Vehicle window dynamic regulation and control method and system based on electrochromic glass and vehicle

Abstract

The invention discloses a vehicle window dynamic regulation and control method and system based on electrochromic glass and a vehicle, and relates to the technical field of vehicle intelligent control. The method comprises the steps that a light conversion landmark site on a route is recognized, and a site entrance and exit are positioned; obtaining the real-time position of the vehicle, calculating the distance between the vehicle and the entrance and exit of the site, and judging whether to start a vehicle window dynamic regulation function or not according to the distance and the vehicle driving direction; when a function is started, a scene image in front of a vehicle is obtained in real time, a landmark site in front of the vehicle and illumination intensity inside and outside a site entrance and exit are recognized, meanwhile, the distance between the vehicle and the site entrance and exit and the vehicle speed are obtained in real time, the target light transmittance is calculated accordingly, and the optimal adjustment time range is determined by combining the light transmittance adjustment rate. And dynamically adjusting the light transmittance of the electrochromic glass of the car window within the time range, so that the light intensity in the car is gradually changed to be consistent with the light intensity in the area which is about to enter. The vehicle window can be regulated and controlled in time, and the detection cost is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle intelligent control, and particularly to a window dynamic regulation method, system and vehicle based on electrochromic glass. Background Art

[0002] The statements in this part only provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] With the rapid development of the modern automotive industry, the comfort attributes of vehicle driving are gradually evolving towards intelligent attributes. Moreover, there are more and more vehicles on the road, and even a slight oversight during driving may cause serious traffic accidents. The construction of modern transportation infrastructure has developed rapidly. In the face of complex terrains, tunnel construction, as a key technical means to break through geographical barriers, has effectively shortened the distance between regions. However, although the tunnel shortens the distance between the two, due to the light-dark changing environment inside the tunnel, it is extremely easy to cause interference to the driver's line of sight, making it a high-incidence area for traffic accidents. For example, usually, the light inside the tunnel is much darker than that outside. When a vehicle enters or exits the tunnel, the environmental change from bright to dark or from dark to bright will cause a short-term interference to the driver's visual perception, and even cause a certain visual blind area. Although this environmental change only lasts for 1 - 2 seconds, for a vehicle traveling at high speed, this is enough for the vehicle to travel dozens of meters. If there are obstacles or emergencies ahead, the driver often has difficulty reacting quickly to brake and may have a safety accident due to untimely obstacle avoidance.

[0004] To address the above situation, the existing method is that at the moment of entering the tunnel, the light-dark perception sensor senses the darkening of the light, drives the vehicle headlights to turn on to illuminate the tunnel ahead, or adjusts the light transmittance of the window glass so that the light inside the vehicle is as close as possible to that before entering the tunnel, to avoid visual interference. However, this solution belongs to passive detection of light changes, and only triggers dimming after the vehicle enters the dark environment, lacking early warning ability. The driver still needs to adapt to the light-dark change for a short time, which poses a safety hazard; moreover, only using the light-dark perception sensor for light sensing is prone to environmental misjudgment and is interfered by extreme weather, resulting in frequent adjustments or untimely adjustments.

[0005] In view of the above problems, a solution has also been proposed to uniformly adjust the light transmittance of the window glass at a constant speed in advance when the vehicle is about to enter a tunnel. Although this solution can provide early warnings, it is necessary to continuously detect the surrounding environment in real time to identify areas with large light and darkness changes such as tunnels during the whole process. However, the number of tunnel areas on the driving route is not necessarily fixed. Therefore, this may cause a certain waste of detection resources. Moreover, this method highly depends on efficient detection algorithms. Existing methods mostly use a fixed rate for color change adjustment. The time point of this color change adjustment mostly depends on the time when the tunnel area is detected, which may result in the situation that the subsequent adjustment of the glass light transmittance is affected due to the untimely detection of the tunnel area, and then cause the situation of untimely adjustment and slow adjustment. Summary of the Invention

[0006] To solve the deficiencies of the above-mentioned prior art, the present invention provides a window dynamic regulation method, system and vehicle based on electrochromic glass. By identifying venues with large light and darkness changes such as tunnels on the navigation route and pre-adjusting the window glass regulation function in combination with the actual position of the vehicle, environmental detection is only carried out after the function is started, thus avoiding waste of detection resources. Using binocular vision cameras and radars, accurately identify in advance the distance from the light and darkness conversion areas such as tunnels and the change of light intensity at the tunnel entrance, determine the time point to automatically adjust the color of the windshield, so that the light conditions inside the vehicle are consistent before and after entering the tunnel, avoid the situation of slow adjustment, avoid visual interference of the driver caused by light and darkness changes when entering the tunnel, and reduce the occurrence of accidents.

