Automatic driving safety control method and system based on environmental perception

Abstract

The invention is suitable for the technical field of automatic driving environment perception and safety control, and provides an automatic driving safety control method and system based on environment perception, and the method comprises the steps: analyzing a historical environment perception data set to screen out a plurality of reference samples matched with the current environment state characteristics, performing time sequence analysis on the reference sample to determine a visual identification result stability index when the vehicle passes through the illumination interference area in history and a polarization characteristic attenuation index of a corresponding building reflection structure; and analyzing the time change trend of the visual identification result stability index and the polarization characteristic attenuation index based on the multi-time-sequence reference sample so as to judge whether the visual identification result stability index and the polarization characteristic attenuation index present a preset coupling relationship. According to the method, the time sequence attenuation rule of the polarization characteristic of the building reflection structure is considered for the first time, and the influence of polarization change on the visual identification performance is quantified by comparing polarization characteristic attenuation indexes of different time sequences, so that predictive correction on the weight is realized before entering an illumination interference area.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automatic driving environment perception and safety control, and particularly relates to an automatic driving safety control method and system based on environment perception. BACKGROUND

[0002] At present, automatic driving technology generally relies on multi-sensor fusion to realize comprehensive perception of the environment around the vehicle, among which the visual sensor plays a key role in target identification, lane keeping and obstacle detection. In order to ensure the reliability of multi-source information fusion, the vehicle-mounted perception system usually generates a visual fusion confidence weight value according to the real-time detected light intensity, image contrast, exposure information and recognition confidence, etc., to balance the influence weight of visual data and other sensor data such as radar and lidar. The existing algorithm mainly adjusts adaptively according to light intensity, shadow distribution and scene brightness change, and performs stably in most ordinary environments. However, in building environments with high reflectivity or strong polarization characteristics, such as glass curtain wall facades, mirror decorative outer walls and other areas, the visual sensor is easily disturbed by the polarization characteristics of reflected light, resulting in image information distortion and recognition performance degradation.

[0003] In actual application, when the vehicle drives to the same building reflection area for multiple times, the vehicle-mounted perception control system usually generates a visual fusion confidence weight value for multi-sensor fusion in advance according to the real-time detected light parameters before entering the light interference area. Since the external light conditions at this time are basically the same as when the vehicle first enters, the system usually considers that the environmental characteristics have not changed, thereby generating a visual fusion confidence weight value similar or the same as when the vehicle first enters. However, the polarization characteristics of the building reflection structure will gradually deteriorate over time, for example, due to surface dust adhesion, coating aging or humidity change, causing changes in the polarization ratio and polarization angle of reflected light. The existing system does not have the ability to detect and model such polarization characteristic attenuation, so it cannot identify the correlation between the decline in visual recognition performance and the change in polarization characteristics, causing unbalanced weight distribution in the visual fusion stage, and thus reducing the stability and accuracy of target identification. SUMMARY

[0004] The present application aims to provide an automatic driving safety control method and system based on environment perception, which aims to solve the problems raised in the background art.

[0005] The present application is implemented as follows: an automatic driving safety control method based on environment perception, the method comprising: When the vehicle is about to enter a light interference area formed by a specific building reflection structure in a high-frequency driving path, an initial visual fusion confidence weight value for multi-sensor fusion is extracted, and a historical environment perception data set of the vehicle on the high-frequency driving path is obtained; The historical environment perception dataset is analyzed to screen out a plurality of reference samples matched with the current environment state feature, and the reference samples are analyzed in time sequence to determine the visual recognition result stability index of the vehicle when passing through the light interference area and the polarization feature attenuation index of the corresponding building reflection structure; Based on the multi-time sequence reference sample analysis, the time variation trend of the visual recognition result stability index and the polarization feature attenuation index is analyzed to determine whether they present a preset coupling relationship; If it is determined that the preset coupling relationship exists, the current polarization feature attenuation index of the building reflection structure is obtained, which is differentially analyzed with the corresponding polarization feature attenuation index of the vehicle when the initial visual fusion confidence weight value is first formulated, a correction factor is generated, and the initial visual fusion confidence weight value is dynamically corrected by using the correction factor.

[0006] As a further limitation of the technical scheme of the embodiment of the application, the specific building reflection structure is a glass curtain wall facade with a high reflectivity coating or a polarization layer on the surface.

[0007] As a further limitation of the technical scheme of the embodiment of the application, the current environment state feature matching refers to the consistency between the reference sample and the light distribution, the incident angle, the environment brightness and the reflection direction of the current environment of the vehicle being higher than a preset threshold.

[0008] As a further limitation of the technical scheme of the embodiment of the application, the historical environment perception dataset includes multi-source perception data collected by the vehicle side and reflection feature data obtained by the building reflection structure side.

