matching local regions in each frame of an image;
[0064] Calculate the product of the dissimilarity measure and the difference measure;
[0065] The inter-frame jitter difference is obtained by the product of each local region in each frame and all its matching local regions, and the inter-frame jitter difference is positively correlated with the product.
[0066] It should be noted that positive correlation means that the variables change in the same direction; when one variable increases, the other variable also increases, and when one variable decreases, the other variable also decreases.
[0067] In this embodiment, the dissimilarity between probability statistics results is measured by the normalized value of KL divergence. KL divergence is a well-known technique and will not be elaborated upon here. As other implementation methods, implementers can use other existing feasible techniques to measure the dissimilarity between probability statistics results, and this application does not impose any special restrictions. Specifically, the normalized value of KL divergence is obtained using the Min-Max normalization method, which is a well-known technique and will not be elaborated upon here. It should be noted that when performing probability statistics on the grayscale values of pixels in each local region, a Laplace smoothing strategy is used to assign a very small initial value to terms with a grayscale probability of 0 to prevent undefined or NaN (Not a Number) errors in logarithmic operations when using KL divergence later. In this embodiment, the value of the very small initial value is... The value of the minimum initial value is preset by humans, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.
[0068] In this embodiment, the process of measuring the difference between the number of pixels is as follows: calculate the absolute value of the difference between the number of pixels in each local region and its matching local region in each frame of the image, and use the ratio of the absolute value of the difference to the number of pixels in each local region in each frame of the image as the measurement result of the difference between the number of pixels. As another implementation method, based on the ability to measure the difference between the number of pixels, the implementer may adopt other existing feasible technologies, such as ratios, etc. This application does not impose any special restrictions.
[0069] In this embodiment, the expression for the inter-frame jitter difference in each local region of each frame image is:
[0070] In the formula, This represents the inter-frame jitter difference of the x-th local region in a single frame image; n represents the number of matching local regions in the x-th local region of a single frame image. This represents the product between the x-th local region and its y-th matching local region in a single frame image.
[0071] It should be noted that: the greater the dissimilarity measurement result, the greater the difference in pixel grayscale distribution of the same local region in different frame images, the greater the impact of inter-frame jitter on the judgment and analysis of the same local region, and the more likely it is to interfere with the accuracy of target center extraction; the greater the calculated inter-frame jitter difference, the greater the difference of the same local region in different frame images, and the more likely it is to interfere with the accuracy of target center extraction.
[0072] Furthermore, under the influence of dynamic interference, inter-frame jitter may cause the position of the same local region to deviate in different frame images. Therefore, the inter-frame jitter deviation of each local region in each frame image is obtained by measuring the degree of deviation of the centroid coordinates between each local region and its matching local regions. The specific process is as follows:
[0073] Calculate the mean coordinates of the centroids of each local region and all its matching local regions in each frame of the image;
[0074] The distance from the centroid coordinates of each local region in each frame of the image to the mean of the coordinates is calculated, and the maximum value among the distances from the centroid coordinates of all matching local regions in each frame of the image to the mean of the coordinates is calculated.
[0075] The ratio of the distance from the centroid coordinates of each local region in each frame to the mean of the coordinates to the maximum value is used as the inter-frame jitter deviation of each local region in each frame.
[0076] In this embodiment, the centroid coordinates of each local region are obtained by the gray-scale centroid method. The gray-scale centroid method is a well-known technique and will not be described in detail in this application.
[0077] It should be noted that the larger the calculated inter-frame jitter deviation, the greater the deviation in the position of the same local region in different frame images. This means that the possibility of inter-frame jitter under the influence of dynamic interference is greater, and the more likely it is to interfere with the accuracy of target center extraction.
[0078] Furthermore, by combining the inter-frame jitter difference and inter-frame jitter deviation of each local region in each frame, the dynamic interference difference value of each local region in each frame is obtained, specifically:
[0079] The dynamic interference difference value of each local region in each frame is positively correlated with the inter-frame jitter difference and inter-frame jitter deviation of each local region in each frame. A schematic diagram of the process for obtaining the dynamic interference difference value is shown below. Figure 2 As shown.
