Panoramic looking-around system usability evaluation method and device, terminal and medium

Abstract

The invention provides a method and a device for evaluating usability of a panoramic looking-around system, a terminal and a medium. The method comprises the following steps: acquiring a plurality of test tasks of the panoramic looking-around system and test evaluation indexes for evaluating the plurality of test tasks; according to the test task, test environment parameters are set for a whole vehicle optical test platform, subjective scoring data and objective test data are obtained, and objective scoring data are obtained according to the objective test data; analyzing correlation intensity between a subjective evaluation index and an objective evaluation index based on the subjective scoring data and the objective scoring data to obtain objective forward close degree data and net correlation intensity data; and obtaining system usability according to the subjective score, the objective score, the objective forward close degree data and the net correlation intensity data. The fusion degree of technical parameters and user perception is improved, the evaluation dimension of the panoramic looking-around system is improved, and the evaluation effect of the panoramic looking-around system is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to a method, device, terminal, and medium for evaluating the usability of a panoramic surround view system. Background Technology

[0002] With the rapid development of intelligent connected vehicle technology, panoramic surround view systems have become an indispensable core auxiliary system in smart cockpits. By fusing images from multiple cameras (front, rear, left, right, and overhead) to generate a 360° blind-spot-free panoramic view, these systems effectively address safety hazards caused by blind spots in scenarios such as static parking and low-speed maneuvering. The ease of use of these systems directly determines the driver's acceptance and actual safety value. Therefore, establishing a scientific and comprehensive method for evaluating the ease of use of panoramic surround view systems is of great significance for optimizing human-machine interaction and improving driving safety.

[0003] Research on panoramic surround view systems has been conducted to improve their image generation and target detection capabilities, and to verify system performance through quantitative evaluation methods. This research primarily focuses on: providing methods for building or optimizing the basic functions and image fusion of panoramic surround view systems; using virtual camera devices to score and evaluate the systems, such as by detecting objective parameters like screen resolution to assess the hardware and algorithm performance; and evaluating the user experience through subjective user ratings or simple interactive tests. These evaluation results are often used to determine whether the system meets basic usage requirements.

[0004] However, there is limited research on evaluation methods for panoramic surround view systems. Existing evaluation techniques and methods suffer from two major drawbacks: on the one hand, these methods focus solely on objective technical indicators, yielding quantitative results that demonstrate the panoramic surround view system meets basic requirements, but without providing a rating or score for the system, and the quantitative technical indicators are relatively simplistic; on the other hand, they rely solely on subjective evaluation, lacking an organic combination and correlation analysis of subjective and objective indicators, making it difficult to comprehensively and reliably assess the usability of the panoramic surround view system in actual operating scenarios, and failing to provide precise guidance for in-depth system optimization. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention proposes a method, device, terminal, and medium for evaluating the usability of panoramic surround view systems. The aim is to improve the integration of technical parameters and user perception, enhance the evaluation dimensions of panoramic surround view systems, and improve the evaluation effect of panoramic surround view systems.

[0006] In a first aspect, embodiments of this application provide a method for evaluating the usability of a panoramic surround view system, including: The system acquires multiple test tasks for a panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks, the test evaluation indicators including subjective evaluation indicators and objective evaluation indicators. According to the test task, the test environment parameters are set for the whole vehicle optical test platform, subjective scoring data and objective test data are obtained, and objective scoring data is obtained based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation index, and the objective scoring data is the scoring data for evaluating the objective evaluation index. Based on the subjective rating data and the objective rating data, the correlation strength between the subjective evaluation indicators and the objective evaluation indicators is analyzed to obtain objective positive closeness data and net correlation strength data; The system usability is obtained based on the subjective rating, the objective rating, the objective positive closeness data, and the net correlation strength data.

[0007] Optionally, obtaining the system usability based on the subjective rating, the objective rating, the objective positive proximity data, and the net correlation strength data includes: Based on the net correlation strength data, objective evaluation indicators that are strongly correlated with subjective evaluation indicators are selected as core objective indicators. The core objective indicators are normalized by standard deviation based on objective scoring data and net correlation strength data to obtain the objective indicator weights. The subjective evaluation indicators are processed using the geometric mean method based on the subjective rating data and the net correlation strength data to obtain the weights of the subjective indicators. The comprehensive weight is obtained based on the objective indicator weights, the subjective indicator weights, and the net correlation strength data. The system usability is obtained based on the subjective score, the objective score, the comprehensive weight, the objective positive closeness data, and the net correlation strength data.

