Reversing image performance test method, device and equipment

Abstract

The invention provides a reverse image performance testing method, device and equipment, and relates to the technical field of reverse image performance testing, and the method comprises the steps: obtaining a first moment corresponding to a reverse gear triggering action of a tested vehicle; acquiring the brightness of a vehicle machine screen of the test vehicle; determining a moment when the brightness of the vehicle machine screen is greater than or equal to a preset brightness detection reference threshold value as a second moment; the preset brightness detection reference threshold value is determined according to the environment illumination intensity and the mapping relation between the preset environment illumination intensity and the screen display brightness; determining the time difference between the first moment and the second moment as the reaction duration of the back-up image of the tested vehicle; the reaction duration is used for evaluating the performance of the reversing image of the tested vehicle; according to the invention, the reaction time of the back-up image can be automatically and accurately tested.

Description

Technical Field

[0001] This invention relates to the field of reversing camera performance testing technology, and in particular to a reversing camera performance testing method, apparatus and equipment. Background Technology

[0002] In the field of automotive active safety, the performance testing of reversing cameras encompasses many aspects. The reaction time of the reversing camera system (the time interval from shifting the vehicle into reverse to the display of a clear image on the screen) is a crucial factor and a key indicator affecting driving safety. Industry safety standards require this time to be ≤100ms; exceeding this time can easily lead to drivers misjudging obstacle distances, increasing the risk of collision. Currently, the mainstream method for testing reversing camera display time in the industry is manual timing, requiring two testers to operate collaboratively: one responsible for shifting gears, and the other using a stopwatch to time and observe the screen display. This method has significant drawbacks: firstly, the combined visual delay of the testers and the delay of manual operation result in a single timing error ≥150ms; secondly, different personnel, and even the same personnel, have inconsistent standards for judging the start time of image display (i.e., the end time of timing), resulting in a repeatability deviation ≥30ms, making it impossible to accurately determine whether the camera system is qualified. Therefore, how to automatically and accurately test the reaction time of reversing cameras has become an urgent technical problem to be solved. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows: According to a first aspect of this application, a method for testing the performance of a reversing camera is provided, comprising: Obtain the first moment corresponding to the reverse gear trigger action of the test vehicle; Obtain the brightness of the vehicle's infotainment screen; The moment when the brightness of the vehicle screen is greater than or equal to a preset brightness detection benchmark threshold is defined as the second moment; the preset brightness detection benchmark threshold is determined by the ambient light intensity and the preset mapping relationship between the ambient light intensity and the screen display brightness. The time difference between the first moment and the second moment is determined as the reaction time of the reversing image of the test vehicle; the reaction time is used to evaluate the performance of the reversing image of the test vehicle.

[0004] Furthermore, the preset mapping relationship between ambient light intensity and screen display brightness is established through the following steps: Several sets of ambient light intensity samples and the corresponding actual brightness values ​​of the vehicle's infotainment screen in the reversing image display state were collected; the ambient light intensity samples covered the light range of 0-10000 lux. Based on the aforementioned sets of ambient light intensity samples and actual brightness values, a mapping function between ambient light intensity and screen display brightness is obtained through linear regression or neural network algorithms; the mapping function is used to characterize the screen brightness benchmark when the reversing image is clearly displayed under different ambient light conditions.

[0005] Furthermore, the preset brightness detection benchmark threshold is determined through the following steps: Real-time detection of the rate of change in ambient light intensity in the environment where the test vehicle is located; If the rate of change is greater than or equal to a preset threshold for the rate of change of ambient light intensity, the brightness detection benchmark threshold is re-determined based on the current ambient light intensity and the mapping relationship between ambient light intensity and screen display brightness. The recalculated brightness detection benchmark threshold replaces the original brightness detection benchmark threshold and is used for subsequent determination at the second time step.

[0006] Furthermore, the method also includes: Obtain the distortion rate, MTF value, and ΔE color difference of the reversing image displayed on the vehicle's infotainment screen; Based on the reaction time ΔT, distortion rate D, MTF value M, and chromatic difference ΔQE of the test vehicle's reversing image, the corresponding safety risk coefficient SRC of the test vehicle is determined. SRC satisfies the following relationship: SRC=(ΔT / ΔT0)×W t +(D / D0)×W i +(1-M / M0)×W m +(ΔQE / ΔE0)×W e ; Wherein, ΔT0, D0, M0, and ΔE0 are the basic thresholds corresponding to ΔT, D, M, and ΔQE, respectively; W t W i W m and W e The dynamic weights corresponding to ΔT, D, M, and ΔQE are, in order. Based on the SRC, determine the corresponding safety risk level of the test vehicle.

[0007] Furthermore, the adjustment of the dynamic weights is achieved through a scene recognition submodule; the scene recognition submodule includes a miniature LiDAR and a brightness sensor, used to identify the test scene type; When the lidar detects obstacles on either side of the test vehicle at a distance less than a preset distance, the clarity priority mode is triggered, and the W value is increased. m Lower W t ; When the lidar detects obstacles on either side of the test vehicle at a distance greater than or equal to a preset distance, the display time priority mode is triggered, and W is increased. tLower W m ; If the brightness sensor detects that the ambient illuminance is less than the preset illuminance threshold, increase W. e .

[0008] Furthermore, it also includes: The vehicle bus deep analysis module connects to the vehicle's OBD interface to read real-time data from the vehicle's ECU. Based on the reaction time, distortion rate, MTF value, ΔE color difference, and real-time data read from the ECU, cross-validation is performed using a preset fault knowledge graph; the fault knowledge graph includes abnormal indicator nodes, component fault nodes, and system-related nodes. The fault source conclusion is output through cross-validation; the conclusion is used to locate the root cause of the fault in the reversing camera system.

[0009] Furthermore, the real-time data includes at least one of the following: camera power supply voltage, reversing image data transmission rate, vehicle CPU load, image processing chip parameters, and camera installation angle calibration parameters.

[0010] Furthermore, the reverse gear triggering action of the test vehicle is detected by a microswitch installed at the gear shift lever.