[0080] In this embodiment, the expression for the dynamic interference difference value of each local region in each frame image is:
[0081] In the formula, This represents the dynamic interference difference value of the x-th local region in a single frame image; This represents the inter-frame jitter difference in the x-th local region of a single frame image; This represents the inter-frame jitter deviation of the x-th local region in a single frame image; , Both represent preset weights greater than 0, used to reflect the reference degree of inter-frame jitter difference and inter-frame jitter deviation on the calculation and analysis of dynamic interference difference value under the influence of dynamic interference, and satisfying the following conditions: .
[0082] In this embodiment, , The values are all 0.5, indicating that under the influence of dynamic interference, the inter-frame jitter difference and inter-frame jitter deviation have the same reference value for the calculation and analysis of dynamic interference difference. Implementers can adjust the values according to the actual situation. , The value can be adjusted; for example, if a local region from the same source exhibits significant positional changes in different frames, the value can be increased. The value of is selected to highlight the impact of location differences on the dynamic interference difference analysis.
[0083] Step 2.3: Obtain the weight of each frame of the image when fusing individual images using the dynamic interference difference value, and then obtain the fused image of the individual images.
[0084] Furthermore, since aiming accuracy testing in complex environments may be affected by inter-frame jitter due to dynamic interference, which could impact subsequent aiming accuracy evaluation, an inter-frame fusion technique is employed to reduce the impact of inter-frame jitter interference on the accuracy of aiming accuracy evaluation during optoelectronic equipment aiming testing. This technique uses a weighted average method to superimpose pixel information from all frames of the j-th image to offset the effect of single-frame jitter.
[0085] Based on the above analysis, the weight of each frame of the j-th image is obtained by using the dynamic interference difference value of each local region in each frame of the j-th image. The expression is as follows:
[0086] In the formula, This represents the weight of the v-th frame when fusing individual images; , represents the normalized average of the dynamic interference difference values of all local regions in the v-th and i-th frames when fusing a single type of image, respectively; m represents the total number of all frames of a single type of image.
[0087] In this embodiment, the Min-Max normalization method is used to obtain the normalized value of the average value of dynamic interference difference.
[0088] It should be noted that if a single frame image is more affected by inter-frame jitter, then the weight of the single frame image needs to be reduced when performing inter-frame fusion.
[0089] Furthermore, by using the weights of each frame when fusing the j-th image, the fused image of the j-th image is obtained, specifically as follows:
[0090] By weighting each frame of the j-th image during fusion, the grayscale values of pixels at the same position in all frames of the j-th image are weighted and fused to obtain the grayscale values of each pixel in the fused image of the j-th image. This cancels out the effect of single-frame jitter and obtains a single fused image for testing the aiming accuracy of optoelectronic equipment. A schematic diagram of the fused image acquisition process is shown below. Figure 3 As shown.
[0091] Following the method for obtaining the fused image of the j-th image, obtain the fused images of the other various images.
[0092] Step 3: Using the fused image, the original aiming line data, and the reference target position data, obtain various errors in the aiming accuracy test process of the optoelectronic device, including: laser pointing error, visual positioning error, and optical axis parallelism error, and then evaluate the pass / fail status of the aiming accuracy of the optoelectronic device.
[0093] The system uses fused images of various images, along with raw aiming line data and reference target position data, as input. Halcon software is used to output various errors in the aiming accuracy test process of the optoelectronic equipment, including: laser pointing error, visual positioning error, and optical axis parallelism error. Among them, laser pointing error reflects the pointing accuracy of the laser emission path and the actual aiming deviation; visual positioning error reflects the positioning accuracy of the optoelectronic equipment's imaging system on the target; and optical axis parallelism error reflects the coaxiality and parallelism between multiple optical paths.