[0007] In the first aspect, the present invention provides a window dynamic regulation method based on electrochromic glass.

[0008] A window dynamic regulation method based on electrochromic glass includes:

[0009] Based on the map navigation route generated by the in-vehicle navigation system, identify the light conversion landmark venues on the route and locate the entrances and exits of the venues;

[0010] Obtain the real-time position of the vehicle, calculate the distance between the vehicle and the entrance and exit of the venue, and judge whether to activate the window dynamic regulation function according to the distance and the driving direction of the vehicle;

[0011] When the function is activated, obtain the real-time scene image in front of the vehicle in real time, identify the landmark venue in front of the vehicle and the light intensity inside and outside the entrance and exit of the venue, and at the same time obtain the distance between the vehicle and the entrance and exit of the venue and the vehicle speed in real time;

[0012] According to the real-time distance, vehicle speed, and light intensity inside and outside the entrance and exit of the venue, calculate the target light transmittance, and determine the optimal adjustment time range in combination with the light transmittance adjustment rate. Dynamically adjust the light transmittance of the electrochromic glass of the window within this time range to gradually change the light intensity inside the vehicle to be consistent with the light intensity in the upcoming area.

[0013] A further technical solution is to determine whether to activate the window dynamic regulation function according to the distance and the vehicle driving direction, including:

[0014] When the distance between the vehicle and the site entrance / exit is less than the set distance value and the vehicle driving direction is towards the site entrance / exit, activate the window dynamic regulation function; otherwise, do not activate the window dynamic regulation function yet.

[0015] A further technical solution is to obtain the vehicle front scene image in real time and identify the landmark site in front of the vehicle and the light intensities inside and outside the site entrance / exit, including:

[0016] According to the vehicle front scene image obtained in real time, use the YOLO object detection algorithm to identify the landmark site in front of the vehicle and extract the landmark site area image;

[0017] For the landmark site area image, after image preprocessing, adopt the image region segmentation method of adaptive clustering to divide the overall region into two partial regions, and calculate the average brightness according to the pixel point brightness of the two partial regions respectively. Take the average brightness of the two partial regions inside and outside the landmark site entrance / exit as the light intensity.

[0018] A further technical solution, the image region segmentation, includes:

[0019] Take the landmark site area image as the image to be segmented, and convert the image to be segmented from RGB to the LAB color space;

[0020] Use Sobel edge detection to extract the high-density edge region in the image to be segmented as the candidate region, and select two pixel points in the candidate region as the initial clustering centers;

[0021] Based on the initial clustering centers, use the improved K-means clustering algorithm to cluster all pixel points to form two clustering regions;

[0022] Continuously iterate and update the clustering centers until the silhouette coefficient of the two clustering regions reaches the set value or the number of iterations reaches the set value, and complete the region segmentation.

[0023] A further technical solution, the calculation formula of the target light transmittance is:

[0024] T = T min +(T max -T min )×e -k·D / V ;

[0025] Wherein, T represents the target light transmittance, T min is the lowest light transmittance, T maxFor the highest light transmittance, k is the environmental attenuation coefficient, D represents the distance, and V represents the vehicle speed.

[0026] A further technical solution is that the environmental attenuation coefficient is dynamically corrected according to the difference in the detected light intensities inside and outside the entrance and exit. The calculation formula for this environmental attenuation coefficient is:

[0027]

[0028] where k0 represents the reference coefficient, α is the adjustment coefficient, ΔL = |L out -L in | represents the absolute difference in the light intensities inside and outside the entrance and exit, L out represents the light intensity outside the entrance and exit, L in represents the light intensity inside the entrance and exit, L ref represents the light value.