[0009] As a further limitation of the technical scheme of the embodiment of the application, the determination process of the visual recognition result stability index includes: The multi-source perception data collected by the vehicle side is analyzed to determine the recognition confidence fluctuation amplitude, the recognition result consistency and the false detection rate of the vehicle visual recognition model in the reference sample when passing through the light interference area, and the recognition confidence fluctuation amplitude, the recognition result consistency and the false detection rate are integrated to generate a comprehensive evaluation value, which is used as the visual recognition result stability index.

[0010] As a further limitation of the technical scheme of the embodiment of the application, the calculation and acquisition process of the polarization feature attenuation index includes: The reflection feature data obtained by the building reflection structure side is analyzed to extract the reflection light polarization rate and polarization angle information corresponding to the reference sample, and based on the reflection light polarization rate and polarization angle information relative to the reflection light polarization rate and polarization angle information when the vehicle first formulates the initial visual fusion confidence weight value, the polarization rate attenuation amplitude and the polarization angle offset are generated in turn, and the polarization feature attenuation index is generated by integrating the above results.

[0011] As a further limitation of the technical scheme of the embodiment of the application, the preset coupling relationship refers to: When the change trend of the visual recognition result stability index gradually decreases, the change trend of the polarization feature attenuation index gradually increases, and the correlation coefficient between the change rate or change amplitude of the two is higher than the preset threshold, it is determined that there is a coupling relationship between the decline of the visual recognition performance and the polarization feature attenuation.

[0012] As a further limitation of the technical scheme of the embodiment of the application, if it is determined that there is a preset coupling relationship, the polarization feature attenuation index of the current building reflection structure is obtained, and difference analysis is performed on the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value, a correction factor is generated, and the initial visual fusion confidence weight value is dynamically corrected using the correction factor. The steps include: Obtain the polarization feature attenuation index of the current building reflection structure, and obtain the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value based on the historical environment perception data set; Difference analysis is performed on the two polarization feature attenuation indexes to generate a correction factor, and the initial visual fusion confidence weight value is dynamically corrected using the correction factor; The corrected visual fusion confidence weight value is obtained, and the vehicle passes through the current light interference area based on the corrected visual fusion confidence weight value.

[0013] As a further limitation of the technical scheme of the embodiment of the application, when the initial visual fusion confidence weight value is corrected, a preset correction function is used, and the correction function is: ; Wherein, refers to the corrected visual fusion confidence weight value, refers to the initial visual fusion confidence weight value, refers to the upper limit of the visual fusion confidence weight value, refers to the polarization feature attenuation index of the current building reflection structure, refers to the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value, refers to the correction factor, refers to the control correction amplitude coefficient.

[0014] An automatic driving safety control system based on environment perception, the system comprises: A weight extraction module is used to extract an initial visual fusion confidence weight value for multi-sensor fusion when the vehicle is about to enter a light interference area formed by a specific building reflection structure in a high-frequency driving path, and to obtain a historical environment perception data set of the vehicle on the high-frequency driving path. a sample analysis module, configured to analyze a historical environment perception dataset to filter out a plurality of reference samples matching a current environment state feature, and to perform time series analysis on the reference samples to determine a visual recognition result stability index of the vehicle when passing through a light interference area in history and a polarization feature attenuation index of a corresponding building reflection structure; a coupling determination module, configured to analyze time variation trends of the visual recognition result stability index and the polarization feature attenuation index based on the multi-time series reference samples, to determine whether the two trends present a preset coupling relationship; a dynamic correction module, configured to, if it is determined that the preset coupling relationship exists, obtain a current polarization feature attenuation index of the building reflection structure, perform difference analysis on the current polarization feature attenuation index and a corresponding polarization feature attenuation index when the vehicle first formulates the initial visual fusion confidence weight value, generate a correction factor, and perform dynamic correction on the initial visual fusion confidence weight value by using the correction factor.

[0015] Compared with the prior art, the present application has the following beneficial effects: The present application realizes dynamic adaptive correction of the visual fusion confidence weight value by introducing a coupling analysis mechanism between the polarization feature attenuation index and the visual recognition result stability index. Unlike the prior art which only sets the weight based on the light intensity or brightness parameter, the present application first considers the time series attenuation law of the polarization characteristics of the building reflection structure, compares the polarization feature attenuation indexes at different times, quantifies the influence of polarization change on the visual recognition performance, and thus realizes predictive correction of the weight before entering the light interference area.