[0094] Furthermore, by integrating all types of errors, the comprehensive score result of the aiming accuracy test of the optoelectronic equipment is obtained, expressed as:
[0095] In the formula, S represents the comprehensive score result in the aiming accuracy test of the optoelectronic equipment; M represents the total number of error types. This represents the normalized value of the r-th type of error; This represents the weight of the r-th type of error.
[0096] In this embodiment, the Min-Max normalization method is used to obtain the normalized value of the error.
[0097] In this embodiment, weights are assigned based on the priority of the impact of various errors on aiming accuracy. Specifically: laser pointing error directly determines whether the optoelectronic device can accurately hit or indicate the target, reflecting its core operational efficiency; visual positioning error determines the optoelectronic device's ability to accurately detect and lock onto the target, which is a prerequisite for the optoelectronic aiming system to perceive the target; optical axis parallelism error is a fundamental indicator for ensuring the physical alignment of multiple optical paths; therefore, the weight of laser pointing error is set to 0.5, the weight of visual positioning error is set to 0.3, and the weight of optical axis parallelism error is set to 0.2. Implementers can set the specific values of the weights of various errors according to the actual situation, and this application does not impose any special restrictions.
[0098] It should be noted that the comprehensive score result is used to reflect the overall aiming performance level of the optoelectronic equipment in multiple dimensions; the higher the calculated comprehensive score result, the higher the aiming accuracy of the optoelectronic equipment.
[0099] Furthermore, by comparing the comprehensive score results during the aiming accuracy test of the optoelectronic equipment with the preset pass threshold, the passability of the aiming accuracy of the optoelectronic equipment is evaluated, specifically as follows:
[0100] If the overall score during the aiming accuracy test of the optoelectronic device is greater than or equal to the preset pass threshold, the aiming accuracy of the optoelectronic device is deemed to be qualified. If the overall score during the aiming accuracy test of the optoelectronic device is less than the preset pass threshold, the aiming accuracy of the optoelectronic device is deemed to be unqualified, and a comprehensive investigation of core modules such as optical components, mechanical structure, and control algorithm is required.
[0101] In this embodiment, the process of obtaining the preset qualified threshold is as follows: 30 qualified optoelectronic devices of the same model as the optical device to be tested for aiming accuracy are extracted, aiming accuracy tests are performed on the 30 qualified optoelectronic devices respectively, the comprehensive score result of the aiming accuracy test process of each optoelectronic device is obtained, and the average of the comprehensive score results of the aiming accuracy test process of the 30 qualified optoelectronic devices is used as the preset qualified threshold. Here, 30 is only one embodiment of this application, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.
[0102] Based on the same inventive concept as the above method, this application embodiment also provides an optoelectronic device aiming accuracy testing system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described optoelectronic device aiming accuracy testing methods.
[0103] In summary, this application divides the entire image into multiple local regions, enabling refined analysis of image content and providing processable basic units for subsequent inter-frame matching and jitter analysis. By quantifying the impact of dynamic interference in complex environments from two aspects—pixel grayscale distribution and region size—it accurately reflects the degree of influence of inter-frame jitter on pixel distribution within local regions. Furthermore, it introduces spatial position offset to comprehensively characterize the degree of influence of dynamic interference on a single frame image, providing an accurate basis for subsequent calculation of image fusion weights.
[0104] Furthermore, by adaptively determining the inter-frame fusion weights based on the degree of dynamic interference, images less affected by inter-frame jitter are assigned higher weights, and vice versa. This effectively suppresses inter-frame jitter interference, improves image quality, and provides a more reliable basis for subsequent aiming accuracy evaluation. In this way, the impact of dynamic interference on the aiming accuracy evaluation of optoelectronic equipment is reduced, and the accuracy of optoelectronic equipment aiming accuracy testing is improved.
[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0106] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects.