[0029] A further technical solution is to judge according to the real-time position of the vehicle and the position of the located site entrance and exit. When it is detected that the vehicle passes a set distance from the site entrance and exit, the light transmittance of the electrochromic glass of the window is restored to the initial light transmittance.

[0030] A further technical solution is to judge according to the real-time speed of the vehicle. If the vehicle brakes emergently, the dynamic regulation function of the window is automatically turned off, and the light transmittance of the electrochromic glass of the window is restored to the initial light transmittance.

[0031] In a second aspect, the present invention provides a window dynamic regulation system based on electrochromic glass.

[0032] A window dynamic regulation system based on electrochromic glass includes:

[0033] An identification and detection module, including a vehicle-mounted navigation system for generating a map navigation route and locating landmark site entrances and exits, a binocular vision camera for obtaining an image of the scene in front of the vehicle, a radar for detecting the distance of the vehicle from the site entrance and exit, and a vehicle speed sensor for obtaining the vehicle speed;

[0034] An operation and processing module, including a vehicle controller, for executing the window dynamic regulation method based on electrochromic glass proposed in the first aspect to obtain the target light transmittance;

[0035] An execution module, including a window color change controller, for dynamically adjusting the color of the electrochromic glass of the window according to the target light transmittance to adjust the light transmittance.

[0036] In a third aspect, the present invention further provides a vehicle.

[0037] A vehicle includes the window dynamic regulation system based on electrochromic glass proposed in the second aspect, or implements the window dynamic regulation method based on electrochromic glass proposed in the first aspect.

[0038] The above one or more technical solutions have the following beneficial effects:

[0039] 1. A window dynamic regulation method, system and vehicle based on electrochromic glass proposed by the present invention identify sites with large light and darkness changes such as tunnels on the navigation route, and pre-invoke the window glass regulation function in combination with the actual position of the vehicle. Only after the function is activated, environmental detection is carried out, avoiding waste of detection resources; using binocular vision cameras and radars, accurately identify in advance the distance from light and darkness conversion areas such as tunnels and the change of light intensity at the tunnel entrance, determine the time point to automatically change the color of the windshield, so that the light conditions inside the vehicle are the same before and after driving into the tunnel, avoiding the situation of too slow adjustment, avoiding visual interference of the driver caused by light and darkness changes when entering the tunnel, and reducing the occurrence of accidents.

[0040] 2. In the present invention, an adaptive clustering image region segmentation method is adopted to divide the extracted landmark area into two parts. An improved K-means algorithm is introduced in this adaptive clustering method. Through lightweight clustering optimization and edge density prediction, the segmentation efficiency of the two regions is effectively improved, thereby improving the efficiency of the subsequent regulation process and ensuring the timeliness of dynamic regulation.

[0041] The advantages of the additional aspects of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The specification drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0043] Figure 1 It is a flowchart of the window dynamic regulation method based on electrochromic glass in an embodiment of the present invention;

[0044] Figure 2 It is a relationship schematic diagram of the window dynamic regulation system based on electrochromic glass in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0045] It should be noted that the following detailed description is exemplary only for describing specific embodiments, aiming to provide further explanation of the present invention and not intended to limit the exemplary embodiments according to the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. In addition, it should also be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0046] Embodiment 1