[0016] The method not only can accurately identify the recognition performance decline caused by the deterioration of the polarization characteristics, but also can realize dynamic balance of the visual channel weight in multi-sensor fusion, greatly improves the perception stability and driving safety of the vehicle in the high reflection and complex light environment, and has significant engineering application value and innovative significance. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 a flowchart of the method provided by the embodiment of the present application; Figure 2 a flowchart of the correction of the initial visual fusion confidence weight value in the method provided by the embodiment of the present application; Figure 3 an application architecture diagram of the system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0019] Figure 1 A flow chart of the method provided by the embodiment of the application is shown.

[0020] Specifically, an automatic driving safety control method based on environment perception comprises the following steps: Step S100, when a vehicle is about to enter a light interference area formed by a specific building reflection structure in a high-frequency driving path, an initial visual fusion confidence weight value for multi-sensor fusion is extracted, and a historical environment perception data set of the vehicle on the high-frequency driving path is obtained. The specific building reflection structure is a glass curtain wall facade with a high reflectivity coating or a polarizing layer on the surface.

[0021] The historical environment perception data set comprises multi-source perception data collected by the vehicle and reflection feature data obtained by the building reflection structure.

[0022] In the embodiment of the application, the vehicle refers to an intelligent vehicle with an automatic driving function and integrated with a vehicle visual recognition model. The vehicle can obtain environment information through a visual perception system, a laser radar, a millimeter wave radar, an infrared sensor and other types of sensors, and realize functions such as automatic navigation, obstacle recognition, path planning and environment understanding based on multi-source perception results. The visual recognition model of the vehicle can perceive and recognize environmental factors such as external light, reflection and occlusion, thereby providing basic data for the generation of the visual fusion confidence weight value.

[0023] The high-frequency driving path refers to a route repeatedly driven by the vehicle in daily operation, such as a city commuting trunk road, a fixed regional connection route or a logistics distribution route. In such a path, the vehicle can accumulate rich historical environment perception data during long-term operation, so that the system can analyze the trend and adaptively correct the light conditions, building reflection features and traffic states of the same area, thereby improving the environmental adaptability of automatic driving.

[0024] The specific building reflection structure is a building facade located on one side of the road or in the adjacent area of the driving path, which has a glass curtain wall structure with a high reflectivity coating or a polarizing layer on the surface. Such structures usually exist in large quantities on the outer facades of city high-rise buildings, and the reflected light not only has high brightness, but also has obvious polarization characteristics. When sunlight or other strong light sources shine on such building surfaces, directional and polarized reflected light distribution is formed, which may form local overexposure, reflected glare or visual deviation in the perception range of the vehicle camera system, thereby affecting the visual recognition performance of the automatic driving system.

[0025] The light interference area refers to a specific spatial area formed by the above-mentioned building reflection structure, in which the light distribution is strongly affected by reflection, and the light intensity, incident angle and polarization state have obvious differences from the surrounding environment. When the vehicle enters this area, the light signal received by its visual sensor contains strong reflection interference components, which can easily lead to a decrease in the stability of visual recognition results or misjudgment of visual fusion.

[0026] The visual fusion confidence weight value is a weighting coefficient set by the vehicle perception system in the multi-sensor fusion process to represent the reliability of the visual recognition result. This weight value is calculated by the vehicle-mounted perception control system based on environmental light intensity, image contrast, recognition confidence distribution, sensor consistency and other factors. It is a relatively mature weight adjustment method in existing automatic driving technology.

[0027] In a popular understanding, this weight value is equivalent to a quantitative indicator of the degree to which the system trusts the camera. When the environmental light is stable, the reflection interference is small, and the image quality is clear, the system will give a high confidence weight to the visual recognition, making the visual sensor dominant in the fusion decision. When the light is abnormal, the reflection is strong, or the recognition fluctuation is large, the system will reduce the weight of the visual channel and increase the dependence on radar, infrared and other sensor data, thereby ensuring the stability and safety of the overall perception result.

[0028] The historical environmental perception data set includes multi-source perception data collected by the vehicle and reflection feature data obtained by the building reflection structure. The multi-source perception data collected by the vehicle includes vehicle camera images, radar echo signals, environmental light intensity parameters, sensor synchronization time stamps and recognition confidence, etc., which are used to reflect the perception performance of the vehicle in the historical driving process. The reflection feature data obtained by the building reflection structure includes reflection light polarization rate, polarization angle, reflection intensity distribution and light incident angle, etc. This kind of data is obtained through external monitoring devices based on environmental perception or through lateral detection by the vehicle perception system, and is used to reflect the physical property changes of the reflected light of the building surface.

