Vehicle anti-glare control methods, devices, electronic equipment and storage media

Abstract

This application relates to a vehicle anti-glare control method, device, electronic device, and storage medium. The method calculates the incident angle vector of the light source based on the light source information around the vehicle, accurately determining the incident direction of external strong light relative to the driver's eyes. Based on the incident angle vector, it determines the intersection point of the light source's rays projected onto the driver's eyes in the windshield or rearview mirror. It accurately correlates the light source and the driver's eye position to the specific point on the windshield or rearview mirror. Then, it determines the glare impact index based on the driver's multi-dimensional characteristics. Finally, based on the glare impact index and the intersection point, it identifies the target area for adjusting the light transmittance from the windshield or rearview mirror, adjusting the light only in a targeted local area. This effectively eliminates glare while maximizing the preservation of the driver's overall visual clarity, avoiding secondary safety risks caused by limited visibility due to overall darkening, and improving driving safety.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle anti-glare control method, device, electronic device and storage medium. Background Technology

[0002] In daily driving, drivers often encounter problems with the high beams of oncoming vehicles or the strong light from vehicles behind them. For example, when driving at night, the high beams of oncoming vehicles shine directly into the driver's eyes, or the strong light from vehicles behind is reflected into the eyes through the rearview mirror, causing temporary glare, visual persistence, and blurred vision. In severe cases, it may lead to a blind spot for several seconds. In addition, when driving during the day, the low-angle direct sunlight can also cause similar problems, seriously affecting driving safety. Summary of the Invention

[0003] This application provides a vehicle anti-glare control method, device, electronic device, and storage medium to solve the technical problem of how to effectively eliminate glare.

[0004] In a first aspect, this application provides a vehicle anti-glare control method, the method comprising: Calculate the incident angle vector of the light source based on the light source information around the vehicle; The intersection point is determined based on the incident angle vector; wherein, the intersection point is the point in the windshield or rearview mirror where the light from the light source is projected onto the driver's eye position; The glare impact index is determined based on the driver's multi-dimensional characteristics; wherein, the multi-dimensional characteristics include at least head features and eye features; The target area to be adjusted is determined based on the glare impact index and the intersection point, so as to adjust the light transmittance of the target area.

[0005] Optionally, the incident angle vector of the light source is calculated based on the light source information around the vehicle, including: Collect information on the light sources around the vehicle; Determine the three-dimensional spatial coordinates and angle of the light source information; The incident angle vector of the light source relative to the driver is calculated based on the three-dimensional spatial coordinates, the light source angle, and the driver's position information.

[0006] Optionally, determining the intersection point based on the incident angle vector includes: Calculate the angle between the driver's line-of-sight vector and the incident angle vector; If the target angle is less than a preset angle threshold, calculate the coordinates of the intersection point between the incident angle vector and the windshield, and use the intersection point coordinates as the intersection point. or, Calculate the direction of the reflected light ray after the incident angle vector is reflected by the rearview mirror; When the direction of the reflected light is pointing towards the driver's eyes, the coordinates of the reflection point in the rearview mirror in the direction of the reflected light are determined, and the coordinates of the reflection point are used as the intersection point.

[0007] Optionally, determining the target area to be adjusted based on the glare impact index and the intersection point to adjust the light transmittance of the target area includes: The target radius is determined based on the light source intensity and the glare impact index, and the dimming depth is determined based on the light source intensity and the glare impact index. The target area is determined in the windshield based on the target radius and the intersection point; wherein the target area is centered on the intersection point. The transmittance of the target area is adjusted according to the dimming depth.

[0008] Optionally, determining the target area to be adjusted based on the glare impact index and the intersection point to adjust the light transmittance of the target area includes: The dimming depth is determined based on the glare impact index; The target area is determined in the rearview mirror based on the intersection point and a preset radius; wherein the target area is centered on the intersection point. The transmittance of the target area is adjusted according to the dimming depth.

[0009] Optionally, the glare impact index is determined based on the driver's multi-dimensional characteristics, including: Acquire the driver's average eyelid opening and closing, average pupil area, number of gaze deviations, and head deviation angle within the target time period; The degree of squinting is determined based on the preset eyelid opening and closing degree and the average eyelid opening and closing degree; The pupil change rate is determined based on the preset pupil area and the average pupil area; The gaze deviation frequency is determined based on the number of gaze deviations. The degree of head avoidance is determined based on the preset head angle and the head offset angle. The glare impact index is determined based on the degree of squinting, the pupil change rate, the frequency of gaze deviation, and the degree of head avoidance.