[0008] Optionally, obtaining the system usability based on the subjective rating, the objective rating, the comprehensive evaluation weight, the objective positive proximity data, and the net correlation strength data includes: Where U represents the usability rating of the panoramic surround view system; For the first The overall weight of each indicator; For the first The objective positive closeness of the indicators; The coupling coefficient between subjective and objective factors; For the first The net correlation strength of the indicator; For non-linear factors to ensure the target is met; For the first The measured values ​​of the scores for each indicator; For the first The score for this indicator is the optimal value; For the first The worst score for each indicator.

[0009] Optionally, the objective test data includes objective test time data and objective test image quality data; the test environment parameters include the hardware and software technical parameters required for the test task, the setup of the optical test environment, and the ground test environment; the step of setting the test environment parameters for the whole vehicle optical test platform according to the test task, obtaining subjective scoring data and objective test data, and obtaining objective scoring data based on the objective test data includes: According to the test task, set the required hardware and software technical parameters, optical test environment and ground test environment for the whole vehicle optical test platform. Objective test time data and objective test image quality data are obtained through the vehicle optical platform. Based on the objective test time data and the objective test image quality data, objective scoring data is obtained; Obtain subjective rating data provided by drivers.

[0010] Optionally, based on the subjective rating data and the objective rating data, the correlation strength between the subjective evaluation indicators and the objective evaluation indicators is analyzed to obtain objective positive closeness data and net correlation strength data, including: Based on the objective scoring data, objective positive closeness data is obtained; The subjective and objective evaluation indicators that are correlated are grouped to obtain the subjective and objective indicator correlation groups; Based on the objective positive closeness data, the subjective rating data, and the objective rating data, the Pearson correlation coefficient is used to calculate the correlation strength between the indicators in each group of the subjective and objective indicator association groups, and the correlation strength data is obtained. Based on the aforementioned correlation strength data, net correlation strength data is obtained.

[0011] Optionally, based on the objective positive closeness data, the subjective rating data, and the objective rating data, the Pearson correlation coefficient is used to calculate the correlation strength between the indicators in each group of the subjective and objective indicator association groups, obtaining correlation strength data, including: in, The correlation strength of each group of subjective and objective indicators; For the first The subjective evaluation score for this test; For the first The objective metrics of this test show a positive closeness. This represents the mean of the subjective ratings. The mean of subjective ratings Optionally, obtaining net correlation strength data based on the correlation strength data includes: in, To control for interference index Z, the partial correlation coefficient between subjective index S and objective index O; The correlation strength between subjective indicator S and objective indicator O. The correlation strength between the subjective index S and the interference index Z. The correlation strength between objective index O and interference index Z.

[0012] Secondly, embodiments of this application provide a usability evaluation device for a panoramic surround view system, comprising: The data acquisition module is used to acquire multiple test tasks of the panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks. The test evaluation indicators include subjective evaluation indicators and objective evaluation indicators. The scoring determination module is used to set test environment parameters for the whole vehicle optical test platform according to the test task, obtain subjective scoring data and objective test data, and obtain objective scoring data based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation index, and the objective scoring data is the scoring data for evaluating the objective evaluation index. The data determination module is used to analyze the correlation strength between subjective evaluation indicators and objective evaluation indicators based on the subjective rating data and the objective rating data, and to obtain objective positive closeness data and net correlation strength data. The usability determination module is used to obtain the system usability based on the subjective rating, the objective rating, the objective positive closeness data, and the net correlation strength data.

[0013] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the panoramic surround view system usability evaluation method as described in any one of the first aspects above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the panoramic surround view system usability evaluation method as described in any one of the first aspects above.

[0015] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the panoramic surround view system usability evaluation method described in any of the first aspects.

