Automatic detection system for in-vehicle electronic streaming media rearview mirror

Abstract

The invention, which relates to the streaming media rearview mirror detection field, discloses an in-vehicle electronic streaming media rearview mirror automatic detection system comprising a light source camera obscura, a multi-axis light source array, a moving light source track, a dimming module, a temperature and humidity adjusting module, a camera, a dynamic light test environment determination module and an output module. The adaptive test environment is determined based on the parallel depth random forest model, so that the test condition is always focused in the sensitive interval where the potential fault is most easily exposed, a standardized dynamic light environment simulation test system is realized, the test efficiency is ensured, the defect detection rate and the fault mode recognition precision are maximized, and the test efficiency is improved. And a dynamic enhanced optical stress test system is established for product quality verification.

Description

Technical Field

[0001] The present invention relates to the field of streaming media rearview mirror detection, and in particular to an automatic detection system for an in-vehicle electronic streaming media rearview mirror. Background Art

[0002] Automated testing of in-vehicle electronic streaming media rearview mirrors is crucial to driving safety, directly impacting the driver's ability to assess road conditions in complex environments. A key shortcoming in the current industry lies in the lack of a standardized dynamic light environment simulation testing system. This system is particularly unable to accurately replicate extreme lighting scenarios, such as strong headlights from vehicles behind at night and sudden changes in brightness in tunnels. Existing testing processes often rely on static lighting conditions, exposing products to serious defects in real-world road conditions. For example, sudden bursts of strong light can overload the image sensor, causing glare and whiteout, loss of detail, and loss of basic environmental recognition capabilities. This lack of dynamic light environment verification prevents potential optical adaptation defects from being effectively addressed, ultimately leading to the risk of misjudgment in driving decisions. Establishing an automated testing environment capable of simulating dynamic light interference has become an essential technical foundation for improving product optical robustness and ensuring safe, all-weather visibility. Summary of the Invention

[0003] In order to solve the technical problem of lack of standardized dynamic light environment simulation test in the prior art, the present invention provides an automatic detection system for in-vehicle electronic streaming media rearview mirror.

[0004] The present invention is achieved through the following technical solutions: An automatic detection system for an in-vehicle electronic streaming media rearview mirror, comprising: Light source darkroom, multi-axis light source array, motion light source track, dimming module, temperature and humidity adjustment module, camera, dynamic light test environment determination module, output module; The multi-axis light source array is composed of a number of independently controllable LEDs, which are used to simulate natural light and lighting; The multi-axis light source array is installed on a moving light source track and can move on the track; The dynamic light test environment determination module includes a preliminary test environment determination module, a detection result processing module, and an adaptive test environment determination module, which are used to determine the preliminary test environment and the adaptive test environment; The dimming module and the temperature and humidity adjustment module adjust the dynamic light source parameters and the test environment temperature and humidity according to the output of the dynamic light test environment determination module; The camera is used to collect the electronic streaming media rearview mirror image during testing; The output module outputs the total test result based on the test result under the test environment determined by the dynamic light test environment determination module.

[0005] Furthermore, the dynamic light source parameters include light source optical parameters, motion parameters and environmental parameters.

[0006] Furthermore, the optical parameters of the light source include spectral characteristics and polarization characteristics of the light source; The motion parameters include brightness change parameters, flicker frequency, motion trajectory, moving speed, acceleration, and angle change rate; The environmental parameters are used to couple the simulated light environment and adjust the parameters by adjusting the temperature and humidity adjustment module. 。

[0007] Furthermore, the operation of the dynamic light test environment determination module specifically includes the following steps: S1: Build a preliminary test environment; Building a preliminary test environment includes determining a dynamic light source parameter library and determining dynamic light source parameters under the preliminary test environment; S2: Obtain the test results under the preliminary test environment and the test results of the same batch of products and perform feature extraction; S3: Conduct supplementary testing based on the test results of the preliminary test environment and the test results of the same batch of products to establish an adaptive test environment.

[0008] Furthermore, the determination of the dynamic light source parameter library includes compensating and correcting the simulated light in combination with environmental interference parameters, atmospheric transmission parameters and surface reflection parameters to obtain the final and complete dynamic light source parameter library output of the simulated light based on the actual usage scenario based on the specific environment.