[0010] Optionally, adjusting the transmittance of the target area according to the dimming depth includes: Determine the driver's gaze point; When the gaze point is within the target area, the dimming depth is corrected according to a preset correction coefficient to obtain a corrected dimming depth, and the transmittance of the target area is adjusted according to the corrected dimming depth; If the gaze point is not within the target area, the transmittance of the target area is adjusted according to the dimming depth.

[0011] Secondly, this application provides a vehicle anti-glare control device, the device comprising: The calculation module is used to calculate the incident angle vector of the light source based on the light source information around the vehicle. The first determining module is used to determine the intersection point based on the incident angle vector; wherein, the intersection point is the point where the light rays from the light source are projected onto the driver's eye position in the windshield or rearview mirror; The second determining module is used to determine the glare impact index based on the driver's multi-dimensional characteristics; wherein, the multi-dimensional characteristics include at least head characteristics and eye characteristics; The control module is used to determine the target area to be adjusted based on the glare impact index and the intersection point, so as to adjust the light transmittance of the target area.

[0012] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When the processor executes a program stored in the memory, it implements the vehicle anti-glare control method according to any embodiment of the first aspect.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle anti-glare control method as described in any embodiment of the first aspect.

[0014] Compared with the prior art, the above-mentioned technical solution provided in this application embodiment has the following advantages: The method provided in this application embodiment calculates the incident angle vector of the light source based on the light source information around the vehicle; determines the intersection point based on the incident angle vector; wherein, the intersection point is the intersection point in the windshield or rearview mirror when the light from the light source is projected onto the driver's eye position; determines the glare impact index based on the driver's multi-dimensional characteristics; wherein, the multi-dimensional characteristics include at least head characteristics and eye characteristics; and determines the target area to be adjusted based on the glare impact index and the intersection point, so as to adjust the light transmittance of the target area. This method calculates the incident angle vector of the light source based on the light source information around the vehicle, accurately determining the incident direction of external strong light relative to the driver's eyes. This lays the foundation for accurate identification of the light source position. Based on this, it determines the intersection point of the light from the light source projected onto the driver's eyes in the windshield or rearview mirror according to the incident angle vector. This allows for precise correlation between the light source and the driver's eye position, pinpointing the exact location of the glare area and avoiding ineffective processing of non-glare areas. Then, based on the driver's multi-dimensional characteristics, it determines the glare impact index, quantifying the degree of glare impact from the driver's actual state of interference. Finally, based on the glare impact index and the intersection point, it identifies the target area for adjusting the transmittance in the windshield or rearview mirror. It only adjusts the localized area directly illuminated by the light source, rather than adjusting the overall brightness. This effectively eliminates glare while preserving the driver's overall visual clarity to the greatest extent, avoiding secondary safety risks caused by limited visibility due to overall darkening, and improving driving safety. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1 A system architecture diagram of a vehicle anti-glare control method provided in one embodiment of this application; Figure 2A schematic flowchart illustrating a vehicle anti-glare control method according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a vehicle anti-glare control device provided in one embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0021] To address the technical problem of effectively eliminating glare in the prior art, this application provides a vehicle anti-glare control method, device, electronic device, and storage medium that can dim only the local area directly illuminated by the light source, thereby effectively eliminating glare while preserving the driver's overall visual clarity to the greatest extent and improving driving safety.

[0022] The first embodiment of this application provides a vehicle anti-glare control method, which can be applied to, for example... Figure 1The system architecture shown includes at least a data acquisition module 101 and a data processing module 102, which establish a communication connection. The data acquisition module 101 may include various sensors, cameras, lidar, etc., to collect data such as vehicle status, surrounding environment information, and light source information. It may also include a driver monitoring system to collect driver head and eye information. The data processing module 102 processes the data, and may integrate intelligent systems with perception, decision-making, and execution capabilities, such as AI agents (Artificial Intelligence Agents). Specifically, this system architecture can be a vehicle, and the type of vehicle is not limited; for example, it could be a gasoline-powered vehicle, a pure electric vehicle, a hybrid vehicle, or a fuel cell vehicle, etc.

[0023] Next, based on this system architecture, the anti-glare control method for this vehicle will be described in detail, such as... Figure 2 The vehicle anti-glare control method includes: Step 201: Calculate the incident angle vector of the light source based on the light source information around the vehicle.

[0024] The light sources around a vehicle can include forward-facing and rearward-facing light sources. Forward-facing light source information can be collected by a forward-facing binocular camera, a wide-angle photosensitive sensor array, an infrared sensor, etc., while rearward-facing light source information can be collected by a rear-facing camera, a rearward-facing photosensitive sensor, etc. The incident angle vector of the light source can be calculated based on the collected light source information.