[0016] This application obtains multiple test tasks for a panoramic surround view system and test evaluation indicators for evaluating these tasks. These indicators include subjective and objective evaluation indicators. Test environment parameters are set on a vehicle optical test platform according to the test tasks. Subjective scoring data and objective test data are obtained, and objective scoring data is derived from the objective test data. The subjective scoring data evaluates the subjective and objective evaluation indicators. The correlation strength between the subjective and objective evaluation indicators is analyzed based on the subjective and objective scoring data to obtain objective positive proximity data and net correlation strength data. The system usability is determined based on the subjective scores, objective scores, objective positive proximity data, and net correlation strength data. This improves the integration of technical parameters with user perception, enhances the evaluation dimensions of the panoramic surround view system, and improves the evaluation effect of the panoramic surround view system. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0018] Figure 1 This is a flowchart illustrating the first embodiment of the panoramic surround view system usability evaluation method provided in this application. Figure 2 This is a schematic diagram of the panoramic surround view system usability evaluation device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0021] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] Figure 1 The diagram illustrates a flowchart of a first embodiment of the panoramic surround view system usability evaluation method provided in this application. This is an example and not a limitation; the method can be applied to the aforementioned panoramic surround view system usability evaluation device. Figure 1 As shown, the method may include: S10, acquire multiple test tasks of the panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks, the test evaluation indicators including multiple subjective evaluation indicators and multiple objective evaluation indicators. To improve the integration of technical parameters and user perception, enhance the evaluation dimensions of panoramic surround view systems, and improve the evaluation effect of panoramic surround view systems, a panoramic surround view system usability evaluation device acquires multiple test tasks of the panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks. The test evaluation indicators include subjective evaluation indicators and objective evaluation indicators. The subjective evaluation indicators include at least two of the following: ease of view switching, intuitiveness of obstacle recognition, satisfaction with image clarity, satisfaction with brightness adaptation, satisfaction with natural stitching transition, sufficiency of field of view coverage, and overall operational smoothness. The objective evaluation indicators include at least two of the following: view switching efficiency, view switching response rate, obstacle recognition response speed, total stitching failure area, image clarity score, image symmetry deviation rate, field of view coverage integrity, and blind spot rate.

[0023] In other words, based on the whole vehicle optical testing platform, multiple test tasks are constructed for the panoramic surround view system, ranging from functional verification to performance testing. The test tasks include subjective and objective tests, and subjective and objective evaluation indicators characterizing the interactive usability of the in-vehicle central control screen are constructed to evaluate the usability of the panoramic surround view system.

[0024] In one embodiment, the vehicle optical testing platform includes: a lighting simulation system, an image quality analyzer, a stitching quality inspection system, a multi-source data acquisition and synchronization system, and a field of view testing system. The lighting simulation system includes a 360-degree movable solar light source, a top-radial light source matrix, and an adjustable color temperature chamber-type light source, capable of simulating real lighting scenarios with uniform illumination, polarization, and metering. The image quality analyzer includes an exposure time analysis system, an eccentricity testing system, a glare and ghosting testing system, and camera clarity testing software, used to detect the image quality displayed by the panoramic surround view system. The stitching quality inspection system includes an automatic image card switching platform, a test card kit (including checkerboard test cards, clarity test cards, gray cards, dynamic range test cards, etc.), and an automated stitching effect testing system, used to construct a quantifiable and analyzable ground testing environment and analyze stitching quality. The multi-source data acquisition and synchronization system includes touch sensors, a sound acquisition system, and a CAN bus, used for millisecond-level synchronous acquisition of touch time data and recognition response data.

[0025] In one embodiment, multiple test tasks are constructed, including at least: test tasks for viewpoint switching, obstacle recognition, and field of view recognition, and a subjective rating scale. The viewpoint switching task requires completing a cyclic switching operation of "panoramic view → rear view → left view → top view". The obstacle recognition task requires identifying obstacles around the vehicle body through a panoramic surround view. The field of view recognition task requires confirming the field of view coverage through a panoramic surround view.

[0026] The subjective evaluation indicators include at least two of the following: ease of switching perspectives, intuitiveness of obstacle recognition, satisfaction with image clarity, satisfaction with brightness adaptation, satisfaction with natural stitching transition, sufficiency of field of view coverage, and overall smoothness of operation.