[0011] According to another aspect of this application, a reversing camera performance testing device is also provided, the device comprising: The first moment acquisition module is used to acquire the first moment corresponding to the reverse gear trigger action of the test vehicle. The screen brightness acquisition module is used to acquire the brightness of the vehicle's infotainment screen. The second moment acquisition module is used to determine the moment when the brightness of the vehicle screen is greater than or equal to a preset brightness detection benchmark threshold as the second moment; the preset brightness detection benchmark threshold is determined by the ambient light intensity and the preset mapping relationship between the ambient light intensity and the screen display brightness. The reaction time determination module is used to determine the time difference between the first moment and the second moment as the reaction time of the test vehicle's reversing image; the reaction time is used to evaluate the performance of the test vehicle's reversing image.

[0012] According to another aspect of this application, an electronic device is also provided, including a processor and the aforementioned reversing image performance testing device, or the processor performing the method described in any of the first aspects.

[0013] The present invention has at least the following beneficial effects: The reversing image performance testing method of this invention determines the brightness detection benchmark threshold based on ambient light intensity and a preset mapping relationship between ambient light intensity and screen display brightness. This dynamically adapts to the screen display characteristics under different lighting scenarios (such as strong light, weak light, and dusk), effectively avoiding the problem of misjudgment due to lighting interference caused by fixed thresholds or manual judgment in existing technologies. It not only achieves automatic and accurate testing of the reversing image's reaction time but also significantly improves the accuracy of the second moment determination. Simultaneously, by accurately capturing the first moment of reverse gear triggering and the second moment of brightness reaching the standard and calculating the reaction time, it overcomes the shortcomings of traditional manual timing, such as large errors and poor repeatability. This provides an objective and reliable quantitative indicator for reversing image performance evaluation, accurately reflecting the response speed of the image system and laying the foundation for subsequent multi-dimensional evaluations combining image quality and safety risks. This helps to comprehensively improve the scientific rigor and reliability of reversing image testing, ensuring driving safety. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A flowchart illustrating the workflow of a reversing camera system provided in an embodiment of the present invention; Figure 2 A flowchart of a reversing camera performance testing method provided in an embodiment of the present invention; Figure 3 A flowchart of the triggering module provided in an embodiment of the present invention; Figure 4 A flowchart illustrating the operation of the brightness detection module provided in an embodiment of the present invention; Figure 5 A flowchart illustrating the operation of the reference calibration module provided in this embodiment of the invention; Figure 6 This is a flowchart of the main control computing module provided in an embodiment of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] It should be noted that, based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Furthermore, this device and / or practice the method can be implemented using other structures and / or functionalities besides one or more of the aspects set forth herein.

[0018] As a core component of automotive active safety, the reversing camera system's workflow is as follows: Figure 1 As shown, its main workflow is as follows: 1. Driver shifts to reverse gear → reverse switch closes → Body Control Controller (BCM) sends trigger command to vehicle infotainment system; 2. Place an external stable light source behind the reversing camera → the vehicle's infotainment system wakes up the reversing camera → the camera captures the rear image and transmits it to the image processing chip; 3. After the chip completes distortion correction and color optimization, it outputs the image to the vehicle's infotainment screen for display.

[0019] The time interval of the above process is the reaction time, which directly affects driving safety: if the reaction time exceeds 100ms, when the vehicle is reversing at 5km / h, the vehicle has moved about 0.14m within 100ms, which may cause the driver to misjudge the distance of the obstacle and increase the risk of collision (especially in narrow sections or low-speed maneuvering scenarios).

[0020] The core requirements for testing tools vary significantly across different scenarios: Research and development scenario: High precision (error ≤ ±2ms), multi-environment adaptability (temperature range -10℃-50℃, strong light / dim environment), support for data export and trend analysis, used to optimize the startup logic of imaging system software; Production scenario: High efficiency (single unit test ≤ 5 minutes), simple operation (ordinary workers can learn to use), low cost (single set of equipment ≤ 500 yuan), used for quality control of 10%-20% sampling inspection ratio on the production line; After-sales scenario: It needs to be portable (weight ≤300g, size ≤15cm×10cm×5cm), have long battery life (continuous testing ≥4 hours), and be free from modification, for performance verification after vehicle repair.

[0021] The currently used mainstream method is manual timing, as follows: Personnel configuration: 2 testers operate in coordination, 1 person is responsible for switching vehicle gears, and 1 person is responsible for timing and observation; Tools: stopwatch (accuracy 0.01s), notebook, flashlight (for observation in low light conditions); Test process: Tester 1 issues the "shift gear" command, and at the same time, tester 2 starts the stopwatch; Tester 2 observed the vehicle's infotainment screen and stopped the stopwatch when the reversing image appeared. Repeat the test 3-5 times and take the average as the final result; Key parameters: timing accuracy ±50ms, repeatability deviation ±30ms, single-unit test time ≥10 minutes.

[0022] The existing testing methods have the following drawbacks: 1. Delayed human reaction → large timing error Testers observed a "visual delay" (approximately 0.1-0.3s) between gear shifting and screen display, and a "motion delay" (approximately 0.05-0.1s) when manually operating the stopwatch. The combination of these two factors resulted in a single timing error of ≥150ms, far exceeding the industry's testing requirement of "display time ≤100ms," making it impossible to accurately determine whether the imaging system was qualified.

[0023] 2. Inconsistent judgment criteria → poor repeatability Different testers have different criteria for determining when an image begins to display (e.g., some believe that a blurry image is considered to have started to display, while others believe that a clear and stable image is considered to have started to display); even the same tester may have different timing for multiple observations, resulting in a deviation of ≥30ms in repeated tests and low data reliability.

[0024] 3. Interference resistance design → weak environmental adaptability In bright light, screen reflections make observation difficult and delay the determination of "start display"; in low light, screen brightness fluctuations are easily mistaken for "start display". The test results in the two scenarios deviate by ≥50ms, which cannot meet the needs of multi-environment testing.

[0025] Based on the above issues, the following will refer to Figure 2 The flowchart shown illustrates a method for testing the performance of a reversing camera, introducing such a method.