[0029] The core research point of the present application is that the existing automatic driving system mainly sets the weight according to the static light intensity, image contrast and recognition confidence when generating the visual fusion confidence weight value, without considering the dynamic attenuation effect of the polarization characteristics of the building reflection structure. When the vehicle first passes through the light interference area formed by the specific building reflection structure, the system can generate an adaptive visual fusion confidence weight value according to the light and reflection characteristics at that time. However, when the vehicle subsequently drives to the same area multiple times, the vehicle-mounted perception control system will generally automatically generate a visual fusion confidence weight value for multi-sensor fusion according to the real-time detected light parameters before entering the light interference area. Since the external light conditions at this time are basically the same as when the vehicle first enters, the system generally considers that the environmental characteristics have not changed, thereby generating a visual fusion confidence weight value that is approximately or the same as when the vehicle first enters.

[0030] In fact, the polarization characteristics of the building reflection structure will gradually decay over time and with the accumulation of surface attachments, and the polarization ratio and polarization angle of the reflected light will shift, causing the stability of the visual recognition result to decrease significantly when the vehicle uses the uncorrected weight value. The existing technology does not consider the dynamic degradation of polarization characteristics, nor can it extract the influence of polarization changes on visual fusion performance from historical environmental perception data, resulting in the system being unable to reasonably adjust the weight under seemingly consistent light conditions.

[0031] Further, the automatic driving safety control method based on environmental perception further comprises the following steps:

[0032] Step S200, analyze the historical environmental perception data set to filter out a plurality of reference samples matching the current environmental state characteristics, and perform time series analysis on the reference samples to determine the visual recognition result stability index of the vehicle when passing through the light interference area and the polarization characteristic decay index of the corresponding building reflection structure.

[0033] The current environmental state characteristic matching refers to the consistency between the reference sample and the light distribution, incident angle, environmental brightness and reflection direction of the current environment of the vehicle being higher than a preset threshold.

[0034] The determination process of the visual recognition result stability index includes: analyzing the multi-source perception data collected by the vehicle side, determining the recognition confidence fluctuation amplitude, recognition result consistency and false detection rate of the vehicle visual recognition model in the reference sample when passing through the light interference area, and generating a comprehensive evaluation value by comprehensively generating the recognition confidence fluctuation amplitude, recognition result consistency and false detection rate, and taking the comprehensive evaluation value as the visual recognition result stability index.

[0035] The calculation process of the polarization feature attenuation index comprises: analyzing the reflection feature data obtained by the building reflection structure side, extracting the reflection light polarization ratio and polarization angle information corresponding to the reference sample, and based on the reflection light polarization ratio and polarization angle information relative to the initial visual fusion confidence weight value when the vehicle is first formulated, generating polarization ratio attenuation amplitude and polarization angle offset in turn, and generating the polarization feature attenuation index by comprehensively generating the above results.

[0036] In the embodiment of the present application, in order to accurately evaluate the change trend of the visual recognition stability of the vehicle in the light interference area and the environmental polarization characteristics, it is necessary to analyze the historical environmental perception data set to screen out a number of reference samples highly matched with the current environmental state characteristics. The reason for this screening is that there may be slight differences in external environmental parameters (such as solar elevation angle, cloud distribution, aerosol concentration, etc.) when the vehicle passes through the same section at different times, and these differences will significantly affect the polarization characteristics of the reflected light and the visual recognition performance. If strict screening is not performed, the analysis of the visual recognition result stability index and the polarization feature attenuation index will be deviated, thereby affecting the accuracy of the correction factor.

[0037] Therefore, the present application constructs an environmental state feature matching model to perform multi-dimensional similarity calculation on each sample in the historical environmental perception data set, and screens out a sample set highly consistent with the current environmental state of the vehicle. The current environmental state characteristics not only include basic parameters such as light distribution, incident angle, environmental brightness, and reflection direction, but also can further include environmental color temperature, weather type, solar radiation intensity, geographical azimuth angle corresponding to the driving time, suspended particle concentration in the air, etc. By introducing these additional characteristic parameters, the comparability of the selected samples in the light environment and the reflection condition can be effectively guaranteed, thereby ensuring the stability and reliability of the time series analysis results.

[0038] In the process of determining the visual recognition result stability index, the system calls the vehicle multi-source perception results recorded in the historical running data for each reference sample meeting the screening condition, and restores and analyzes the recognition performance of the vehicle visual recognition model when passing through the light interference area. Specifically, when the vehicle passes through the light interference area, the visual fusion confidence weight value is usually generated according to the current environmental light state before entering the area, and the actual application effect of the weight value can be inversely evaluated by the historical recognition data. The system uses a multi-source sensor data fusion algorithm to analyze the confidence fluctuation curve of the visual recognition output, combines the consistency test and false rejection rate calculation of the time series recognition results, constructs a comprehensive evaluation model, generates a stability comprehensive evaluation value in a mathematical weighted manner, and takes the value as the visual recognition result stability index. The processing process can be realized by a deep belief network (DBN) model to ensure that the index reflects the true recognition stability performance of the vehicle in the area.