[0027] The subjective evaluation indicators are shown in Table 1, among which: ease of viewpoint switching This indicates the driver's subjective feeling regarding the complexity of the operation steps and the ease of finding the switching buttons when using a panoramic surround view system to switch between different perspectives, such as panoramic → rearview → left view → overhead view. It reflects whether the perspective switching operation aligns with the driver's intuitive habits; and the intuitiveness of obstacle recognition. This refers to the driver's subjective feeling regarding the visibility of obstacles such as pedestrians, bollards, and cargo box corners in the panoramic surround view system, as well as the ease of understanding of distance markings. It reflects whether obstacle information can be perceived quickly and accurately; and the level of satisfaction with image clarity. This indicates the driver's subjective satisfaction with the panoramic surround view system's visual presentation, focusing on image clarity and brightness compatibility. This indicates the driver's subjective satisfaction with the brightness of the panoramic surround view system's screen, with a strong focus on the comfort of the screen brightness display and the naturalness of the stitching transitions. This indicates the driver's subjective satisfaction with the panoramic surround view system's image quality, focusing on whether there are ghosting, gaps, misalignment, or uneven color in the stitched areas; and the sufficiency of the field of view coverage. This indicates the driver's subjective satisfaction with the panoramic surround view system's field of view, focusing on whether the system covers frequently observed areas around the vehicle, such as pedestrian crossings on the side, and whether there are any obvious blind spots that could affect safety judgment. It reflects the adaptability of the field of view to actual usage needs; overall operational smoothness. The term "panoramic surround view system" refers to the driver's subjective experience of the smooth and seamless operation after completing the core tasks of the system (such as perspective switching, obstacle recognition, and field of view confirmation). It comprehensively reflects the synergistic effect of the system's hardware response and software interaction. Table 1 Subjective Evaluation Indicators In one embodiment, the constructed objective evaluation indicators include at least two of the following: viewpoint switching efficiency, viewpoint switching response rate, obstacle recognition response speed, total stitching failure area, image clarity score, image symmetry deviation rate, field of view coverage integrity, and field of view blind spot rate.

[0028] The formula for calculating the perspective switching efficiency is: in, This reflects the smoothness of multi-view loop switching; a lower value indicates lower efficiency. This indicates the actual total time to complete the cycle of "panoramic view → rear view → left view → overhead view". This represents the ideal completion time in a static scenario; The formula for calculating the viewpoint switching response rate is: in, This indicates the viewpoint switching response rate, reflecting the system's feedback speed to switching operations. A higher value indicates a more timely response. This represents the average time from clicking the toggle button to the screen fully refreshing. The formula for calculating the obstacle recognition response speed is as follows: in, This indicates the obstacle recognition response speed, reflecting the system's ability to display obstacles; a higher value indicates a better display effect. This represents the average time from the completion of the viewpoint switch to the driver verbally reporting the obstacle information; The formula for calculating the image sharpness score is as follows: Where Q represents an objective clarity metric score based on image analysis, with a maximum score of 10. This represents the grayscale change value of the image detected by the image sharpness analyzer. This represents the defined standard image grayscale variation value.

[0029] The formula for calculating the image symmetry deviation rate is as follows: in, This indicates the deviation rate between the inner and outer edges of the left side of the view and the inner and outer edges of the right side. The smaller the size, the better the symmetry. This indicates the distance between the inner and outer edges on the left side of the panoramic view. This indicates the distance between the inner and outer edges on the right side of the panoramic view.

[0030] The formula for calculating the total failed area of ​​the splicing is: Where S represents the total area of ​​stitching failure, reflecting the quality of the stitched panoramic image; the larger S is, the worse the stitching effect. This indicates the area of ​​misaligned splicing. Indicates the area of ​​the stitched ghosting. This indicates the area lost due to splicing.

[0031] The formula for calculating the field of view coverage integrity is as follows: Where C represents the field of view coverage integrity, reflecting the degree of agreement between the actual field of view and the theoretical design; a higher value indicates more complete coverage. The maximum distance that can be identified in the panoramic surround view (front / back / left / right). This indicates the maximum field of view distance in each direction of the system design. Compared to the problems of single evaluation dimensions and unrelated evaluation indicators in related technologies, the embodiments of this application construct multiple subjective and objective evaluation indicators, which can comprehensively and reliably evaluate the usability of the panoramic surround view system.

[0032] S20, according to the test task, set the test environment parameters for the whole vehicle optical test platform, obtain subjective scoring data and objective test data, and obtain objective scoring data based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation index, and the objective scoring data is the scoring data for evaluating the objective evaluation index. After acquiring the test task and test evaluation indicators, the panoramic surround view system usability evaluation device sets the test environment parameters for the whole vehicle optical test platform according to the test task, acquires subjective scoring data and objective test data, and obtains objective scoring data based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation indicators, and the objective scoring data is the scoring data for evaluating the objective evaluation indicators.

[0033] As one implementation method, the objective test data includes objective test time data and objective test image quality data; the test environment parameters include the hardware and software technical parameters required for the test task, the setup of the optical test environment, and the ground test environment; the step of setting the test environment parameters for the whole vehicle optical test platform according to the test task, obtaining subjective scoring data and objective test data, and obtaining objective scoring data based on the objective test data includes: A1. The tester sets the required hardware and software technical parameters for the test task, and sets up the optical test environment and ground test environment for the whole vehicle optical test platform according to the test task. In other words, the testers set the required hardware and software technical parameters, optical test environment and ground test environment for the test tasks through the vehicle optical test platform; and conduct subjective scoring and objective testing of the drivers based on the set test tasks. A2, objective test time data and objective test image quality data are obtained through the vehicle optical platform; Then, through the multi-source data acquisition and synchronization system of the vehicle optical platform, objective test time data and image quality data are obtained.