[0026] The method for testing the performance of a reversing camera may include the following steps: S100, obtain the first moment corresponding to the reverse gear trigger action of the test vehicle.

[0027] In this embodiment, a combination of a highly sensitive micro switch and an adjustable bracket is used to achieve the acquisition of the first moment. The micro switch is selected with a response time of ≤1ms and is fixed next to the vehicle gear lever by a telescopic and rotatable bracket. The gap between the switch and the lever is adjusted to 0.2mm (≤0.3mm to ensure that the lever action can be accurately triggered).

[0028] When the driver shifts the gear to reverse, the lever mechanically contacts the microswitch, which immediately outputs a low-level trigger signal (jumping from a high level of 5V to 0V). The main control module (such as an STM32H743 microprocessor) captures this signal through the interrupt interface and records this moment as the first moment (t1). For example, in a certain test, t1 = 16:23:45.000000.

[0029] The process of obtaining the first moment through a microswitch is as follows: Figure 3 As shown, the adjusting bracket makes the micro switch trigger end contact with the gear shift lever (gap ≤ 0.3mm); when the driver shifts the gear to reverse, the lever pushes the micro switch trigger end, the switch closes, and a low-level start signal is output; after the gear returns to the original position, the switch automatically resets and outputs a high level, waiting for the next trigger.

[0030] S200, obtains the brightness of the vehicle's infotainment screen.

[0031] In this embodiment, a brightness detection module is provided above the reversing image screen. The brightness detection module integrates a "focusing lens + photoelectric sensor (such as TSL2591)": the focusing lens has a focal length of 5mm and only collects light from a 3cm×3cm area in the center of the vehicle screen (to avoid ambient light interference). The photoelectric sensor converts the light signal into a current signal (sensitivity 0.1μA / lux), which is then amplified 100 times by an operational amplifier (such as OPA333) and converted into a voltage signal of 0-3.3V (corresponding to a screen brightness of 0-10000lux), and transmitted in real time to the ADC interface of the main control module (sampling rate 1kHz).

[0032] The process of obtaining screen brightness through the brightness detection module is as follows: Figure 4 As shown, adjust the focal length of the focusing lens so that the photodiode only receives light from the central image area of ​​the screen.

[0033] When no image is displayed: Low screen brightness → weak current output from photodiode → amplified voltage < reference threshold → comparator output low level.

[0034] When displaying images: screen brightness is significantly increased → photodiode outputs strong current → amplified voltage ≥ reference threshold → comparator outputs high-level termination signal. The focusing lens reduces ambient light incidence, and the signal conditioning circuit filters out high-frequency noise to ensure signal stability.

[0035] S300, the moment when the brightness of the vehicle screen is greater than or equal to a preset brightness detection benchmark threshold is determined as the second moment; the preset brightness detection benchmark threshold is determined by the ambient light intensity and the preset mapping relationship between ambient light intensity and screen display brightness.

[0036] In this embodiment, the preset brightness detection benchmark threshold is dynamically calculated using "ambient light intensity + mapping relationship": Ambient light intensity is detected in real time by a brightness sensor (BH1750 integrated in the same module, accuracy ±20%). For example, the detected value is 3000 lux in a certain scene. The mapping relationship is a pre-fitted function. For example, the mapping function for a normal scene (100-5000 lux) is y=0.06x+100 (x is ambient light intensity, y is the brightness threshold, unit cd / m²). Then, the baseline threshold corresponding to 3000 lux is y=0.06×3000+100=280cd / m².

[0037] The main control module continuously compares the screen brightness voltage signal (converted to cd / m²) with the reference threshold. When the screen brightness increases from 200 cd / m² to 280 cd / m², this moment is recorded as the second moment (t2), for example, t2=16:23:45.080000.

[0038] In this embodiment, ambient light interference is dynamically eliminated through a preset benchmark calibration module. The workflow is as follows: Figure 5 As shown, before the test, the reversing camera is aimed at an external stable light source (such as a light panel), and the photoelectric sensor is aimed at the screen; the reversing begins → the camera captures the image, the photoelectric sensor acquires the light signal → V_ref and V_th are calculated; during the test, the brightness detection module uses V_th as the judgment standard and outputs a termination signal.

[0039] S400, the time difference between the first moment and the second moment is determined as the reaction time of the reversing image of the test vehicle; the reaction time is used to evaluate the performance of the reversing image of the test vehicle.

[0040] The response time = t2-t1 = 80ms. Compared with the industry safety standard (≤100ms), the response speed of the reversing camera system is deemed to be qualified.

[0041] In this embodiment, the main control computing module can achieve high-precision time difference calculation, and its structure consists of: Core component: MCU.

[0042] Error compensation algorithm: Before leaving the factory, the timer is calibrated by a standard signal source and a "timer zero-point error Δt0" (usually ≤0.5ms) is pre-stored. Δt0 is automatically deducted during calculation. The formula is: final reaction time ΔT = (second moment T2 - first moment T1) / 1000 - Δt0 (unit: ms).

[0043] Data processing: Supports continuous test data statistics, automatically calculates the average, maximum and minimum values ​​(the number of tests can be set from 1 to 99).

[0044] The workflow of the main control computing module is as follows: Figure 6 As shown: The MCU receives a low-level start signal from the trigger module via GPIO interrupt → immediately starts the TIM3 timer and records T1; The MCU receives a high-level termination signal from the brightness detection module via a GPIO interrupt → immediately stops the timer and records T2; ΔT is calculated according to the formula, and Δt0 is automatically deducted. If continuous testing is enabled, ΔT will be stored in a temporary cache and the statistical data will be updated.

[0045] Compared to traditional manual timing (error ≥ 150ms) and fixed threshold judgment, the method in this embodiment achieves a triple improvement through "hardware triggering + dynamic brightness threshold": First, the first-moment capture error is ≤ 1ms (the mechanical response of the micro-switch is much faster than human reaction); second, the brightness reference threshold is dynamically adjusted according to the ambient light, greatly reducing the misjudgment rate in low-light (such as dusk) and strong-light scenes; third, the reaction time calculation accuracy reaches ±2ms, providing a quantifiable and highly reliable basis for the performance evaluation of reversing images, directly solving the industry pain points of "inconsistent manual judgment standards and large environmental interference", and better meeting the actual driving safety needs.