Claims
1. A method for testing the aiming accuracy of optoelectronic devices, characterized in that, The method includes the following steps: Collect multiple frames of various images during the aiming accuracy test of the optoelectronic equipment, and collect the original data of the aiming line and the position data of the reference target. For a single image, threshold segmentation and connected component analysis are performed on each frame to obtain local regions in each frame. By analyzing the temporal variation characteristics of pixel grayscale, matching local regions in other frames are obtained for each local region in each frame. By comparing the pixel grayscale distribution and number of pixels in each local region with its matching local regions, the inter-frame jitter difference of each local region in each frame is obtained. Combined with the degree of deviation of the centroid coordinates between each local region and its matching local regions, the dynamic interference difference value of each local region in each frame is obtained. Based on the dynamic interference difference value, the weight of each frame is obtained when fusing the single image, thus obtaining the fused image of the single image. By using the fused image, along with the original aiming line data and the reference target position data, various errors in the aiming accuracy test process of the optoelectronic device are obtained, including: laser pointing error, visual positioning error, and optical axis parallelism error, thereby evaluating the pass / fail status of the aiming accuracy of the optoelectronic device.
2. The method for testing the aiming accuracy of an optoelectronic device as described in claim 1, characterized in that, The process of obtaining the inter-frame jitter difference is as follows: Perform probability statistics on the grayscale values of pixels in each local region; Measure the dissimilarity of each local region in each frame of an image between its probability statistics and its matching local regions; Measure the difference in the number of pixels between each local region and its matching local regions in each frame of an image; The inter-frame jitter difference is obtained by combining the dissimilarity measurement result and the difference measurement result.
3. The method for testing the aiming accuracy of an optoelectronic device as described in claim 2, characterized in that, The calculation process for the inter-frame jitter difference is as follows: Calculate the product of the dissimilarity measure and the difference measure; The inter-frame jitter difference is obtained by the product of each local region in each frame and all its matching local regions, and the inter-frame jitter difference is positively correlated with the product.
4. The method for testing the aiming accuracy of an optoelectronic device as described in claim 1, characterized in that, The process for obtaining the dynamic interference difference value is as follows: Calculate the mean coordinates of the centroids of each local region and all its matching local regions in each frame of the image; The distance from the centroid coordinates of each local region in each frame of the image to the mean of the coordinates is calculated, and the maximum value among the distances from the centroid coordinates of all matching local regions in each frame of the image to the mean of the coordinates is calculated. The inter-frame jitter deviation of each local region in each frame image is obtained by using the distance from the centroid coordinates of each local region to the mean of the coordinates, and the maximum value of the coordinates. The dynamic interference difference value is positively correlated with the inter-frame jitter difference degree and the inter-frame jitter deviation degree, respectively.
5. The method for testing the aiming accuracy of an optoelectronic device as described in claim 4, characterized in that, The inter-frame jitter deviation is the ratio of the distance from the centroid coordinates of each local region in each frame to the mean of the coordinates to the maximum value.
6. The method for testing the aiming accuracy of an optoelectronic device as described in claim 1, characterized in that, The method for obtaining the weights is as follows: Calculate the average value of the dynamic interference difference values of all local regions in each frame of the image; calculate the difference between 1 and the normalized value of the average value; The weights are positively correlated with the differences.
7. The method for testing the aiming accuracy of an optoelectronic device as described in claim 6, characterized in that, The weight is the percentage of the difference in each frame of an image relative to the differences in all frames of the same image category.
8. The method for testing the aiming accuracy of an optoelectronic device as described in claim 1, characterized in that, The process for evaluating the aiming accuracy of the optoelectronic equipment is as follows: Calculate the difference between 1 and the normalized values of various errors, and combine the differences of all kinds of errors to obtain the comprehensive score result in the aiming accuracy test of the optoelectronic equipment. The aiming accuracy of the optoelectronic device is evaluated by comparing the comprehensive score with a preset pass threshold.
9. The method for testing the aiming accuracy of an optoelectronic device as described in claim 8, characterized in that, The overall score is a weighted sum of the differences in all types of errors.
10. A photoelectric device aiming accuracy testing system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the optoelectronic device aiming accuracy testing method as described in any one of claims 1-9.