[0034] In one embodiment, the time data under the above objective test includes the total time consumed by the viewpoint switching task, the single switching response time, and the reaction time of the obstacle recognition task; the image quality data includes image clarity, image symmetry, image brightness, splicing misalignment area, splicing loss area, and splicing ghosting area; the field of view data includes the actual field of view coverage in front, behind, left, and right.

[0035] A3. Based on the objective test time data and the objective test image quality data, objective scoring data is obtained.

[0036] That is, the evaluation results of objective evaluation indicators are calculated based on the time data and image quality data of objective tests; A4. Obtain the subjective rating data given by the driver, wherein the subjective rating data is the evaluation score data of the subjective evaluation index given by the driver. In this embodiment, considering factors such as gender, age, and the occupational groups applicable to different vehicle models, a predetermined number of test subjects are selected, such as a total of 10 drivers participating in the test.

[0037] After the test, the driver will fill out a subjective rating scale, which involves 7 evaluation dimensions. Each dimension has 3-4 questions with a score of 1 to 10, thus obtaining the evaluation score of the subjective evaluation index.

[0038] In this embodiment, testers set up the necessary hardware and software technical parameters and arranged the test environment using the vehicle optical testing platform. This included the light source environment (sunlight, uniform overhead lighting, color temperature, etc.), the ground test environment (chessboard test cards, clarity cards / gray cards from the automatic image card switching platform), and the recognition scenarios (adults / children / stone blocks, etc.). Simultaneously, vehicle length and width data and a panoramic surround-view visualization model were input to adjust the software test parameters of the image quality analyzer, stitching quality inspection system, and multi-source data acquisition and synchronization system. Based on the test task, a usability test of the panoramic surround-view system was conducted. Objective test time data and image quality data were acquired through the multi-source data acquisition and synchronization system, and then the evaluation results of objective evaluation indicators were calculated.

[0039] This application quantifies the functionality and visual quality of the panoramic surround view system into evaluation indicators through multiple test tasks, and reliably achieves the evaluation of the usability of the panoramic surround view system by combining subjective and objective methods.

[0040] S30, Based on the subjective rating data and the objective rating data, analyze the correlation strength between the subjective evaluation index and the objective evaluation index to obtain objective positive closeness data and net correlation strength data; After obtaining subjective and objective rating data, the panoramic surround view system usability evaluation device analyzes the correlation strength between subjective and objective evaluation indicators based on the subjective and objective rating data to obtain objective positive closeness data and net correlation strength data.

[0041] In other words, based on the evaluation scores of subjective evaluation indicators and the results of objective evaluation indicators, the positive closeness is calculated to obtain objective positive closeness data; an evaluation matrix is ​​constructed, and the larger the closeness value of an evaluation indicator, the better the performance of that indicator. Subjective and objective indicators are grouped and processed, and the correlation between subjective and objective indicators in each group is calculated based on the positive closeness data to obtain net correlation strength data.

[0042] As one implementation method, the correlation strength between subjective evaluation indicators and objective evaluation indicators is analyzed based on the subjective rating data and the objective rating data to obtain objective positive closeness data and net correlation strength data, specifically including: B1. Based on the objective scoring data, obtain the objective positive closeness data; In one embodiment of this application, objective positive closeness data is obtained based on the evaluation scores of each evaluation index, and the positive closeness of each index is calculated in the following manner: in, Indicates the first Positive closeness of the objective indicators Indicates the first The measured values ​​of the objective evaluation indicators. Indicates the first The worst value of the objective indicator evaluation index. No. The objective indicator represents the optimal value of the evaluation indicator.

[0043] B2, group the subjective and objective evaluation indicators that are related to each other to obtain the subjective and objective evaluation indicator related groups; Group the subjective and objective evaluation indicators that are related, and sort out the related subjective and objective evaluation indicators to obtain the subjective and objective indicator association groups; Table 2. Association Groups of Subjective and Objective Indicators B3. Based on the objective positive closeness data, the subjective rating data, and the objective rating data, the Pearson correlation coefficient is used to calculate the correlation strength between the indicators in each group of the subjective and objective indicator association groups to obtain the correlation strength data. As one implementation method, based on the objective positive closeness data, the subjective rating data, and the objective rating data, the Pearson correlation coefficient is used to calculate the correlation strength between the indicators in each group of the subjective and objective indicator association groups, obtaining correlation strength data, specifically including: in, The correlation strength of each group of subjective and objective indicators; For the first The subjective evaluation score for this test; For the first The objective metrics of this test show a positive closeness. This represents the mean of the subjective ratings. This represents the mean of the subjective ratings. ∈[-1,1],| |≥0.6 indicates a strong correlation, 0.3≤| | < 0.6 indicates moderate correlation, | |<0.3 indicates a weak correlation.