[0046] Furthermore, the preset mapping relationship between ambient light intensity and screen display brightness is established through the following steps: Several sets of ambient light intensity samples and the corresponding actual brightness values ​​of the vehicle's infotainment screen in the reversing image display state were collected; the ambient light intensity samples covered the illumination range of 0-10000 lux.

[0047] In this embodiment, samples can be collected in three categories of scenarios (≥50 groups per category, covering 0-10000 lux): Low-light scenario (0-100 lux): Simulates an underground parking lot and a rainy night. Use dimmable LED lights to control the ambient light. Adjust the light value each time (e.g., 10 lux, 50 lux, 100 lux). At the same time, use a luminance meter to measure the actual brightness of the car screen when the reversing image is clearly displayed (e.g., 80 cd / m² at 10 lux and 150 cd / m² at 100 lux).

[0048] Typical scenarios (100-5000 lux): Simulate cloudy days and indoor environments, collecting data such as 300 lux (screen 200 cd / m²) and 1000 lux (260 cd / m²).

[0049] Strong light scene (5000-10000 lux): Simulate midday sunlight, use xenon lamps to simulate strong light, and collect data such as 5000 lux (screen 400 cd / m²) and 10000 lux (600 cd / m²).

[0050] Based on the aforementioned sets of ambient light intensity samples and actual brightness values, a mapping function between ambient light intensity and screen display brightness is obtained through linear regression or neural network algorithms; the mapping function is used to characterize the screen brightness benchmark when the reversing image is clearly displayed under different ambient light conditions.

[0051] In this embodiment, a linear regression algorithm is used to process the samples: the low-light scene data is substituted into y=kx+b to calculate k and b; then, 10 sets of new data are used for testing. The deviation between the fitted value and the actual value is ≤5cd / m², confirming that the mapping function is reliable, and the data is stored in the main control module Flash.

[0052] In this embodiment, the mapping relationship constructed by "full-scene samples + algorithm fitting" solves the shortcomings of the traditional fixed threshold "one-size-fits-all" approach. For example, in low-light scenes, a fixed threshold of 300 cd / m² can cause the screen brightness to be below standard (actually only 150 cd / m²) but still be misjudged as "not displayed". However, the low-light mapping function of this solution can accurately output a threshold of 150 cd / m², which greatly improves the accuracy of the judgment. At the same time, scene-specific fitting avoids the deviation of a single function across scenes, provides a data-driven scientific basis for the brightness benchmark threshold, and significantly improves the robustness of the test.

[0053] Furthermore, the preset brightness detection benchmark threshold is determined through the following steps: Real-time detection of the rate of change in ambient light intensity in the environment where the test vehicle is located.

[0054] If the rate of change is greater than or equal to a preset threshold for the rate of change of ambient light intensity, the brightness detection benchmark threshold is re-determined based on the current ambient light intensity and the mapping relationship between ambient light intensity and screen display brightness.

[0055] The recalculated brightness detection benchmark threshold replaces the original brightness detection benchmark threshold and is used for subsequent determination at the second time step.

[0056] In this embodiment, the detection of the rate of change of illumination can be achieved through the following steps: The ambient light intensity is sampled 10 times per second using a brightness sensor (BH1750). The main control module calculates the difference between two consecutive samples (e.g., 3000 lux in the first second and 5000 lux in the second second, with a difference of 2000 lux), and divides it by the time interval (1s) to obtain the rate of change of 2000 lux / s. The preset threshold for the rate of change is 500 lux / s (based on the measured light change rate in scenarios such as "tunnel entrance, tree shade switching").

[0057] Dynamically update the baseline threshold: When the rate of change is ≥500 lux / s (such as 2000 lux / s above), the threshold is updated. For example, read the current illumination of 5000 lux, call the strong light scene mapping function y=0.04x+400, and calculate the new threshold = 0.04×5000+400=600cd / m².

[0058] The main control module immediately replaces the original threshold (280 cd / m² corresponding to 3000 lux), and the subsequent second-time determination is based on 600 cd / m² until the light change rate is <500 lux / s (if it is stable at 5000 lux, the change rate is 0).

[0059] The method in this embodiment addresses dynamic scenarios such as "suddenly entering a tunnel (light intensity drops abruptly from 10,000 lux to 100 lux)" and "sunlight being blocked by clouds (5,000 lux → 2,000 lux)" by dynamically updating the threshold. This avoids misjudgments caused by "threshold lag." For example, in a tunnel entrance scenario, if the threshold is not updated, the original strong light threshold of 600 cd / m² would cause the screen brightness to reach 200 cd / m² (actually qualified) but be judged as "unqualified." However, this solution can update the threshold to 143 cd / m² (100 lux × 0.7 + 73) within 1 second, reducing the judgment delay in dynamic scenarios from 500 ms to less than 50 ms, significantly improving the environmental adaptability of the testing method.

[0060] Furthermore, the method also includes: Obtain the distortion rate, MTF value, and ΔE color difference of the reversing image displayed on the vehicle's infotainment screen.

[0061] In this embodiment, the distortion rate, MTF value, and ΔE chromatic difference of the reversing image are obtained through the following methods: Distortion rate (D): A standard checkerboard calibration board (10×10 grids, 20cm per grid) is placed 5m behind the test vehicle. The CMOS sensor (OV5640, 5-megapixel) captures images, and the distortion correction algorithm chip (GM7150) extracts the grid vertex coordinates. The coordinates are compared with the standard coordinates, and the proportion of the average offset to the total grid length is calculated (e.g., in a certain test, the average offset is 1.2cm, the total grid length is 200cm, and D=0.6%).