[0025] Specifically, during vehicle operation, a forward-facing binocular camera, a forward-facing wide-angle photosensitive sensor array (covering a 180° range in front), and an infrared sensor can be activated to collect real-time information on forward-facing light sources in front of the vehicle. The forward-facing binocular camera captures images of the headlights of vehicles ahead, the forward-facing wide-angle photosensitive sensor array detects the intensity of the light source, and the infrared sensor assists in light source identification in low-light conditions at night, preventing the missed detection of oncoming high beams. Similarly, information on rearward light sources is collected using a rear-view camera and a rear-facing photosensitive sensor; the rear-view camera captures images of the headlights behind the vehicle, and the rear-facing photosensitive sensor detects the intensity of the light source. Next, taking forward light source information as an example, the collected forward light source information is preprocessed. The headlights of oncoming vehicles can be identified through image recognition algorithms (e.g., based on the YOLOv8 model), and the high beams and low beams can be distinguished. At the same time, the three-dimensional spatial coordinates of the high beam are calculated using the principle of binocular vision ranging (e.g., a three-dimensional spatial coordinate system is established with the center point of the driver's seat as the origin). Assume that the detected three-dimensional spatial coordinates of the oncoming high beam are (-50m, 2.5m, 1.2m) (the negative sign indicates that it is traveling in the opposite direction, 50m away from the vehicle, with a lateral offset of 2.5m and a height of 1.2m). At the same time, the intensity of the high beam is detected as 8000 lux by a photosensitive sensor array, and the angle of the light source is determined. By combining the determined three-dimensional spatial coordinates of the high beam, the angle of the light source, and the position of the driver's eyes, the incident angle vector V_light of the high beam relative to the driver's eyes is calculated through spatial vector operation. The incident angle vector can include the horizontal incident angle and the vertical incident angle. For example, V_light is represented as V_light(α, β), where α is the horizontal incident angle and β is the vertical incident angle.

[0026] In one embodiment, calculating the incident angle vector of the light source based on the light source information around the vehicle includes: acquiring light source information around the vehicle; determining the three-dimensional spatial coordinates of the light source information and the light source angle; and calculating the incident angle vector of the light source relative to the driver based on the three-dimensional spatial coordinates, the light source angle, and the driver's position information.

[0027] In this embodiment, AI vision algorithms can be used to identify the headlights of vehicles ahead and distinguish between low beams and high beams. The system can perceive the light source information of vehicles with high beams on, determining the three-dimensional spatial coordinates and angle of the light source. For example, using the current vehicle or driver's location as the origin (0, 0, 0) of the three-dimensional spatial coordinate system, the three-dimensional spatial coordinates (x, y, z) of the light source information can be determined using LiDAR or visual ranging. The light source angle is then calculated based on the current emission angle of the light source. Therefore, the incident angle vector V_light relative to the driver can be calculated based on the three-dimensional spatial coordinates, the light source angle, and the driver's position information. Furthermore, each vehicle with high beams on can be assigned an ID, with different IDs for different vehicles, and its position changes can be continuously tracked to predict its trajectory. Similarly, the intensity of the headlights of vehicles behind can be detected, and the three-dimensional spatial coordinates and angle of the following vehicle's headlight source can be calculated. This allows for the calculation of the incident angle vector relative to the driver's headlight source. It should be understood that this incident angle vector, reflected by the rearview mirror, may affect the driver's vision.

[0028] Step 202: Determine the intersection point based on the incident angle vector; where the intersection point is the point in the windshield or rearview mirror where the light from the light source is projected onto the driver's eye position.

[0029] The intersection point of the light rays from the light source when they are projected onto the driver's eyes can be calculated based on the incident angle vector in the windshield or rearview mirror. This step is used to pinpoint the specific intersection point (cross-point) on the windshield or in the rearview mirror when the light rays from the light source are projected onto the driver's eyes, thus achieving precise location of the glare effect.

[0030] Next, we will describe in detail how to determine the intersection point for both forward and backward light sources.

[0031] In one embodiment, taking a forward-facing light source as an example, determining the intersection point based on the incident angle vector includes: calculating the target angle between the driver's line of sight direction vector and the incident angle vector; if the target angle is less than a preset angle threshold, calculating the coordinates of the intersection point between the incident angle vector and the windshield, and using the intersection point coordinates as the intersection point.