[0044] B4. Based on the aforementioned correlation strength data, obtain the net correlation strength data.

[0045] As one implementation method, net correlation strength data is obtained based on the correlation strength data, including: in, To control for interference index Z, the partial correlation coefficient between subjective index S and objective index O; The correlation strength between subjective indicator S and objective indicator O. The correlation strength between the subjective index S and the interference index Z. The correlation strength between objective index O and interference index Z.

[0046] That is to say, The partial correlation coefficient between subjective indicator S and objective indicator O after controlling for interference indicator Z (range [-1, 1]) is given. The larger the absolute value, the stronger the net correlation. This represents the Pearson correlation coefficient between the subjective indicator S and the objective indicator O. This represents the Pearson correlation coefficient between the subjective indicator S and the interference indicator Z. This represents the Pearson correlation coefficient between the objective indicator O and the interference indicator Z.

[0047] S40, the system usability is obtained based on the subjective score, the objective score, the objective positive closeness data, and the net correlation strength data; The panoramic surround view system usability evaluation device obtains subjective scores, objective scores, objective positive proximity data, and net correlation strength data. Based on these data, it determines the system usability.

[0048] In other words, objective indicators are selected based on correlation strength (net correlation strength), multicollinearity is handled, and weights are assigned to the objective indicators. The higher the correlation, the greater the weight. At the same time, the independent weights of subjective indicators are confirmed based on the entropy weight method, and finally, a comprehensive weight is formed by merging them. A usability evaluation model for the panoramic surround view system is constructed, and the usability is calculated.

[0049] As one implementation method, the system usability is obtained based on the subjective rating, the objective rating, the objective positive proximity data, and the net correlation strength data, including: C1, based on net correlation strength data, selects objective evaluation indicators that are strongly correlated with subjective evaluation indicators as core objective indicators; Based on the partial correlation coefficient (net correlation strength data), core objective indicators that are strongly correlated with subjective indicators are selected as core objective indicators.

[0050] C2, the standard deviation of the core objective indicators is normalized based on the objective scoring data and net correlation strength data to obtain the objective indicator weights; The selected objective indicators are positively evaluated. The standard deviation of the j-th core objective indicator is calculated, and the weight is normalized. The calculation formula is as follows: in, Let j be the standard deviation of the j-th indicator. Let j be the k-th measured value of the j-th indicator. Let be the mean of the j-th indicator.

[0051] in, Let the relevance-weighted standard deviation of the j-th indicator be . Let be the net correlation strength of the j-th indicator (that is, the partial correlation coefficient of the j-th indicator).

[0052] in, denoted by , where is the weight of the objective indicators, and p is the total number of objective indicators after filtering.

[0053] C3. The subjective evaluation indicators are processed by the geometric mean method based on the subjective rating data and the net correlation strength data to obtain the subjective indicator weights. The geometric mean of subjective indicators is calculated by introducing a partial correlation coefficient-weighted geometric mean, and then normalizing the weights. The calculation formula is as follows: in, Let be the geometric mean of the i-th subjective indicator. Rate the kth tester, where m is the number of testers.

[0054] in, Let be the relevance-weighted geometric mean of the i-th indicator. Let be the average net correlation strength of the i-th indicator (that is, the average partial correlation coefficient of the i-th indicator).

[0055] in, q represents the weight of the subjective indicators, and q represents the total number of subjective indicators after filtering.

[0056] C4. Based on the objective indicator weights, the subjective indicator weights, and the net correlation strength data, a comprehensive weight is obtained. A non-linear fusion approach is adopted to consider the complex relationships between indicators and obtain a comprehensive weight. The calculation formula is as follows: in, C5. The system usability is obtained based on the subjective score, the objective score, the comprehensive weight, the objective positive proximity data, and the net correlation strength data.