[0062] MTF value (M): Take a picture of an ISO 12233 resolution card, extract the contrast of a 10 line pairs / mm area (maximum brightness - minimum brightness), divide by the standard contrast (measured value on the calibration board), and get M=0.65 (≥0.5 is acceptable).

[0063] ΔE color difference (ΔQE): Shoot a standard 24-color card, collect the RGB values ​​of the red block (R=240, G=30, B=40), and substitute them with the standard value (R=255, G=0, B=0) into the ΔE formula to calculate ΔQE=3.2 (≤5 is acceptable).

[0064] Based on the reaction time ΔT, distortion rate D, MTF value M, and chromatic difference ΔQE of the test vehicle's reversing image, the corresponding safety risk coefficient SRC of the test vehicle is determined. SRC satisfies the following relationship: SRC=(ΔT / ΔT0)×W t +(D / D0)×W i +(1-M / M0)×W m +(ΔQE / ΔE0)×W e ; Wherein, ΔT0, D0, M0, and ΔE0 are the basic thresholds corresponding to ΔT, D, M, and ΔQE, respectively; W t W i W m and W e The dynamic weights are ΔT, D, M, and ΔQE, respectively.

[0065] In this embodiment, ΔT0, D0, M0, and ΔE0 can be determined based on relevant regulations, for example: ΔT0 = 100ms, D0 = 3%, M0 = 0.5, ΔE0 = 5; W t W i W m and W e This is an empirical value; the default value is W. t =0.3, W i =0.2, W m =0.3, W e =0.2.

[0066] Based on the SRC, determine the corresponding safety risk level of the test vehicle.

[0067] In this embodiment, the safety risk level is determined based on the SRC value range: for example, SRC≤0.8 is low risk, 0.8<SRC≤1.2 is medium risk, and SRC>1.2 is high risk.

[0068] The above methods overcome the limitations of traditional methods that only measure "reaction time." By integrating quality indicators such as distortion rate and clarity, the hidden danger of "collisions caused by blurry images despite meeting reaction time standards" is resolved (e.g., a certain model has a reaction time of 80ms, which is acceptable, but a distortion rate of 5% can lead to drivers misjudging the distance to obstacles). SRC quantifies risk, upgrading the assessment from "acceptable / unacceptable" to "risk level." For example, an SRC of 1.1 (medium risk) can indicate "the need to optimize color reproduction," providing automakers with more refined improvement directions. At the same time, the weighting based on over 100,000 accident data points enables SRC to achieve a 92% fit with actual collision risks, significantly improving the safety guidance value of the assessment.

[0069] Furthermore, the adjustment of the dynamic weights is achieved through a scene recognition submodule; the scene recognition submodule includes a miniature LiDAR and a brightness sensor, used to identify the test scene type.

[0070] The scene recognition submodule works as follows: The miniature lidar (TF-Luna, ranging accuracy ±1cm) is installed below the rearview mirrors on both sides of the vehicle. It scans the distance to obstacles 5 times per second. When the distance on both sides is less than 1m (e.g., 0.8m on the left and 0.7m on the right), it is judged as a "narrow scene".

[0071] The brightness sensor detects an ambient illuminance of 8 lux (<10 lux), which is then classified as a "night scene".

[0072] When the lidar detects obstacles on either side of the test vehicle at a distance less than a preset distance, the clarity priority mode is triggered, and the W value is increased. m Lower W t ; When the lidar detects obstacles on either side of the test vehicle at a distance greater than or equal to a preset distance, the display time priority mode is triggered, and W is increased. t Lower W m ; If the brightness sensor detects that the ambient illuminance is less than the preset illuminance threshold, increase W. e .

[0073] In this embodiment, the dynamic weight adjustment is as follows: "Clarity priority" is triggered in narrow scenes: W m Adjusted from 0.3 to 0.6, W t It decreased from 0.3 to 0.2; Nighttime scenes trigger "color priority": W e Adjusted from 0.2 to 0.5; Adjusted weight: W t =0.2, W i =0.2, W m =0.6, We =0.5; then perform normalization to ensure the sum is 1, for example, scaled to W. t =0.13, W i =0.13, W m =0.4, W e =0.34; Recalculate SRC.

[0074] In this embodiment, weights are dynamically adjusted through scene recognition to ensure a deep match between risk assessment and scene safety requirements: for example, in a narrow parking space scenario, the driver needs to clearly identify the edge lines (depending on sharpness), and in this case, W m Increase the risk of insufficient magnification (e.g., when M=0.4, SRC increases by 0.2); in night scenes, W e The risk of color deviation that highlights red obstacles is improved (e.g., SRC increases by 0.3 when ΔQE=6). This adaptability solves the problem of evaluation distortion in multiple scenarios with fixed weights (e.g., overemphasis on clarity in open scenes), and greatly improves the scenario fit of risk assessment.

[0075] Furthermore, the method may also include: By connecting to the vehicle's OBD interface through the vehicle bus deep analysis module, real-time data from the vehicle's ECU can be read.

[0076] In this embodiment, the preset vehicle bus deep analysis module is connected to the vehicle ECU through the OBD-II interface (supporting CAN2.0B protocol) and reads data 3 times per second: for example, the camera power supply voltage = 10.2V (standard 12V±0.5V), the data transmission rate = 80Mbps (standard ≥100Mbps), and the vehicle CPU load = 95% (standard ≤70%).

[0077] Based on the reaction time, distortion rate, MTF value, ΔE color difference, and real-time data read from the ECU, cross-validation is performed using a preset fault knowledge graph; the fault knowledge graph includes abnormal indicator nodes, component fault nodes, and system-related nodes.

[0078] The fault source conclusion is output through cross-validation; the conclusion is used to locate the root cause of the fault in the reversing camera system.

[0079] In this embodiment, the fault knowledge graph and cross-validation process are as follows: The knowledge graph contains nodes: abnormal indicators (ΔT=120ms>100ms), component failure (insufficient power supply to the camera), and system correlation (low SOH of the battery).

[0080] Cross-validation logic: 1. Abnormal indicators: ΔT exceeds the standard + low transmission rate + high CPU load.