[0032] In this embodiment, when facing a vehicle with its high beams on, or when the vehicle in front is using a forward-facing light source, the system can collect image or video data of the driver using a driver monitoring system such as a camera, and reconstruct a three-dimensional eye model of the driver. Based on the three-dimensional eye model, the driver's gaze direction vector V_eye is calculated in real time. The target angle γ between the driver's gaze direction vector V_eye and the incident angle vector V_light is calculated. When γ is less than a preset angle threshold, it indicates that the light source is close to the gaze direction, and anti-glare control is required. The coordinates of the intersection point between the incident angle vector and the windshield are calculated, which are the coordinates of the intersection point (x_windshield, y_windshield) where the light passes through the windshield. These intersection points are used as the intersection points.

[0033] In one embodiment, taking a rear-facing light source as an example, determining the intersection point based on the incident angle vector includes: calculating the direction of the reflected light ray reflected by the rearview mirror from the incident angle vector; and, if the direction of the reflected light ray points towards the driver's eyes, determining the coordinates of the reflection point in the rearview mirror and using the coordinates of the reflection point as the intersection point.

[0034] In this embodiment, in a rear-facing light source scenario, the direction of the reflected light reflected by the rearview mirror can be calculated according to the law of reflection. It is then determined whether the direction of the reflected light is pointing towards the driver's eyes. If the direction of the reflected light is pointing towards the driver's eyes, it indicates that anti-glare control is required. At this time, the coordinates of the reflection point in the rearview mirror are determined, and the coordinates of the reflection point are used as the intersection point.

[0035] Step 203: Determine the glare impact index based on the driver's multi-dimensional characteristics; wherein, the multi-dimensional characteristics include at least head characteristics and eye characteristics.

[0036] The actual impact of glare on the driver can be quantified by analyzing the driver's head and eye characteristics, thus determining the glare impact index. By quantifying the actual impact of glare on the driver, we can avoid simply judging "whether there is glare" for coarse control and ensure that subsequent dimming strategies are aligned with the driver's actual condition.

[0037] In one embodiment, the glare impact index is determined based on the driver's multi-dimensional characteristics, including: obtaining the driver's average eyelid opening and closing degree, average pupil area, number of gaze deviations, and head deviation angle within a target time period; determining the degree of squinting based on preset eyelid opening and closing degree and average eyelid opening and closing degree; determining the pupil change rate based on preset pupil area and average pupil area; determining the gaze deviation frequency based on the number of gaze deviations; determining the degree of head avoidance based on preset head angle and head deviation angle; and determining the glare impact index based on the degree of squinting, pupil change rate, gaze deviation frequency, and head avoidance degree.

[0038] In this embodiment, the driver's average eyelid opening and closing degree, average pupil area, number of gaze deviations, and head deviation angle are obtained within a target duration. The squinting degree E is determined by the ratio of the average eyelid opening and closing degree to a preset eyelid opening and closing degree; the pupil change rate P is determined by the ratio of the average pupil area to a preset pupil area; the gaze deviation frequency F is determined by the number of gaze deviations within the target duration; and the head avoidance degree H is determined by the preset head angle and head deviation angle. A smaller squinting degree E indicates a greater degree of glare; the pupil change rate P indicates strong light stimulation; the gaze deviation frequency F indicates interference; and the head avoidance degree H indicates… The behavior of actively avoiding strong light can be mapped using a pre-defined relationship: a first mapping between squinting degree and a first weight; a second mapping between pupil change rate and a second weight; a third mapping between gaze deviation frequency and a third weight; and a fourth mapping between head avoidance degree and a fourth weight. For example, the smaller the squinting degree, the greater the first weight; the greater the pupil change rate, the greater the second weight; the greater the gaze deviation frequency, the greater the third weight; and the greater the head avoidance degree, the greater the fourth weight. This allows us to determine the first, second, third, and fourth weights. Then, the glare impact index G is determined by multiplying these weights. For example, G < 0.3: mild impact, observable, no anti-glare control needed; 0.3 ≤ G < 0.7: moderate impact, intervention recommended; G ≥ 0.7: severe impact, immediate anti-glare control required.

[0039] Specifically, the glare impact index is determined based on the driver's multi-dimensional characteristics. The specific process can be as follows: Multi-dimensional feature acquisition: The driver monitoring camera is activated to capture the driver's facial images in real time, focusing on head and eye features. The acquisition time is the target duration, such as 10 seconds, to obtain multiple frames of facial images (e.g., 250 frames of facial images if the camera acquisition frequency is 25Hz). Multi-dimensional features in each frame are extracted using image recognition algorithms, such as eyelid opening and closing, pupil area, number of gaze shifts, and head shift angle. Then, the average eyelid opening and closing, average pupil area, number of gaze shifts, and head shift angle of the multiple frames of facial images are calculated.