[0057] As one implementation method, the system usability is obtained based on the subjective rating, the objective rating, the comprehensive weight, the objective positive proximity data, and the net correlation strength data, which may include: Where U represents the usability rating of the panoramic surround view system; For the first The overall weight of each indicator; For the first The objective positive closeness of the indicators; The coupling coefficient between subjective and objective factors; For the first The net correlation strength of the indicator; For non-linear factors to ensure the target is met; For the first The measured values ​​of the scores for each indicator; For the first The score for this indicator is the optimal value; For the first The worst score for each indicator.

[0058] This application effectively addresses the problems of existing evaluation methods, such as the disconnect between subjective and objective indicators, limited application scenarios, and lack of practical value, by deeply integrating subjective and objective indicators and scientifically and dynamically allocating weights. This improves the credibility of the evaluation results and provides practical guidance for the optimization and selection of panoramic surround view systems.

[0059] This application achieves deep integration of subjective and objective data, solving the problems of disconnect between technical parameters and user perception, single evaluation dimensions, and poor evaluation results in related technologies.

[0060] In summary, this application obtains multiple test tasks for a panoramic surround view system and test evaluation indicators for evaluating these tasks. These indicators include subjective and objective evaluation indicators. Test environment parameters are set on a vehicle optical test platform according to the test tasks to obtain subjective scoring data and objective test data. Objective scoring data is then obtained based on the objective test data. The subjective scoring data evaluates the subjective evaluation indicators, and the objective scoring data evaluates the objective evaluation indicators. The correlation strength between the subjective and objective evaluation indicators is analyzed based on the subjective and objective scoring data to obtain objective positive proximity data and net correlation strength data. Finally, the system usability is obtained based on the subjective scores, objective scores, objective positive proximity data, and net correlation strength data. This improves the integration of technical parameters with user perception, enhances the evaluation dimensions of the panoramic surround view system, and improves the evaluation effect of the panoramic surround view system.

[0061] For those consistent with the above, please refer to Figure 2 , Figure 2 This application provides a schematic diagram of the structure of a panoramic surround view system usability evaluation device. For example... Figure 2 As shown, the device includes: The data acquisition module 201 is used to acquire multiple test tasks of the panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks, wherein the test evaluation indicators include subjective evaluation indicators and objective evaluation indicators. The scoring determination module 202 is used to set test environment parameters for the whole vehicle optical test platform according to the test task, obtain subjective scoring data and objective test data, and obtain objective scoring data based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation index, and the objective scoring data is the scoring data for evaluating the objective evaluation index. The data determination module 203 is used to analyze the correlation strength between the subjective evaluation indicators and the objective evaluation indicators based on the subjective rating data and the objective rating data, and obtain objective positive closeness data and net correlation strength data. The usability determination module 204 is used to obtain the system usability based on the subjective rating, the objective rating, the objective positive closeness data, and the net correlation strength data.

[0062] like Figure 3As shown, this application embodiment also provides a terminal device 2, which includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor. The processor 20 and the memory 21 are connected. When the processor 20 executes the computer program 22, it implements the steps in the embodiments of the HIC value prediction method or the vehicle data augmentation method.

[0063] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the panoramic surround view system usability evaluation methods described in the above method embodiments.

[0064] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the panoramic surround view system usability evaluation methods described in the above method embodiments.

[0065] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include at least: any entity or device capable of carrying computer program code to a device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable storage media cannot be electrical carrier signals or telecommunication signals.

[0066] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0067] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0068] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0069] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. A method for evaluating the usability of a panoramic surround view system, characterized in that, include: The system acquires multiple test tasks for a panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks, the test evaluation indicators including subjective evaluation indicators and objective evaluation indicators. According to the test task, the test environment parameters are set for the whole vehicle optical test platform, subjective scoring data and objective test data are obtained, and objective scoring data is obtained based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation index, and the objective scoring data is the scoring data for evaluating the objective evaluation index. Based on the subjective rating data and the objective rating data, the correlation strength between the subjective evaluation indicators and the objective evaluation indicators is analyzed to obtain objective positive closeness data and net correlation strength data; The system usability is obtained based on the subjective rating, the objective rating, the objective positive closeness data, and the net correlation strength data.

2. The method for evaluating the usability of a panoramic surround view system according to claim 1, characterized in that, The process of obtaining system usability based on the subjective rating, the objective rating, the objective positive proximity data, and the net correlation strength data includes: Based on the net correlation strength data, objective evaluation indicators that are strongly correlated with subjective evaluation indicators are selected as core objective indicators. The core objective indicators are normalized by standard deviation based on objective scoring data and net correlation strength data to obtain the objective indicator weights. The subjective evaluation indicators are processed using the geometric mean method based on the subjective rating data and the net correlation strength data to obtain the weights of the subjective indicators. The comprehensive weight is obtained based on the objective indicator weights, the subjective indicator weights, and the net correlation strength data. The system usability is obtained based on the subjective score, the objective score, the comprehensive weight, the objective positive closeness data, and the net correlation strength data.