[0009] Furthermore, the dynamic light source parameters under the preliminary test environment are determined based on fault guidance, including obtaining historical detection fault data and dividing the faults into N categories according to the fault phenomena; extracting the light source parameters of each category during the fault, including light source optical parameters, motion parameters and environmental parameters; and constructing a preliminary test environment based on the selection of dynamic light source parameters for testing based on the fault category.

[0010] Furthermore, the supplementary test is performed based on the test results of the preliminary test environment and the test results of the same batch of products to establish an adaptive test environment, including: S31: Building a parallel deep random forest model; S32: Perform model training; S33: Input the test results of the preliminary test environment and the image features of the test results of the same batch of products, and generate dynamic light source parameters and the number of test cases for supplementary testing based on the trained model; S34: Establishing an adaptive test environment based on the dynamic light source parameters for the supplementary test and the number of test cases to obtain a final dynamic light test environment.

[0011] Furthermore, the parallel deep random forest model includes three layers of forests, the first layer of forest inputs the detection results of the preliminary test environment and the image features of the detection results of the same batch of products ,in, are the optical performance characteristics, color characteristics, geometric characteristics, texture characteristics, and timing characteristics of the i-th sample respectively.

[0012] Furthermore, the first layer input of the parallel deep random forest model is:

[0013] Output of layer p (p=1,2,3):

[0014] Where T is the number of trees in each forest layer, is the model function of the t-th tree in the p-th layer, is the input of the pth layer; The expression is as follows:

[0015] [ ; ] is the feature splicing operation.

[0016] Furthermore, the loss function expression of the parallel deep random forest model is as follows:

[0017] in, is the prediction error, which is used to measure the difference between the model prediction result and the true value; is the test cost item; is a physical constraint; is the regularization term; 、 、 is the weight coefficient Compared with the prior art, the beneficial effects of the present invention are as follows: through the construction of a systematic adaptive test environment, a dynamically reconfigurable light source control platform is constructed, and a closed-loop decision-making mechanism is driven based on real-time collected test feedback data. The system intelligently explores the light source parameters through a multi-dimensional optimization algorithm, and generates highly customized light source strategies for the core pain points of different test scenarios. Each round of testing dynamically adjusts the parameter combination based on historical performance, and gives priority to the test light source parameters that are most challenging for the current object under test, so that the test conditions are always focused on the sensitive intervals that are most likely to expose potential faults. This closed-loop adaptive mechanism not only avoids the coverage blind spots of fixed light source configurations, but also actively induces abnormal responses under critical conditions by continuously applying targeted optical pressure, thereby maximizing the defect detection rate and fault mode recognition accuracy while ensuring test efficiency, and establishing a dynamically enhanced optical stress testing system for product quality verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a schematic diagram of the workflow of a dynamic light test environment determination module according to an embodiment of the present application; Figure 2 2 is a schematic diagram of the structure of a parallel deep random forest model according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0020] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0021] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The illustrations only show components related to the present invention and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be changed at will, and the component layout form may also be more complicated.

[0022] An automatic detection system for an in-vehicle electronic streaming media rearview mirror, comprising: Light source darkroom, multi-axis light source array, motion light source track, dimming module, temperature and humidity adjustment module, camera, dynamic light test environment determination module, output module; Specifically, the multi-axis light source array is composed of a number of independently controllable LEDs, which are used to simulate natural light and lighting; The multi-axis light source array is installed on a moving light source track and can move on the track; The dynamic light test environment determination module includes a preliminary test environment determination module, a preliminary detection result processing module, and an adaptive test environment determination module; its workflow is to construct a preliminary test environment through the preliminary test environment determination module, and to construct an adaptive test environment based on historical detection results, and finally obtain test results under the preliminary test environment and the adaptive test environment.

[0023] The dimming module and the temperature and humidity adjustment module determine the output parameters of the module according to the dynamic light test environment, that is, the dynamic light source parameters adjust the optical parameters, motion parameters of the light source and the environmental parameters of the test environment; Furthermore, it also includes controlling the motion trajectory, movement speed, acceleration, and angle change rate of the multi-axis light source array on the moving light source track; The camera is used to collect the electronic streaming media rearview mirror image during testing; The output module outputs the total test result based on the test result under the test environment determined by the dynamic light test environment determination module.

[0024] The overall test result includes the detected fault type and the deviation degree.