[0040] Multi-dimensional feature processing: (1) Calculation of squinting degree: The driver's normal eyelid opening degree is stored in advance (i.e., preset eyelid opening degree, for example, 0.8). The average eyelid opening degree of 250 frames in 10 seconds is calculated, for example, 0.4. Then the squinting degree E = average eyelid opening degree / normal eyelid opening degree = 0.4 / 0.8 = 0.5 (E∈[0,1], the smaller the value, the greater the impact of glare). (2) Calculation of pupil change rate: The baseline pupil area of ​​the driver under normal nighttime lighting conditions (i.e., the preset pupil area, for example, 2.5 mm) is stored in advance. 2If the average pupil area over 10 seconds is calculated to be 1.25 mm, then... 2 Then the pupil change rate P = average pupil area / reference pupil area = 1.25 / 2.5 = 0.5 (P∈[0,1], a sudden decrease in value indicates that the strong light stimulus is obvious). (3) Calculation of line of sight deviation frequency: By using the line of sight tracking algorithm, the number of times the driver's line of sight deviates from the road in 10 seconds is counted. For example, if the number of line of sight deviations is 3, the line of sight deviation frequency F can be calculated as: line of sight deviations / target duration = 3 / 10 = 0.3 (F∈[0,1], the larger the value, the more serious the glare interference). (4) Calculation of head avoidance degree: The reference head angle of the driver during normal driving is stored in advance (i.e., the preset head angle, for example, the preset maximum offset angle is 10°). The average head offset angle within 10 seconds is calculated to be 5°. Therefore, the head avoidance degree H = average head offset angle / preset maximum offset angle = 5 / 10 = 0.5 (H∈[0,1], the larger the value, the more obvious the behavior of actively avoiding strong light).

[0041] Glare impact index calculation: The AI ​​processing unit uses a preset neural network model (trained and optimized with a large amount of driver data) to fuse and calculate the above-mentioned squinting degree E, pupil change rate P, gaze deviation frequency F, and head avoidance degree H, and assigns dynamic weights to each feature (for example, the first weight w1=0.3, the second weight w2=0.3, the third weight w3=0.2, and the fourth weight w4=0.2, and the weights can be obtained through machine learning optimization). Finally, the glare impact index G=w1×E+w2×P+w3×F+w4×H=0.3×0.5+0.3×0.5+0.2×0.3+0.2×0.5=0.46. According to the G value grading standard, 0.3≤G<0.7 is a moderate impact, which requires dimming intervention.

[0042] Step 204: Determine the target area to be adjusted based on the glare impact index and the crossover point, so as to adjust the light transmittance of the target area.

[0043] Based on the quantified degree of glare impact, namely the glare impact index, and the precise intersection point, the local dimming area (target area) to be adjusted can be defined and the transmittance can be adjusted to achieve the effect of adjusting the transmittance of the target area to block glare, while not adjusting the transmittance of other areas to avoid obstructing the field of vision.

[0044] This method calculates the incident angle vector of the light source based on the light source information around the vehicle, accurately determining the incident direction of external strong light relative to the driver's eyes. This lays the foundation for accurate identification of the light source position. Based on this, it determines the intersection point of the light from the light source projected onto the driver's eyes in the windshield or rearview mirror according to the incident angle vector. This allows for precise correlation between the light source and the driver's eye position, pinpointing the exact location of the glare area and avoiding ineffective processing of non-glare areas. Then, based on the driver's multi-dimensional characteristics, it determines the glare impact index, quantifying the degree of glare impact from the driver's actual state of interference. Finally, based on the glare impact index and the intersection point, it identifies the target area for adjusting the transmittance in the windshield or rearview mirror. It only adjusts the localized area directly illuminated by the light source, rather than adjusting the overall brightness. This effectively eliminates glare while preserving the driver's overall visual clarity to the greatest extent, avoiding secondary safety risks caused by limited visibility due to overall darkening, and improving driving safety.

[0045] In one embodiment, determining the target area to be adjusted based on the glare impact index and the intersection point to adjust the transmittance of the target area includes: determining the target radius based on the light source intensity and the glare impact index, and determining the dimming depth based on the light source intensity and the glare impact index; determining the target area in the windshield based on the target radius and the intersection point; wherein the target area is centered on the intersection point; and adjusting the transmittance of the target area based on the dimming depth.

[0046] In this embodiment, for a forward light source, the target radius is determined based on the light source intensity and glare impact index. For example, the target radius R = R_base × (light source intensity coefficient) × (1 + G), where R_base is a preset base radius, and the light source intensity coefficient can be determined by the ratio of the light source intensity to the preset light source intensity. Next, the dimming depth is determined based on the light source intensity and glare impact index. The dimming depth can be the transmittance; the default transmittance is 100%, and if the dimming depth is 50%, then the transmittance is 50%. After determining the target radius and dimming depth, the target area can be defined with the intersection point as the center and the target radius as the radius. The transmittance of the target area is then adjusted according to the dimming depth.