3. The method for evaluating the usability of a panoramic surround view system according to claim 2, characterized in that, The process of obtaining system usability based on the subjective rating, the objective rating, the comprehensive evaluation weight, the objective positive proximity data, and the net correlation strength data includes: Where U represents the usability rating of the panoramic surround view system; For the first The overall weight of each indicator; For the first The objective positive closeness of the indicators; The coupling coefficient between subjective and objective factors; For the first The net correlation strength of the indicator; For non-linear factors to ensure the target is met; For the first The measured values ​​of the scores for each indicator; For the first The score for this indicator is the optimal value; For the first The worst score for each indicator.

4. The method for evaluating the usability of a panoramic surround view system according to any one of claims 1 to 3, characterized in that, The objective test data includes objective test time data and objective test image quality data; the test environment parameters include the hardware and software technical parameters required for the test task, the setup of the optical test environment, and the ground test environment; the process of setting the test environment parameters for the whole vehicle optical test platform according to the test task, obtaining subjective scoring data and objective test data, and obtaining objective scoring data based on the objective test data includes: According to the test task, set the required hardware and software technical parameters, optical test environment and ground test environment for the whole vehicle optical test platform. Objective test time data and objective test image quality data are obtained through the vehicle optical platform. Based on the objective test time data and the objective test image quality data, objective scoring data is obtained; Obtain subjective rating data provided by drivers.

5. The method for evaluating the usability of a panoramic surround view system according to any one of claims 1 to 3, characterized in that, Based on the subjective rating data and the objective rating data, the correlation strength between subjective evaluation indicators and objective evaluation indicators is analyzed to obtain objective positive closeness data and net correlation strength data, including: Based on the objective scoring data, objective positive closeness data is obtained; The subjective and objective evaluation indicators that are correlated are grouped to obtain the subjective and objective indicator correlation groups; Based on the objective positive closeness data, the subjective rating data, and the objective rating data, the Pearson correlation coefficient is used to calculate the correlation strength between the indicators in each group of the subjective and objective indicator association groups, and the correlation strength data is obtained. Based on the aforementioned correlation strength data, net correlation strength data is obtained.

6. The method for evaluating the usability of a panoramic surround view system according to claim 5, characterized in that, Based on the objective positive closeness data, the subjective rating data, and the objective rating data, the Pearson correlation coefficient is used to calculate the correlation strength between the indicators in each group of the subjective and objective indicator association groups, resulting in correlation strength data, including: in, The correlation strength of each group of subjective and objective indicators; For the first The subjective evaluation score for this test; For the first The objective metrics of this test show a positive closeness. This represents the mean of the subjective ratings. This represents the mean of the subjective ratings.

7. The method for evaluating the usability of a panoramic surround view system according to claim 5, characterized in that, The step of obtaining net correlation strength data based on the correlation strength data includes: in, To control for interference index Z, the partial correlation coefficient between subjective index S and objective index O; The correlation strength between subjective indicator S and objective indicator O. The correlation strength between the subjective index S and the interference index Z. The correlation strength between objective index O and interference index Z.

8. A device for evaluating the usability of a panoramic surround view system, characterized in that, include: The data acquisition module is used to acquire multiple test tasks of the panoramic surround view system and test evaluation indicators for evaluating the multiple test tasks. The test evaluation indicators include subjective evaluation indicators and objective evaluation indicators. The scoring determination module is used to set test environment parameters for the whole vehicle optical test platform according to the test task, obtain subjective scoring data and objective test data, and obtain objective scoring data based on the objective test data; the subjective scoring data is the scoring data for evaluating the subjective evaluation index, and the objective scoring data is the scoring data for evaluating the objective evaluation index. The data determination module is used to analyze the correlation strength between subjective evaluation indicators and objective evaluation indicators based on the subjective rating data and the objective rating data, and to obtain objective positive closeness data and net correlation strength data. The usability determination module is used to obtain the system usability based on the subjective rating, the objective rating, the objective positive closeness data, and the net correlation strength data.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the panoramic surround view system usability evaluation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the panoramic surround view system usability evaluation method as described in any one of claims 1 to 7.

Images