[0025] The dynamic light test environment determination module specifically includes the following steps: Figure 1 As shown: S1: Build a preliminary test environment; Building a preliminary test environment includes determining a dynamic light source parameter library and determining dynamic light source parameters under the preliminary test environment; S11: Determination of dynamic light source parameter library; Determination of the dynamic light source parameter library includes selecting the dynamic light source parameters according to actual conditions, including selection of light source optical parameters, motion parameters and environmental parameters; The optical parameters of the light source include the spectral characteristics and polarization characteristics of the light source; the spectral characteristics include color temperature, spectral half width, color rendering index, and peak wavelength; The motion parameters include brightness change parameters, flicker frequency, motion trajectory, moving speed, acceleration, and angle change rate; wherein, the brightness change parameters include different types of change modes, such as step mutation mode, which is used to simulate tunnel exit / entry, exponential decay mode, which is used to simulate sunset scenes, sinusoidal modulation mode, which is used to simulate boulevard strobe, and random pulse mode, which is used to simulate the random appearance of car lights.

[0026] Environmental parameters are used to couple the simulated light environment and are adjusted by adjusting the temperature and humidity adjustment module.

[0027] Preferably, the present invention also combines environmental interference parameters, atmospheric transmission parameters and surface reflection parameters to compensate and correct the simulated light, thereby obtaining a final and perfect dynamic light source parameter library output of the simulated light based on the actual usage scenario and the specific environment; Specifically, the environmental interference parameters include temperature, humidity, precipitation intensity, and pollutant concentration; the atmospheric transmission parameters include attenuation coefficient and visibility, and the attenuation coefficient characterizes the distance-related brightness attenuation; the surface reflection parameters include the effects of reflections such as ice, roads of different materials, and vehicle body paint on light.

[0028] The dynamic light source parameter library finally obtained includes light source parameters of simulated light in various usage environments.

[0029] S12: Determine the parameters of the dynamic light source under the preliminary test environment; According to the research on existing common faults, it can be found that some electronic streaming media rearview mirrors have white images in strong light areas due to excessive reflectivity of the lens coating or too high setting of the highlight clipping threshold of the processing algorithm; some have multiple reflections inside the lens due to insufficient extinction processing of the lens barrel, resulting in ghosting; in some scenarios, the built-in algorithm incorrectly identifies the light source, resulting in color distortion and other situations. Therefore, the present invention determines the test environment based on the fault type, and adopts different dynamic light tests for different faults to improve the test coverage of the faults.

[0030] Based on this, the present invention constructs a test environment based on fault guidance, which specifically includes the following steps: a. Obtain historical fault detection data and classify the faults into N categories based on the fault phenomena; The fault phenomena include screen whitening, motion smearing, color distortion, freezing, screen noise, ghosting, etc. b. Extract the light source parameters for each category of fault, including light source optical parameters, motion parameters, and environmental parameters; c. Select dynamic light source parameters for testing and build a preliminary test environment, including a basic test library; The basic test library uses dynamic light source parameters determined based on common fault types as a preliminary test environment. The selection of test light is relatively balanced and does not take individual needs into consideration.

[0031] S2: Obtain the test results under the preliminary test environment and the test results of the same batch of products and perform feature extraction; S21: collecting image data of the electronic streaming media rearview mirror under test through a camera to obtain detection result image data under different dynamic light source tests; S22: extracting image features from the image data; Specifically, the image features include optical performance features, color characteristics, geometric characteristics, texture characteristics, and time sequence characteristics; The optical performance characteristics include global brightness mean, highlight area brightness, dark area details, dynamic range, glare suppression rate, halo area ratio, and contrast loss rate; The color characteristic features include average color difference, maximum color difference, white balance error, and color saturation; The geometric characteristics include barrel distortion rate, pincushion distortion rate, edge resolution loss, straight line curvature, distance calibration error, and angle preservation; The texture characteristics include edge sharpness, signal-to-noise ratio, and noise power spectrum; The temporal characteristics include light adaptation time, motion blur value, inter-frame consistency, and maximum delay.