[0039] The polarization feature attenuation index is used to represent the degree of attenuation of the polarization characteristics of the building reflection structure over time, which is one of the important innovations of the present application. The calculation and acquisition process of the index includes: first, analyzing the reflection feature data obtained from the side of the building reflection structure, which can be obtained in real time by a polarization imaging device, a spectral reflection sensor or a polarization camera installed on the roadside or the exterior of the vehicle, for recording the polarization ratio, polarization angle and reflection spectrum distribution of the incident light on the building surface; then extracting the reflection light polarization ratio, polarization angle and polarization spectrum intensity distribution information corresponding to the reference sample, and comparing these data with the reflection features corresponding to the initial visual fusion confidence weight value when the vehicle is first formulated, to calculate the polarization ratio attenuation amplitude and polarization angle shift.

[0040] In addition, in order to improve the stability and representativeness of the index, the present application can further introduce the reflection spectrum width change amount, the polarization light reflectivity ratio and the time series difference parameters of the reflection light intensity as auxiliary dimensions for weighted fusion, to comprehensively generate the polarization feature attenuation index.

[0041] The unique feature of the polarization feature attenuation index is that it not only reflects the physical degradation of the building reflection surface (such as surface dust, coating aging or microscopic scratches), but also quantifies the change trend of the reflection properties over time through the dynamic characteristics of the polarization light, so that the system can identify the subtle degradation of the polarization characteristics under the condition that the macroscopic illumination conditions remain unchanged. Traditional automatic driving vision systems only estimate reflection interference based on brightness or contrast parameters, and cannot identify changes in this "polarization dimension". Therefore, by introducing the polarization feature attenuation index, the system can dynamically adjust the visual fusion confidence weight under stable environmental illumination, realize adaptive compensation for the change of polarization characteristics, and significantly improve the visual fusion accuracy and safety in complex urban reflection environments.

[0042] Further, the automatic driving safety control method based on environmental perception further comprises the following steps: Step S300, based on the multi-time series reference sample analysis of the visual recognition result stability index and the time variation trend of the polarization feature attenuation index, to determine whether they present a preset coupling relationship.

[0043] The preset coupling relationship refers to: when the change trend of the visual recognition result stability index gradually decreases, and the change trend of the polarization feature attenuation index gradually increases, and the correlation coefficient between the change rate or change amplitude of the two is higher than a preset threshold, it is determined that there is a coupling relationship between the decline of visual recognition performance and the attenuation of polarization features.

[0044] In the embodiment of the present application, the core of step S300 is to identify whether there is a significant coupling relationship between the visual recognition result stability index and the polarization feature attenuation index through comparative analysis of multiple time sequence reference samples. Since the external environmental light conditions, incident angles, driving speeds, and sensor working states remain basically unchanged when the vehicle passes through the same building reflection area multiple times, when the stability of the visual recognition result continuously decreases, the main difference factor is usually derived from the change of the polarization characteristics of the building reflection structure. However, in order to avoid misjudgment caused by accidental noise or other unknown factors, the correlation between the two needs to be quantitatively identified and verified through a preset coupling relationship model.

[0045] The preset coupling relationship is an empirical model established based on a large amount of experimental data and deep learning technology. Through statistical analysis of the visual recognition performance under different polarization feature attenuation conditions in the laboratory and actual road environment, a functional mapping relationship between the polarization feature attenuation index and the visual recognition result stability index is constructed. The system uses a multi-time sequence data analysis model (such as a time sequence convolution network TCN or a long short-term memory network LSTM) to perform trend fitting and correlation calculation on the index sequence of the reference samples. When the visual recognition result stability index presents a gradual downward trend, the polarization feature attenuation index presents a gradual upward trend, and the correlation coefficient between the change rates or amplitudes of the two is higher than a preset threshold, it is determined that there is a coupling relationship between the visual recognition performance decline and the polarization feature attenuation.

[0046] Through the establishment and identification of the preset coupling relationship, the system can accurately locate the real reason for the degradation of visual recognition under the condition that the light conditions are stable on the surface, thereby providing a scientific basis for the correction of the subsequent visual fusion confidence weight value.

[0047] Further, the automatic driving safety control method based on environmental perception further comprises the following steps: Step S400, if it is determined that the preset coupling relationship exists, the current polarization feature attenuation index of the building reflection structure is obtained, and difference analysis is performed on the polarization feature attenuation index corresponding to the time when the vehicle first formulates the initial visual fusion confidence weight value, a correction factor is generated, and the initial visual fusion confidence weight value is dynamically corrected using the correction factor.

[0048] Specifically, Figure 2 A flowchart of correcting the initial visual fusion confidence weight value is shown.