[0047] It should be understood that the windshield can support adjustable light transmittance by region. For example, using matrix electrochromic glass, the windshield can be divided into N×M independently controllable microcells (such as 200×120 cells), and the light transmittance of each cell can be adjusted independently. Similarly, the left and right exterior rearview mirrors and the interior rearview mirror also support adjustable light transmittance by region, which will not be elaborated further.

[0048] Specifically, for example, by detecting oncoming vehicles using high beams through a forward-facing camera, the incident angle vector of the light source is calculated, and the AI ​​agent calculates the glare impact index G, for example, G=0.4 (moderate impact). The target area for protection is defined on the windshield, and the dimming depth D=60%. The transmittance of the target area is adjusted according to the dimming depth. At this time, the target area becomes darker, while other areas are clear. Thus, dimming is only applied to the local area directly illuminated by the light source, thereby effectively eliminating glare while maximizing the preservation of the driver's overall visual clarity and improving driving safety.

[0049] In one embodiment, determining the target area to be adjusted based on the glare impact index and the intersection point to adjust the light transmittance of the target area includes: determining the dimming depth based on the glare impact index; determining the target area in the rearview mirror based on the intersection point and a preset radius; wherein the target area is centered on the intersection point; and adjusting the light transmittance of the target area based on the dimming depth.

[0050] In this embodiment, for a rearward light source, the dimming depth is determined based on the glare effect index. Since the rearview mirrors are small, the target area can be determined in the rearview mirror based on the intersection point and the preset radius, and then the light transmittance of the target area is adjusted according to the dimming depth.

[0051] Specifically, when the rearview camera detects that a vehicle behind has turned on its high beams, it calculates the reflection path of the incident angle vector, locates the target area on the rearview mirror, adjusts the dimming depth of the target area, and restores the light transmission of the rearview mirror after the vehicle behind turns off its high beams.

[0052] In one embodiment, adjusting the transmittance of a target area based on the dimming depth includes: determining the driver's gaze point; if the gaze point is within the target area, correcting the dimming depth according to a preset correction coefficient to obtain a corrected dimming depth, and adjusting the transmittance of the target area based on the corrected dimming depth; if the gaze point is not within the target area, adjusting the transmittance of the target area based on the dimming depth.

[0053] In this embodiment, a gaze-point association decision can be introduced to avoid the target area containing critical areas that the driver needs to see clearly. For example, the driver's gaze point can be determined. If the gaze point is within the target area, the dimming depth is adjusted according to a preset correction coefficient to obtain a corrected dimming depth. The transmittance of the target area is then adjusted based on the corrected dimming depth. For example, the initially calculated dimming depth might require reducing the transmittance to 40%. If the gaze point on the windshield is within the target area, to improve the driver's visual discrimination ability, the adjustment depth can be further adjusted according to the preset correction coefficient, such as to 60% or 80%. If the gaze point is not within the target area, the transmittance of the target area is directly adjusted based on the dimming depth. It should be understood that when adjusting the transmittance of the rearview mirror, a different preset correction coefficient can be set than that for the windshield. For example, if the initially calculated dimming depth requires reducing the transmittance to 40%, and the gaze point on the rearview mirror is within the target area, the transmittance can be corrected to reduce it to 50%, etc., without limitation.

[0054] When multiple strong light sources exist, fusion processing can be performed. For example, target area A corresponds to strong light source A, target area B corresponds to strong light source B, and target area C corresponds to strong light source C. If target areas A, B, and C do not overlap, each area can be dimmed independently according to its own dimming depth. If target areas A, B, and C partially overlap, and the overlapping area is smaller than a preset area, target areas A, B, and C can be combined, and the transmittance can be adjusted according to the maximum dimming depth. If target areas A, B, and C largely overlap, i.e., the overlapping area is smaller than a preset area, the minimum transmittance can be limited to not be lower than a preset transmittance (e.g., 30%) to ensure that the driver can see the road conditions clearly.

[0055] In one specific embodiment, the specific implementation process for determining the target area to be adjusted based on the glare impact index and the crossover point, and adjusting the light transmittance of the target area, is as follows: Target area identified: (1) Target radius calculation: For example, the preset base radius R_base is 5cm, the target radius R = R_base × light source intensity coefficient × (1+G). The light source intensity coefficient can be determined by the ratio of the light source intensity to the preset light source intensity. For example, the detected light source intensity is 8400 lux, the preset light source intensity is 7000 lux, then the light source intensity coefficient is 1.2, the calculated glare influence index G is 0.46, then the target radius R = 5cm × 1.2 × (1+0.46) = 8.76cm, which can be rounded to 9cm.