[0081] 2. ECU data: Low power supply voltage (10.2V) → associated with "camera startup delay".

[0082] 3. Matching knowledge graph rules: "Low power supply + low transmission rate → battery depletion" and "High CPU load → image processing frequency reduction".

[0083] The conclusion is: "Insufficient battery health (SOH) leads to low power supply voltage and camera startup delay; overload of the vehicle's CPU (possibly due to too many background programs) causes image processing delay. It is recommended to check the battery and optimize the vehicle's infotainment system."

[0084] Compared to the traditional "single indicator → vague prompt" (e.g., ΔT exceeding the standard only prompts "system delay"), the method in this embodiment achieves a triple breakthrough through "multiple indicators + ECU data + knowledge graph": First, the positioning accuracy is greatly improved (e.g., distinguishing between "camera failure" and "power supply problem"); second, it covers complex faults (multiple indicator anomalies), solving the problem of inefficiency in manual troubleshooting; and third, the conclusions are directly related to maintenance measures (e.g., "testing battery SOH"), saving troubleshooting time for after-sales service and upgrading the testing tool from "performance testing" to "intelligent diagnostic terminal".

[0085] Furthermore, the real-time data includes at least one of the following: camera power supply voltage, reversing image data transmission rate, vehicle CPU load, image processing chip parameters, and camera installation angle calibration parameters.

[0086] In this embodiment, the specific dimensions and functions of the ECU real-time data are defined as follows: Camera power supply voltage: Normal 12V±0.5V. A voltage below 11.5V may cause the sensor to start up slowly (e.g., at 10.2V, the start-up delay increases by 30ms), which explains the excessive ΔT. Data transmission rate: Normal ≥100Mbps, below 80Mbps there is image data transmission delay (e.g., at 80Mbps the delay increases by 20ms), related to ΔT and MTF values ​​(excessive transmission compression leads to a decrease in clarity). Vehicle infotainment system CPU load: When displaying images, it should be ≤70%. Exceeding 90% will cause the image processing algorithm to be downclocked (e.g., from 60fps to 30fps), which directly affects the distortion correction accuracy (D increases) and color processing (ΔQE increases). Image processing chip parameters: If the firmware version is too low, it may cause MTF calculation deviation, which is used to locate faults such as "insufficient software optimization"; Camera installation angle: A horizontal offset greater than 1° will cause an increase in distortion rate D, which is used to distinguish between "hardware installation problems" and "sensor failure".

[0087] By clarifying the specific dimensions and correlation logic of ECU data, the problem of "incomplete data leading to inference interruption" in fault tracing is solved: for example, when only ΔT is known to be excessive, "low power supply voltage" can be combined to rule out "camera failure" and narrow the scope of investigation; at the same time, the direct correlation between data and image indicators (such as CPU load → ΔQE) makes the inference chain more rigorous, avoids generalized conclusions (such as "system abnormality"), significantly shortens the average time for fault location, and significantly improves the engineering application value of the test.

[0088] Furthermore, the reverse gear triggering action of the test vehicle is detected by a microswitch installed at the gear shift lever.

[0089] Microswitch selection and installation: Select a microswitch with a stroke of 0.1mm and a contact resistance of less than 50mΩ to ensure that it can be triggered by a slight lever movement; the bracket is made of aluminum alloy and the X / Y / Z axis position can be adjusted by a knob (adjustment accuracy 0.05mm). When installing, make the switch contact parallel to the side of the lever with a gap of 0.2mm (to avoid false triggering or trigger delay).

[0090] Trigger signal transmission and processing: After the switch output signal is filtered by an RC filter circuit (100Ω resistor + 100nF capacitor) to remove high-frequency noise, it is connected to the GPIO interrupt pin of the main control module (trigger mode: falling edge trigger). The module uses a microsecond-level timer (Sys Tick timer, accuracy 1μs) in the interrupt service routine to record the first moment to avoid the impact of main program delay (e.g., interrupt response time ≤ 5μs).

[0091] Compared with other triggering methods: Compared with CAN bus triggering (which depends on the vehicle protocol being open), microswitches are compatible with most vehicle models (including older vehicles without CAN access); compared with Hall sensors (which depend on the magnet built into the gear lever), they are suitable for mechanical gear levers without magnets and have better compatibility.

[0092] The method in this embodiment solves the shortcomings of traditional manual triggering (relying on human eyes to observe the lever action for timing, with an error ≥150ms) and non-contact triggering (poor compatibility and susceptibility to interference): the mechanical response time of the micro switch is ≤1ms, and with the help of a microsecond-level timer, the first-moment capture error is ≤5ms (far lower than the 150ms of manual triggering); the adjustable bracket ensures compatibility with the gear layout of more than 95% of car models, and the installation time is greatly reduced; at the same time, hardware triggering avoids the delay of software signals (such as the 20ms delay of CAN bus transmission), providing a "zero subjective error" time starting point for reaction time calculation, and reducing the repeatability of test data (deviation of multiple tests) from ±50ms to ±2ms.

[0093] In one exemplary embodiment, the above method can be applied to the automotive field, including vehicle models with and without a gear lever, and is specifically implemented as follows: For vehicles with gear levers (including manual and automatic mechanical gear levers), the capture of the reverse gear trigger moment can utilize a combination of a highly sensitive microswitch and an adjustable bracket. Based on the gear lever's installation angle and travel range, the bracket's lateral / vertical extension and 360° rotation capabilities precisely fix the microswitch at a key position along the gear lever's movement trajectory. The gap between the switch trigger end and the gear lever is adjusted to ≤0.3mm to ensure that the mechanical action of shifting the gear lever to reverse instantly triggers the switch to output a low-level start signal. For some automatic transmission vehicles with gear levers that have a locking mechanism, the locking restriction can be temporarily released before testing (or the locking mechanism's action logic can be adapted to adjust the switch trigger timing) to avoid trigger delays caused by the locking action, ensuring a first-moment capture error of ≤1ms. Simultaneously, the brightness detection module and benchmark calibration module can be deployed according to a common process. By focusing the lens on the center area of ​​the vehicle's screen and dynamically determining the brightness threshold based on ambient light, the accuracy of the response time calculation is ensured.