[0049] If it is determined that the preset coupling relationship exists, the current polarization feature attenuation index of the building reflection structure is obtained, difference analysis is performed on the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value, a correction factor is generated, and the initial visual fusion confidence weight value is dynamically corrected by using the correction factor, specifically including the following steps: In step S401, the current polarization feature attenuation index of the building reflection structure is obtained, and the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value is obtained based on the historical environment perception data set. In step S402, difference analysis is performed on the above two polarization feature attenuation indexes to generate a correction factor, and the initial visual fusion confidence weight value is dynamically corrected by using the correction factor. In step S403, the corrected visual fusion confidence weight value is obtained, and the vehicle passes through the current light interference area based on the corrected visual fusion confidence weight value.

[0050] When correcting the initial visual fusion confidence weight value, a preset correction function is used, and the correction function is as follows: ; Wherein, refers to the corrected visual fusion confidence weight value, refers to the initial visual fusion confidence weight value, refers to the upper limit of the visual fusion confidence weight value, refers to the current polarization feature attenuation index of the building reflection structure, refers to the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value, refers to the correction factor, refers to the control correction amplitude coefficient.

[0051] In the embodiment of the present application, the core of step S400 is that after identifying that the visual recognition result stability index and the polarization feature attenuation index have a preset coupling relationship, the initial visual fusion confidence weight value is dynamically corrected to adapt to the change trend of the polarization characteristics of the building reflection structure.

[0052] Since the polarization characteristics are physical properties that gradually decay over time, when the building surface coating layer or polarization layer is affected by environmental aging, dust deposition, humidity erosion and other factors, its polarization ratio and polarization angle will change, so that the polarization characteristics of the reflected light are no longer consistent with the reference characteristics when the vehicle first formulates the initial visual fusion confidence weight value. If the old weight value is still used before entering the light interference area under the current condition, the confidence estimation of the visual recognition model for the reflection target will be too high, thereby affecting the accuracy of the fusion decision.

[0053] To this end, the application proposes the idea of weight correction based on the polarization feature attenuation index of two different time sequences. By comparing the current polarization feature attenuation index of the building reflection structure with the corresponding polarization feature attenuation index when the vehicle first formulates the initial visual fusion confidence weight value, the system can accurately quantify the degree of change of the polarization characteristics, thereby generating a correction factor reflecting the influence intensity of polarization attenuation. The significance of this correction method is: On the one hand, it is based on the adaptive weight adjustment of physical property changes rather than relying on empirical thresholds, thus having higher scientificity and interpretability; On the other hand, by using the comparison relationship between the historical reference state and the current state, the interference of noise, instantaneous light fluctuation and other factors can be effectively avoided, making the weight correction more stable and reliable.

[0054] In this embodiment, the specific execution process of step S403 is as follows: After calculating the corrected visual fusion confidence weight value, the correction module inputs it into the multi-sensor fusion algorithm of the vehicle perception control system in real time, which is used to replace the original fixed weight parameter. When the system fuses multi-source perception data from cameras, radars, lidar, etc., it redistributes the credibility proportion of visual recognition results in the overall fusion model according to the corrected weight value, so that the vehicle can more accurately recognize the front obstacles and road structures when passing through the light interference area, thereby improving the safety and robustness of automatic driving decision.

[0055] The technical solutions of the application are described below through a specific implementation example.

[0056] When the vehicle first passes through a certain glass curtain wall area on a high-frequency driving path, the vehicle perception control system calculates the visual fusion confidence weight value as 0.80 according to the light intensity, image contrast and sensor consistency at that time, and records the polarization feature attenuation index of the building reflection structure as 0.10. This data is stored as an initial reference in the historical environment perception data set.

[0057] Three weeks later, the vehicle drives to the same area again. Since the light distribution, incident angle and environmental brightness are basically the same as the first time, the system automatically calls the same initial weight value of 0.80 according to the current environmental state. However, it is found in the historical data comparison that the polarization feature attenuation index has risen from 0.10 to 0.25, and the visual recognition result stability index has dropped from 0.92 to 0.78. The system judges that the change direction of the two is opposite, the correlation coefficient reaches 0.82, which exceeds the preset threshold of 0.70, and confirms that there is a preset coupling relationship.

[0058] Subsequently, the correction stage is entered. The system extracts the difference 0.15 between the current polarization feature attenuation index 0.25 and the initial index 0.10, and calculates that the polarization attenuation ratio is 1.5. According to the correction coefficient 0.1, the weight correction ratio is 1 minus 0.1 times 1.5, and the result is 0.85. The system multiplies the initial weight value 0.80 by 0.85 to obtain the corrected visual fusion confidence weight value 0.68, and updates it to the multi-sensor fusion module in real time.