[0032] S3: Conduct supplementary testing based on the test results of the preliminary test environment and the test results of the same batch of products to establish an adaptive test environment; For products of different models and batches, the causes and phenomena of failures may be different. For products of the same batch, since the same materials and processes are used, once a failure occurs, other products of the same batch are likely to have the same problem. Therefore, it is necessary to build an adaptive test environment and focus on troubleshooting the detection problems that have occurred in similar products. This application builds an adaptive test environment based on the detection results in the preliminary test environment and the detection results of products from the same batch. Specifically, the dynamic light source parameters and the number of test cases for supplementary testing are determined based on a parallel deep random forest model to establish an adaptive test environment; the model input is the detection results of the preliminary test environment and the image features of the detection results of products from the same batch, and the output is the dynamic light source parameters for supplementary testing and the number of test cases corresponding to each parameter; The specific steps include: S31: Build a parallel deep random forest model, such as Figure 2 As shown, the model includes three layers of forests. The first layer of forest inputs the detection results of the preliminary test environment and the image features of the detection results of the same batch of products. ,in, are the optical performance characteristics, color characteristics, geometric characteristics, texture characteristics, and temporal characteristics of the i-th sample respectively; Layer 1 input:

[0033] Output of layer p (p=1,2,3):

[0034] Where T is the number of trees in each forest layer, is the model function of the t-th tree in the p-th layer, is the input of the pth layer; The expression is as follows:

[0035] [ ; ] is the feature splicing operation.

[0036] Furthermore, the loss function of the parallel deep random forest model is determined by combining the physical constraints of the light parameters of natural light and lighting and the test cost, and is expressed as follows:

[0037] in, is the prediction error, which is used to measure the difference between the model prediction result and the true value; is the test cost item; is a physical constraint; is the regularization term; 、 、 is the weight coefficient.

[0038] Among them, the prediction error term The expression is as follows:

[0039] Where K is the number of trees in the parallel random forest; For the The weight of a tree is usually based on the accuracy of the tree on the validation set; is the predicted value of the k-th tree for the regression target; is the true target value in the regression task.

[0040] The Huber loss function is defined as: It is a hyperparameter of Huber loss, which controls the switching threshold between square error and absolute error.

[0041] Test cost items , used to control the number of test cases and encourage the use of fewer test samples: is the number of test cases currently selected, is the number of benchmark test cases, used for normalization.

[0042] Physical constraints , which is a penalty term that ensures that the light source parameters meet the physical constraints. It consists of multiple sub-penalty terms for different types of constraints:

[0043] in, Represents the penalty value of the i-th constraint. Specifically includes: Boundary constraints, such as wavelength range, intensity range; For each parameter, a penalty is imposed if it exceeds the bounds:

[0044] in: is the j-th light source parameter, , is the minimum and maximum value allowed for the jth parameter.

[0045] Regularization term , which is used to control the complexity of the model and consists of two parts:

[0046] in, is the feature weight matrix; is the square of the Frobenius norm; is the depth of the k-th tree; is the weight coefficient of the tree depth penalty.

[0047] S32: Perform model training; based on the historical fault data, obtain image data and light source parameters at the time of the historical fault, and manually determine the number of test cases as a training database; S33: Input the test results of the preliminary test environment and the image features of the test results of the same batch of products, and generate dynamic light source parameters and the number of test cases for supplementary testing based on the trained model; S34: Establishing an adaptive test environment based on the dynamic light source parameters for the supplementary test and the number of test cases to obtain a final dynamic light test environment.

[0048] The dynamic light source test optimization model based on a parallel deep random forest offers significant advantages: its multi-granularity scanning mechanism intelligently analyzes the complex features of preliminary test images, accurately capturing their nonlinear correlations with light source parameters, and transcending the limitations of manual experience. Through efficient parallel computing, the model outputs optimized dynamic light parameters and the corresponding adaptive number of test cases in real time. Critical parameters are automatically allocated more resources, and low-confidence scenarios are dynamically tested, avoiding redundancy or omissions caused by evenly distributed testing. This creates a self-evolving "perception-decision-optimization" testing system.

[0049] In this embodiment, a dynamically reconfigurable light source control platform is constructed through the establishment of a systematic adaptive test environment, and a closed-loop decision-making mechanism is driven based on real-time collected test feedback data. The system intelligently explores the light source parameters through a multi-dimensional optimization algorithm, and generates highly customized light source strategies for the core pain points of different test scenarios. Each round of testing dynamically adjusts the parameter combination based on historical performance, giving priority to the test light source parameters that are most challenging for the current object under test, so that the test conditions are always focused on the sensitive range that is most likely to expose potential faults. This closed-loop adaptive mechanism not only avoids the coverage blind spots of fixed light source configurations, but also actively induces abnormal responses under critical conditions by continuously applying targeted optical pressure, thereby maximizing the defect detection rate and fault mode recognition accuracy while ensuring test efficiency, and establishing a dynamically enhanced optical stress testing system for product quality verification.