[0056] (2) Area delineation: With the intersection as the center and a radius of 9cm, a circular area is delineated on the windshield. This area is the target area for adjusting the light transmittance. This area precisely covers the path of the high beam light projected to the driver's eyes, ensuring that the glare can be effectively blocked after the light is adjusted.

[0057] Light transmittance adjustment: (1) Determining the dimming depth: The dimming depth is determined based on the light source intensity and glare effect index. The dimming depth can be the transmittance. The default transmittance is 100%. If the dimming depth is 50%, then the transmittance is 50%. After determining the target radius and dimming depth, the transmittance of the target area can be adjusted according to the dimming depth.

[0058] The dimming depth is determined based on the light source intensity and glare impact index G. For example, if the preset baseline dimming depth D_base is 50%, then the dimming depth D = D_base × (1 + G) = 50% × (1 + 0.46) = 73%, which means that the transmittance of the target area needs to be adjusted to (1 - 73%) = 27% of the original transmittance (if the original transmittance is 80%, the transmittance after adjustment is 80% × 27% ≈ 21.6%). (2) Dimming: The AI ​​processing unit sends control commands to the matrix electrochromic windshield to control all electrochromic cells in the target area. By adjusting the applied voltage of the cells (the transmittance of the electrochromic material is positively correlated with the applied voltage), the transmittance of the target area is adjusted according to the dimming depth. At the same time, the windshield area outside the target area maintains the original transmittance to ensure that the driver can clearly observe other road conditions ahead.

[0059] Dynamic feedback adjustment: After dimming is executed, the system continuously collects light source information and multi-dimensional characteristics of the driver, and continuously updates and calculates the glare impact index and intersection position. If the glare impact index G value drops below 0.3 (mild impact), the target radius can be reduced and the dimming depth can be decreased; if the G value rises above 0.7 (severe impact), the target radius can be increased and the dimming depth can be increased, ensuring that while effectively eliminating glare, the overall visual clarity of the driver is preserved to the greatest extent.

[0060] In the above embodiments of this application, by integrating multimodal sensor data through an AI agent, the position and intensity of external light sources, the driver's line of sight and the degree of interference are perceived in real time. A glare impact index is constructed by multi-dimensional features such as squinting degree, pupil change rate, and line of sight deviation. Based on the gaze point association decision, the windshield and rearview mirror are driven to adopt zoned electrochromic technology, which dynamically dims only the local area directly illuminated by the light source. While effectively eliminating glare, the overall visual clarity of the driver is preserved to the greatest extent, thereby improving driving safety.

[0061] Based on the same technical concept, the second embodiment of this application provides a vehicle anti-glare control device, such as... Figure 3 The device includes: The calculation module 301 is used to calculate the incident angle vector of the light source based on the light source information around the vehicle; The first determining module 302 is used to determine the intersection point according to the incident angle vector; wherein, the intersection point is the point where the light rays from the light source are projected onto the driver's eye position in the windshield or rearview mirror; The second determining module 303 is used to determine the glare impact index based on the multi-dimensional characteristics of the driver; wherein, the multi-dimensional characteristics include at least head features and eye features; The control module 304 is used to determine the target area to be adjusted based on the glare impact index and the intersection point, so as to adjust the light transmittance of the target area.

[0062] This device calculates the incident angle vector of the light source based on the light source information around the vehicle, accurately determining the incident direction of external strong light relative to the driver's eyes. This lays the foundation for accurate identification of the light source position. Based on this, it determines the intersection point of the light from the light source when it is projected onto the driver's eyes in the windshield or rearview mirror according to the incident angle vector. It can accurately correlate the light source and the driver's eye position to the specific point in the windshield or rearview mirror, achieving precise locking of the glare area position and avoiding ineffective processing of non-glare areas. Then, it determines the glare impact index based on the driver's multi-dimensional characteristics, quantifying the degree of glare impact from the driver's actual state of interference. Finally, based on the glare impact index and the intersection point, it determines the target area for adjusting the light transmittance from the windshield or rearview mirror. It only adjusts the light in a targeted local area directly hit by the light source, rather than adjusting the overall light. This effectively eliminates glare while preserving the driver's overall visual clarity to the greatest extent, avoiding secondary safety risks caused by limited vision due to overall darkening, and improving driving safety.

[0063] like Figure 4 As shown in the figure, this application provides an electronic device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114. Memory 113 is used to store computer programs; In one embodiment of this application, the processor 111, when executing the program stored in the memory 113, implements the vehicle anti-glare control method provided in any of the foregoing method embodiments.