[0059] When the vehicle enters the light interference area with the corrected weight, the system reduces the weight ratio of visual recognition in the fusion model, and improves the participation of radar and lidar. The test results show that the stability of visual recognition results is restored from the original 0.74 to 0.88, and the false detection rate is reduced from 12% to 6%, and the vehicle can smoothly pass through the high reflection area.

[0060] The method quantifies the influence of polarization change by comparing two groups of polarization feature attenuation indexes with different time sequences, realizes the adaptive correction of the weight of the visual channel, and has the advantages of intuitive calculation, rapid response and avoidance of noise misjudgment. Through this correction mechanism, the vehicle can still maintain recognition stability when the polarization characteristics deteriorate under the condition that the light condition does not change, and significantly improves the safety, reliability and practical value of automatic driving in complex reflection environment.

[0061] In summary, the overall beneficial effects of the present application are that the polarization feature attenuation index is introduced to dynamically correct the visual fusion confidence weight value, and the adaptive perception and response of the automatic driving system to the change of polarization characteristics are realized for the first time. Compared with the prior art, the present scheme can identify the visual recognition performance degradation problem caused by the deterioration of polarization characteristics under the condition that the light condition is basically unchanged, thereby effectively solving the core problem proposed in step S100 that the existing system cannot identify the change of polarization and correct the weight.

[0062] The technical solution can be widely applied to automatic driving scenes in urban high-reflection environments, such as glass curtain wall dense road sections in urban core areas, airport entrances and exits, commercial complex roads, etc. The core algorithm module can be embedded in the existing vehicle perception control system without increasing additional hardware costs, so as to improve the recognition stability and safety of the vehicle in complex light interference environment, and has a significant promoting effect on the practicality and reliable operation of the automatic driving system.

[0063] Further, Figure 3 The application architecture diagram of the system provided by the embodiment of the present application is shown.

[0064] Among them, in another preferred embodiment provided by the present application, an automatic driving safety control system based on environmental perception comprises: The weight extraction module 100 is configured to extract an initial visual fusion confidence weight value for multi-sensor fusion when the vehicle is about to enter a light interference area formed by a specific building reflection structure in a high-frequency driving path, and obtain a historical environment perception data set of the vehicle on the high-frequency driving path.

[0065] Further, the environment perception-based automatic driving safety control system further comprises: The sample analysis module 200 is configured to analyze the historical environment perception data set to screen a plurality of reference samples matched with the current environment state feature, and perform time sequence analysis on the reference samples to determine a visual recognition result stability index of the vehicle when passing through the light interference area and a polarization feature attenuation index of the corresponding building reflection structure.

[0066] Further, the environment perception-based automatic driving safety control system further comprises: The coupling determination module 300 is configured to analyze the time variation trend of the visual recognition result stability index and the polarization feature attenuation index based on the multi-time sequence reference samples to determine whether they present a preset coupling relationship.

[0067] Further, the environment perception-based automatic driving safety control system further comprises: The dynamic correction module 400 is configured to, if it is determined that the preset coupling relationship exists, obtain the current polarization feature attenuation index of the building reflection structure, perform difference analysis on the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value when the vehicle first formulates the initial visual fusion confidence weight value, generate a correction factor, and dynamically correct the initial visual fusion confidence weight value by using the correction factor.

[0068] It should be understood that, although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least a part of other steps or sub-steps or stages of other steps.

[0069] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0070] Any combination of the technical features of the above-mentioned embodiments can be combined. In order to make the description simple, all possible combinations of the technical features in the above-mentioned embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0071] The above-mentioned embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as limiting the scope of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

[0072] The above-mentioned is only the preferred embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for safe control of autonomous driving based on environmental perception, characterized in that, The method includes: When a vehicle is about to enter a light interference area formed by a specific building reflection structure in a high-frequency driving path, the initial visual fusion confidence weight value for multi-sensor fusion is extracted, and the historical environmental perception dataset of the vehicle on the high-frequency driving path is obtained. The historical environmental perception dataset is analyzed to select several reference samples that match the characteristics of the current environmental state. The reference samples are then analyzed in time series to determine the stability index of the visual recognition results of the vehicle when it passes through the light interference area in the past and the polarization feature attenuation index of the corresponding building reflection structure. Based on the analysis of the time variation trends of the stability index of visual recognition results and the polarization feature attenuation index using multiple time-series reference samples, it is possible to determine whether the two exhibit a pre-defined coupling relationship. If a pre-defined coupling relationship is determined, the current polarization feature attenuation index of the building's reflective structure is obtained. The difference between this index and the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value of the vehicle is analyzed to generate a correction factor. The correction factor is then used to dynamically correct the initial visual fusion confidence weight value.