[0094] For vehicles without a gear lever (such as new energy vehicles using button-type, rotary, or touch-sensitive electronic gear levers), a "non-contact triggering scheme" is used to replace the microswitch, ensuring accurate capture of the reverse gear trigger moment. Specifically, a vehicle bus deep analysis module can be connected to the OBD interface to read the signal data corresponding to the reverse gear state in the CAN bus (e.g., in the data frame with CAN ID 0x18F00500, the reverse gear activation state is specifically identified). When the signal is detected to switch from "non-reverse" to "reverse," this moment is recorded as the first trigger moment. For some vehicles with restricted CAN bus access, a miniature Hall sensor can be integrated inside the button / knob of the electronic gear lever. The trigger signal is generated by the displacement change of the internal magnet during gear lever operation, or by collecting the electrical signal of the gear lever operation (e.g., voltage jump when a button is pressed) as the initial triggering basis. This type of non-contact solution has a response time ≤0.5ms, comparable to the triggering accuracy of a microswitch on a mechanical gear lever, and avoids the wear and tear on the electronic gear lever caused by mechanical contact, making it suitable for testing requirements of 100% gear lever-less vehicles.

[0095] Furthermore, regardless of whether a vehicle model has a gear lever, subsequent stages such as image quality detection, safety risk assessment, and fault tracing remain consistently compatible. For example, the image quality detection submodule aligns with the vehicle's screen via a shared adjustable bracket, unaffected by the gear lever type; the scene recognition submodule's miniature LiDAR and brightness sensor are installed at the front and rear of the vehicle according to a unified standard, accurately identifying scenarios such as narrow / open / nighttime conditions and dynamically adjusting weights; the vehicle bus deep analysis module reads ECU data (camera power supply voltage, vehicle CPU load, etc.) through the OBD interface, which also has vehicle-wide compatibility, and combined with a fault knowledge graph, it can pinpoint the root cause of faults in different gear-type vehicles. This adaptation design requires no customized development for specific gear types, deployment time is ≤2 minutes, and test errors are consistently within ±2ms. It meets the high-precision requirements of R&D scenarios and also adapts to the efficient testing needs of various scenarios such as production line sampling and after-sales maintenance, achieving standardized and highly reliable testing of reversing image performance across all vehicle models.

[0096] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0097] An embodiment of the present invention also provides a reversing camera performance testing device, the device comprising: The first moment acquisition module is used to acquire the first moment corresponding to the reverse gear trigger action of the test vehicle.

[0098] The screen brightness acquisition module is used to acquire the brightness of the vehicle's infotainment screen.

[0099] The second moment acquisition module is used to determine the moment when the brightness of the vehicle screen is greater than or equal to a preset brightness detection benchmark threshold as the second moment; the preset brightness detection benchmark threshold is determined by the ambient light intensity and the preset mapping relationship between ambient light intensity and screen display brightness.

[0100] The reaction time determination module is used to determine the time difference between the first moment and the second moment as the reaction time of the test vehicle's reversing image; the reaction time is used to evaluate the performance of the test vehicle's reversing image.

[0101] Furthermore, the device also includes: An ambient light intensity acquisition module is used to acquire several sets of ambient light intensity samples and the corresponding actual brightness values ​​of the vehicle screen in the reversing image display state; the ambient light intensity samples cover the light range of 0-10000 lux.

[0102] The mapping function fitting module is used to obtain a mapping function between ambient light intensity and screen display brightness by fitting the several sets of ambient light intensity samples and actual brightness values ​​through linear regression or neural network algorithms; the mapping function is used to characterize the screen brightness benchmark when the reversing image is clearly displayed under different ambient light conditions.

[0103] Furthermore, the second-moment acquisition module includes: The ambient light intensity detection unit is used to detect the rate of change of ambient light intensity in the environment where the test vehicle is located in real time.

[0104] The brightness detection reference threshold determination unit is used to redetermine the brightness detection reference threshold based on the current ambient light intensity and the mapping relationship between ambient light intensity and screen display brightness when the rate of change is greater than or equal to a preset ambient light intensity change rate threshold.

[0105] The threshold replacement unit is used to replace the original brightness detection benchmark threshold with a recalculated brightness detection benchmark threshold for subsequent determination at the second time step.

[0106] Furthermore, the device also includes: The parameter acquisition module is used to obtain the distortion rate, MTF value, and ΔE color difference of the reversing image displayed on the vehicle's infotainment screen.

[0107] The safety risk coefficient determination module is used to determine the safety risk coefficient SRC of the test vehicle based on the reaction time ΔT, distortion rate D, MTF value M, and chromatic difference ΔQE of the test vehicle's reversing image. The SRC satisfies the following relationship: SRC=(ΔT / ΔT0)×W t +(D / D0)×W i +(1-M / M0)×W m +(ΔQE / ΔE0)×W e ; Wherein, ΔT0, D0, M0, and ΔE0 are the basic thresholds corresponding to ΔT, D, M, and ΔQE, respectively; W t W i W m and W e The dynamic weights are ΔT, D, M, and ΔQE, respectively.

[0108] The safety risk level determination module is used to determine the safety risk level of the test vehicle based on the SRC.

[0109] Furthermore, the device also includes: The first adjustment module is used to trigger the clarity priority mode and increase W when the lidar detects obstacles on both sides of the test vehicle at a distance less than a preset distance. mLower W t .

[0110] The second adjustment module is used to trigger the display time priority mode and increase W when the lidar detects obstacles on both sides of the test vehicle at a distance greater than or equal to a preset distance. t Lower W m .

[0111] The third adjustment module is used to increase W when the brightness sensor detects that the ambient illuminance is less than a preset illuminance threshold. e .

[0112] Furthermore, the device also includes: The real-time data reading module is used to connect to the vehicle's OBD interface via the vehicle bus deep analysis module to read real-time data from the vehicle's ECU.