[0064] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0065] The communication interface is used for communication between the aforementioned terminal and other devices.

[0066] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0067] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0068] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the vehicle anti-glare control method as provided in any of the foregoing method embodiments.

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

[0070] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0071] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0072] It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. In the description, suffixes such as "module," "part," or "unit" used to denote elements are used solely for illustrative purposes and have no specific meaning in themselves. Therefore, "module," "part," or "unit" may be used interchangeably.

[0073] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for controlling vehicle anti-glare, characterized in that, The method includes: Calculate the incident angle vector of the light source based on the light source information around the vehicle; The intersection point is determined based on the incident angle vector; wherein, the intersection point is the point in the windshield or rearview mirror where the light from the light source is projected onto the driver's eye position; The glare impact index is determined based on the driver's multi-dimensional characteristics; wherein, the multi-dimensional characteristics include at least head features and eye features; The target area to be adjusted is determined based on the glare impact index and the intersection point, so as to adjust the light transmittance of the target area.

2. The method according to claim 1, characterized in that, The incident angle vector of the light source is calculated based on the light source information around the vehicle, including: Collect information on the light sources around the vehicle; Determine the three-dimensional spatial coordinates and angle of the light source information; The incident angle vector of the light source relative to the driver is calculated based on the three-dimensional spatial coordinates, the light source angle, and the driver's position information.

3. The method according to claim 1, characterized in that, Determining the intersection point based on the incident angle vector includes: Calculate the angle between the driver's line-of-sight vector and the incident angle vector; If the target angle is less than a preset angle threshold, calculate the coordinates of the intersection point between the incident angle vector and the windshield, and use the intersection point coordinates as the intersection point. or, Calculate the direction of the reflected light ray after the incident angle vector is reflected by the rearview mirror; When the direction of the reflected light is pointing towards the driver's eyes, the coordinates of the reflection point in the rearview mirror in the direction of the reflected light are determined, and the coordinates of the reflection point are used as the intersection point.

4. The method according to claim 3, characterized in that, Determining the target area to be adjusted based on the glare impact index and the intersection point, and adjusting the light transmittance of the target area, includes: The target radius is determined based on the light source intensity and the glare impact index, and the dimming depth is determined based on the light source intensity and the glare impact index. The target area is determined in the windshield based on the target radius and the intersection point; wherein the target area is centered on the intersection point. The transmittance of the target area is adjusted according to the dimming depth.

5. The method according to claim 3, characterized in that, Determining the target area to be adjusted based on the glare impact index and the intersection point, and adjusting the light transmittance of the target area, includes: The dimming depth is determined based on the glare impact index; The target area is determined in the rearview mirror based on the intersection point and a preset radius; wherein the target area is centered on the intersection point. The transmittance of the target area is adjusted according to the dimming depth.

6. The method according to claim 1, characterized in that, The glare impact index is determined based on the driver's multi-dimensional characteristics, including: Acquire the driver's average eyelid opening and closing, average pupil area, number of gaze deviations, and head deviation angle within the target time period; The degree of squinting is determined based on the preset eyelid opening and closing degree and the average eyelid opening and closing degree; The pupil change rate is determined based on the preset pupil area and the average pupil area; The gaze deviation frequency is determined based on the number of gaze deviations. The degree of head avoidance is determined based on the preset head angle and the head offset angle. The glare impact index is determined based on the degree of squinting, the pupil change rate, the frequency of gaze deviation, and the degree of head avoidance.

7. The method according to claim 4 or 5, characterized in that, Adjusting the transmittance of the target area according to the dimming depth includes: Determine the driver's gaze point; When the gaze point is within the target area, the dimming depth is corrected according to a preset correction coefficient to obtain a corrected dimming depth, and the transmittance of the target area is adjusted according to the corrected dimming depth; If the gaze point is not within the target area, the transmittance of the target area is adjusted according to the dimming depth.

8. A vehicle anti-glare control device, characterized in that, The device includes: The calculation module is used to calculate the incident angle vector of the light source based on the light source information around the vehicle. The first determining module is used to determine the intersection point based on the incident angle vector; wherein, the intersection point is the point where the light rays from the light source are projected onto the driver's eye position in the windshield or rearview mirror; The second determining module is used to determine the glare impact index based on the driver's multi-dimensional characteristics; wherein, the multi-dimensional characteristics include at least head characteristics and eye characteristics; The control module is used to determine the target area to be adjusted based on the glare impact index and the intersection point, so as to adjust the light transmittance of the target area.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing a program stored in the memory, implements the vehicle anti-glare control method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle anti-glare control method as described in any one of claims 1-7.

Images