2. The autonomous driving safety control method based on environmental perception according to claim 1, characterized in that, The specific building reflective structure is a glass curtain wall facade with a high reflectivity coating or polarizing layer on its surface.

3. The autonomous driving safety control method based on environmental perception according to claim 1, characterized in that, The current environment state feature matching refers to the situation where the consistency between the reference sample and the current environment of the vehicle in terms of illumination distribution, incident angle, ambient brightness, and reflection direction is higher than a preset threshold.

4. The autonomous driving safety control method based on environmental perception according to claim 1, characterized in that, The historical environmental perception dataset includes: multi-source perception data collected from the vehicle side and reflection feature data obtained from the building reflection structure side.

5. The autonomous driving safety control method based on environmental perception according to claim 4, characterized in that, The process of determining the stability index of the visual recognition results includes: The multi-source perception data collected from the vehicle side is analyzed to determine the confidence fluctuation range, consistency of recognition results, and false detection rate of the vehicle visual recognition model in the reference sample when passing through the light interference area. The confidence fluctuation range, consistency of recognition results, and false detection rate are combined to generate a comprehensive evaluation value, which is used as the stability index of visual recognition results.

6. The autonomous driving safety control method based on environmental perception according to claim 4, characterized in that, The calculation process for the polarization characteristic attenuation index includes: The reflection feature data obtained from the building's reflective structure is analyzed, and the polarization rate and polarization angle information of the reflected light corresponding to the reference sample are extracted. Based on the polarization rate and polarization angle information of the reflected light when the initial visual fusion confidence weight value is first set relative to the vehicle, the polarization rate attenuation magnitude and polarization angle offset are generated sequentially, and the above results are combined to generate the polarization feature attenuation index.

7. The autonomous driving safety control method based on environmental perception according to claim 1, characterized in that, The preset coupling relationship refers to: The trend of the stability index of visual recognition results is gradually decreasing, while the trend of the polarization feature attenuation index is gradually increasing. When the correlation coefficient between the rate of change or the magnitude of change of the two is higher than the preset threshold, it is determined that there is a coupling relationship between the decline in visual recognition performance and the attenuation of polarization features.

8. The autonomous driving safety control method based on environmental perception according to claim 7, characterized in that, If a pre-defined coupling relationship is confirmed, the steps include obtaining the current polarization feature attenuation index of the building's reflective structure, performing a difference analysis between this index and the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value set for the vehicle, generating a correction factor, and dynamically correcting the initial visual fusion confidence weight value using this correction factor: Obtain the current polarization feature attenuation index of the building's reflective structure, and obtain the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value of the vehicle when it first sets the historical environmental perception dataset; The difference analysis of the two polarization feature attenuation indices is performed to generate a correction factor, and the initial visual fusion confidence weight value is dynamically corrected using the correction factor. Obtain the corrected visual fusion confidence weight value, enabling the vehicle to pass through the current illumination interference area based on the corrected visual fusion confidence weight value.

9. The autonomous driving safety control method based on environmental perception according to claim 8, characterized in that, When correcting the initial visual fusion confidence weight values, a preset correction function is used, which is: ； in, This refers to the corrected confidence weights for visual fusion. This refers to the initial visual fusion confidence weight value. This refers to the upper limit of the confidence weight value for visual fusion. This refers to the attenuation index of the current polarization characteristics of the building's reflective structure. This refers to the polarization feature attenuation index corresponding to the initial vision fusion confidence weight value set for the vehicle. This refers to the correction factor. This refers to the control correction magnitude coefficient.

10. An autonomous driving safety control system based on environmental perception, characterized in that, The system includes: The weight extraction module is used to extract the initial visual fusion confidence weight values ​​for multi-sensor fusion when the vehicle is about to enter the light interference area formed by the reflection structure of a specific building in the high-frequency driving path, and to obtain the historical environmental perception dataset of the vehicle on the high-frequency driving path. The sample parsing module is used to parse the historical environmental perception dataset to filter out several reference samples that match the current environmental state features. The reference samples are then subjected to time-series parsing to determine the stability index of the visual recognition results of the vehicle when it passes through the light interference area in the past and the polarization feature attenuation index of the corresponding building reflection structure. The coupling determination module is used to analyze the time variation trend of the stability index of visual recognition results and the polarization feature attenuation index based on multiple time-series reference samples, so as to determine whether the two present a preset coupling relationship. The dynamic correction module is used to obtain the current polarization feature attenuation index of the building reflection structure if a preset coupling relationship is determined, perform difference analysis between the current polarization feature attenuation index and the polarization feature attenuation index corresponding to the initial visual fusion confidence weight value of the vehicle, generate a correction factor, and use the correction factor to dynamically correct the initial visual fusion confidence weight value.

Images