[0113] The cross-validation module is used to perform cross-validation based on the reaction time, distortion rate, MTF value, ΔE color difference and read ECU real-time data, combined with a preset fault knowledge graph; the fault knowledge graph includes abnormal indicator nodes, component fault nodes and system-related nodes.

[0114] The fault tracing conclusion output module is used to output fault tracing conclusions through cross-validation; the conclusions are used to locate the root cause of the fault in the reversing camera system.

[0115] Embodiments of the present invention also provide an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0116] The electronic device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.

[0117] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and a bus connecting different system components (including memory and processor).

[0118] The memory stores program code that can be executed by the processor, causing the processor to perform the steps in the various embodiments described in this specification.

[0119] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0120] The memory may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0121] A bus can represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus structures.

[0122] Electronic devices can also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable user interaction with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be achieved through input / output (I / O) interfaces. Furthermore, electronic devices can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapters. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0123] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0124] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0125] While specific embodiments of the invention have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention.

Claims

1. A method for testing the performance of a reversing camera, characterized in that, include: Obtain the first moment corresponding to the reverse gear trigger action of the test vehicle; Obtain the brightness of the vehicle's infotainment screen; The moment when the brightness of the vehicle's infotainment screen is greater than or equal to a preset brightness detection threshold is defined as the second moment. The preset brightness detection benchmark threshold is determined by the ambient light intensity and the preset mapping relationship between ambient light intensity and screen display brightness; The time difference between the first moment and the second moment is determined as the reaction time of the reversing image of the test vehicle; the reaction time is used to evaluate the performance of the reversing image of the test vehicle.

2. The reversing image performance testing method according to claim 1, characterized in that, The preset mapping relationship between ambient light intensity and screen display brightness is established through the following steps: Several sets of ambient light intensity samples and the corresponding actual brightness values ​​of the vehicle's infotainment screen in the reversing image display state were collected; the ambient light intensity samples covered the light range of 0-10000 lux. Based on the aforementioned sets of ambient light intensity samples and actual brightness values, a mapping function between ambient light intensity and screen display brightness is obtained through linear regression or neural network algorithms; the mapping function is used to characterize the screen brightness benchmark when the reversing image is clearly displayed under different ambient light conditions.

3. The method for testing the performance of a reversing camera according to claim 1, characterized in that, The preset brightness detection threshold is determined through the following steps: Real-time detection of the rate of change in ambient light intensity in the environment where the test vehicle is located; If the rate of change is greater than or equal to a preset threshold for the rate of change of ambient light intensity, the brightness detection benchmark threshold is re-determined based on the current ambient light intensity and the mapping relationship between ambient light intensity and screen display brightness. The recalculated brightness detection benchmark threshold replaces the original brightness detection benchmark threshold and is used for subsequent determination at the second time step.

4. The reversing camera performance testing method according to claim 1, characterized in that, The method further includes: Obtain the distortion rate, MTF value, and ΔE color difference of the reversing image displayed on the vehicle's infotainment screen; Based on the reaction time ΔT, distortion rate D, MTF value M, and chromatic difference ΔQE of the test vehicle's reversing image, the corresponding safety risk coefficient SRC of the test vehicle is determined. SRC satisfies the following relationship: SRC=(ΔT / ΔT0)×W t +(D / D0)×W i +(1-M / M0)×W m +(ΔQE / ΔE0)×W e ; Wherein, ΔT0, D0, M0, and ΔE0 are the basic thresholds corresponding to ΔT, D, M, and ΔQE, respectively; W t W i W m and W e The dynamic weights corresponding to ΔT, D, M, and ΔQE are, in order. Based on the SRC, determine the corresponding safety risk level of the test vehicle.

5. The reversing camera performance testing method according to claim 4, characterized in that, The adjustment of the dynamic weights is achieved through a scene recognition submodule; the scene recognition submodule includes a miniature LiDAR and a brightness sensor, used to identify the test scene type; When the lidar detects obstacles on either side of the test vehicle at a distance less than a preset distance, the clarity priority mode is triggered, and the W value is increased. m Lower W t ; When the lidar detects obstacles on either side of the test vehicle at a distance greater than or equal to a preset distance, the display time priority mode is triggered, and W is increased. t Lower W m ; If the brightness sensor detects that the ambient illuminance is less than the preset illuminance threshold, increase W. e .

6. The reversing camera performance testing method according to claim 5, characterized in that, Also includes: The vehicle bus deep analysis module connects to the vehicle's OBD interface to read real-time data from the vehicle's ECU. Based on the reaction time, distortion rate, MTF value, ΔE color difference, and real-time data read from the ECU, cross-validation is performed using a preset fault knowledge graph; the fault knowledge graph includes abnormal indicator nodes, component fault nodes, and system-related nodes. The fault source conclusion is output through cross-validation; the conclusion is used to locate the root cause of the fault in the reversing camera system.

7. The reversing image performance testing method according to claim 6, characterized in that, The real-time data includes at least one of the following: camera power supply voltage, reversing image data transmission rate, vehicle CPU load, image processing chip parameters, and camera installation angle calibration parameters.

8. The method for testing the performance of a reversing camera according to claim 1, characterized in that, The reverse gear triggering action of the test vehicle is detected by a microswitch installed at the gear shift lever.

9. A reversing camera performance testing device, characterized in that, The device includes: The first moment acquisition module is used to acquire the first moment corresponding to the reverse gear trigger action of the test vehicle. The screen brightness acquisition module is used to acquire the brightness of the vehicle's infotainment screen. The second moment acquisition module is used to determine the moment when the brightness of the vehicle screen is greater than or equal to a preset brightness detection benchmark threshold as the second moment; the preset brightness detection benchmark threshold is determined by the ambient light intensity and the preset mapping relationship between the ambient light intensity and the screen display brightness. The reaction time determination module is used to determine the time difference between the first moment and the second moment as the reaction time of the test vehicle's reversing image; the reaction time is used to evaluate the performance of the test vehicle's reversing image.

10. An electronic device, characterized in that, It includes a processor and the reversing image performance testing device as described in claim 8, or the processor performs the method as described in any one of claims 1-8.

Images