[0047] To solve the problems of high detection cost, untimely adjustment, and mismatch in adjusting the light transmittance of the windshield before a vehicle enters a tunnel in the prior art, this embodiment proposes a method for dynamically regulating the vehicle window based on electrochromic glass, which is based on an in-vehicle navigation system, a binocular vision camera, a radar, and an electrochromic vehicle window glass. By the map navigation route, it identifies landmark sites where light conversion occurs, such as tunnels, on the route, and determines whether to turn on the dynamic regulation function of the vehicle window according to the actual position of the vehicle and the position of the landmark site. The dynamic regulation function is only turned on when the vehicle is near the landmark site. After it is turned on, detection and analysis are carried out, so as to reduce the detection cost on the basis of ensuring the normal execution of the dynamic regulation, and avoid the situation of frequent regulation caused by incorrect or abnormal detection and regulation during normal driving, which may affect safe driving; after the dynamic regulation function is started, the driver is reminded of the distance through means such as display on the vehicle display screen and intelligent voice, so as to improve attention. At the same time, the binocular vision camera and radar in front of the vehicle are used to obtain the scene image of the entrance and exit of the site in front of the vehicle and the real-time distance between the vehicle and the entrance and exit of the site. For the scene image, image recognition algorithms are used to identify the landmark scene and determine the light intensity inside and outside the entrance and exit of the site. Combining information such as vehicle speed, the electrochromic regulation of the vehicle window glass is automatically carried out to make the regulation match the vehicle speed, the distance of the vehicle from the entrance and exit, the light intensity, etc. in real time, ensuring the timeliness of the regulation. Taking a tunnel as an example, before entering the tunnel, the light transmittance is gradually reduced, and before exiting the tunnel, the light transmittance is gradually increased, so as to avoid visual interference of the driver caused by light and dark changes when entering and exiting the tunnel and reduce the occurrence of accidents.

[0048] The method for dynamically regulating the vehicle window based on electrochromic glass proposed in this embodiment, as Figure 1 shown, specifically includes the following steps:

[0049] Step S1: Based on the map navigation route generated by the in-vehicle navigation system, identify the landmark sites where light conversion occurs on the route and locate the entrances and exits of the sites.

[0050] Specifically, based on the in-vehicle navigation system, a map navigation route is generated according to the starting point and the ending point input by the driver, and the in-vehicle navigation system can display road landmark buildings, so as to accurately identify light conversion landmark sites with large light changes such as tunnels and underground parking lots on the navigation route, and locate the entrances and exits of the landmark sites.

[0051] Step S2: Obtain the real-time position of the vehicle, calculate the distance between the vehicle and the entrance and exit of the site, and determine whether to activate the window dynamic regulation function according to the distance and the driving direction of the vehicle.

[0052] Specifically, the real-time position of the vehicle is located through the GPS in the in-vehicle navigation system. The distance between the vehicle and the entrance and exit of each landmark site can be calculated according to the real-time position. Judgment is made according to the distance and the driving direction of the vehicle. When the distance between the vehicle and the entrance and exit of the site is less than the set distance value (set to 500m in this embodiment), and the driving direction of the vehicle is the direction towards the entrance and exit of the site, the window dynamic regulation function is activated; otherwise, the window dynamic regulation function is still not activated.

[0053] Through the above judgment, the dynamic regulation function is only activated when the vehicle travels near the landmark site. After activation, detection and analysis are carried out, so as to reduce the detection cost on the basis of ensuring the normal execution of the dynamic regulation, and avoid the situation of frequent regulation when detection is incorrect or abnormal, and regulation during normal driving affecting safe driving.

[0054] Step S3: When the function is activated, the scene image in front of the vehicle is obtained in real time, the landmark site in front of the vehicle and the light intensities inside and outside the entrance and exit of the site are identified, and at the same time, the distance between the vehicle and the entrance and exit of the site and the vehicle speed are obtained in real time.

[0055] Specifically, when the above window dynamic regulation function is activated, the binocular vision camera and the distance detection radar carried on the vehicle are turned on to detect the entrances and exits of sites such as tunnels. Among them:

[0056] Step S3.1: Use the binocular vision camera to obtain the scene image of the tunnel entrance in front of the vehicle in real time, and identify the tunnel entrance in front of the vehicle and the light intensities inside and outside the tunnel entrance, including:

[0057] First, according to the scene image in front of the vehicle obtained in real time, use the YOLO target detection algorithm to identify the landmark site in front of the vehicle and extract the regional image of the landmark site.

[0058] Secondly, for the extracted iconic site area image (such as the image of the tunnel entrance area), after image preprocessing, an image region segmentation method of adaptive clustering is adopted to divide the overall region into two parts, and the average brightness is calculated respectively according to the pixel brightness of the two parts. The average brightness of the two parts inside and outside the iconic site entrance and exit is used as the illumination intensity.