[0050] The embodiments described above are merely descriptions of preferred implementations of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the scope of protection determined by the claims of the present invention.

Claims

1. An automatic detection system for in-vehicle electronic streaming media rearview mirror, characterized in that: include Light source darkroom, multi-axis light source array, motion light source track, dimming module, temperature and humidity adjustment module, camera, dynamic light test environment determination module, output module; The multi-axis light source array is composed of a number of independently controllable LEDs, which are used to simulate natural light and lighting; The multi-axis light source array is installed on a moving light source track and can move on the track; The dynamic light test environment determination module includes a preliminary test environment determination module, a detection result processing module, and an adaptive test environment determination module, which are used to determine the preliminary test environment and the adaptive test environment; The dimming module and the temperature and humidity adjustment module adjust the dynamic light source parameters and the test environment temperature and humidity according to the output of the dynamic light test environment determination module; The camera is used to collect the electronic streaming media rearview mirror image during testing; The output module outputs the total test result based on the test result under the test environment determined by the dynamic light test environment determination module.

2. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 1 is characterized in that: The dynamic light source parameters include light source optical parameters, motion parameters and environmental parameters.

3. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 2 is characterized in that: The optical parameters of the light source include spectral characteristics and polarization characteristics of the light source; The motion parameters include brightness change parameters, flicker frequency, motion trajectory, moving speed, acceleration, and angle change rate; The environmental parameters are used to couple the simulated light environment and adjust the parameters by adjusting the temperature and humidity adjustment module. 。 4. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 1 is characterized in that: The dynamic light test environment determination module specifically includes the following steps: S1: Build a preliminary test environment; Building a preliminary test environment includes determining a dynamic light source parameter library and determining dynamic light source parameters under the preliminary test environment; S2: Obtain the test results under the preliminary test environment and the test results of the same batch of products and perform feature extraction; S3: Conduct supplementary testing based on the test results of the preliminary test environment and the test results of the same batch of products to establish an adaptive test environment.

5. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 4 is characterized in that: The determination of the dynamic light source parameter library includes compensating and correcting the simulated light in combination with environmental interference parameters, atmospheric transmission parameters and surface reflection parameters to obtain the final and complete dynamic light source parameter library output of the simulated light based on the actual usage scenario based on the specific environment.

6. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 4 is characterized in that: The dynamic light source parameter determination under the preliminary test environment is performed based on fault guidance, including obtaining historical fault detection data and classifying the faults into N categories according to the fault phenomena; extracting the light source parameters of each category at the time of the fault, including light source optical parameters, motion parameters and environmental parameters; Based on the fault category, the dynamic light source parameters for testing are selected to construct a preliminary test environment.

7. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 4 is characterized in that: The aforementioned supplementary testing based on the test results of the preliminary test environment and the test results of the same batch of products to establish an adaptive test environment includes: S31: Building a parallel deep random forest model; S32: Perform model training; S33: Input the test results of the preliminary test environment and the image features of the test results of the same batch of products, and generate dynamic light source parameters and the number of test cases for supplementary testing based on the trained model; S34: Establishing an adaptive test environment based on the dynamic light source parameters for the supplementary test and the number of test cases to obtain a final dynamic light test environment.

8. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 7 is characterized in that: The parallel deep random forest model includes three layers of forests. The first layer of forest inputs the detection results of the preliminary test environment and the image features of the detection results of the same batch of products. ,in, are the optical performance characteristics, color characteristics, geometric characteristics, texture characteristics, and timing characteristics of the i-th sample respectively.

9. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 8, characterized in that: The first layer input of the parallel deep random forest model is: Output of layer p (p=1,2,3): Where T is the number of trees in each forest layer, is the model function of the t-th tree in the p-th layer, is the input of the p-th layer; The expression is as follows: [ ; ] is the feature splicing operation.

10. The automatic detection system for in-vehicle electronic streaming media rearview mirror according to claim 9, characterized in that: The loss function expression of the parallel deep random forest model is as follows: in, is the prediction error, which is used to measure the difference between the model prediction result and the true value; is the test cost item; is a physical constraint; is the regularization term; 、 、 is the weight coefficient.

Images