[0059] Step S3.1.1: Take the extracted iconic site area image as the original image to be segmented. This image is an RGB image. To ensure the accuracy of subsequent illumination intensity calculation, first preprocess this original RGB image: use bilateral filtering to reduce noise while retaining edge information, and use the method of Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the details of dark and bright areas.

[0060] Step S3.1.2: Adopt an image region segmentation method of adaptive clustering to divide the bright and dark regions of the image, including:

[0061] Step S3.1.2.1: Take the iconic site area image as the image to be segmented, and convert the image to be segmented from RGB to the LAB color space to optimize the color discrimination.

[0062] Step S3.1.2.2: Use Sobel edge detection to extract the high-density edge region in the image to be segmented as the candidate region, and select two pixel points in the candidate region as the initial clustering centers. In this embodiment, in the candidate region, calculate the mean value of the LAB color space of each pixel point, and select the two color pixel points with the largest Euclidean distance as the initial clustering centers. Compared with randomly initializing the selection of clustering centers, the subsequent iterative process can be optimized and the number of iterations can be reduced through the above method.

[0063] Step S3.1.2.3: Based on the initial clustering centers, use an improved K-means clustering algorithm to cluster all pixel points to form two clustering regions. That is, calculate the Euclidean distance from each pixel point to the two clustering centers, and divide it into the nearest cluster according to the distance, and form two clustering regions through the division of the cluster.

[0064] Step S3.1.2.4: Continuously iterate and update the clustering centers until the silhouette coefficient of the two clustering regions reaches the set value or the number of iterations reaches the set value, and complete the region segmentation. That is, based on the updated two clustering regions, recalculate the mean centers of the two clusters, update the clustering centers accordingly, and then iterate and execute the above Step S3.1.2.3 again, continuously iterate and update the clustering centers and clustering regions until the silhouette coefficient of the two clustering regions reaches the set value or the number of iterations reaches the set value, and complete the region segmentation.

[0065] Among them, the calculation formula of the silhouette coefficient is:

[0066]

[0067] In the above formula, a(i) is the average distance between pixel i and other pixels in the same cluster, and b(i) is the minimum average distance from pixel i to another cluster.

[0068] In this embodiment, when the silhouette coefficient S≥0.6 or the number of iterations t≥10, the iteration is terminated.

[0069] Based on the above lightweight clustering optimization, using the improved K-means algorithm, through edge density prediction, the segmentation efficiency of the two regions is improved.

[0070] Step S3.1.2.5: Calculate the average brightness according to the brightness of the pixel points in the two parts of the region respectively, and use the average brightness of the two parts of the region inside and outside the landmark site entrance and exit as the illumination intensity.

[0071] Step S3.2: Use a distance detection radar to obtain the distance between the vehicle and the site entrance and exit in real time.

[0072] Step S3.3: Obtain the real-time vehicle speed during the vehicle's driving through an in-vehicle vehicle speed sensor.

[0073] Step S4: Calculate the target transmittance according to the real-time distance, vehicle speed, and illumination intensity inside and outside the site entrance and exit, determine the optimal adjustment time range in combination with the transmittance adjustment rate, and dynamically adjust the transmittance of the electrochromic glass of the vehicle window within this time range, so that the light intensity inside the vehicle gradually changes to be consistent with the light intensity in the upcoming entering region.

[0074] Among them, the target transmittance calculated according to the real-time distance, vehicle speed, and illumination intensity inside and outside the site entrance and exit can be expressed as:

[0075] T = T min +(T max -T min )×e -k·D / V ;

[0076] Among them, T min is the lowest transmittance, T max is the highest transmittance, k is the environmental attenuation coefficient, D represents the distance, and V represents the vehicle speed.

[0077] Preferably, the environmental attenuation coefficient is dynamically corrected according to the difference in the detected illumination intensity inside and outside the entrance and exit, and the calculation formula of this environmental attenuation coefficient is:

[0078]

[0079] Among them, k0 represents the reference coefficient, which is an initial value set by experiments or experience and represents the default attenuation rate without light difference; α is the adjustment coefficient that controls the influence weight of light difference on k and needs to be calibrated through experiments. For example, α = 0.5 means that when the light difference increases by 1 time the reference value, k increases by 50%. is the light difference proportional term, ΔL = |L out -L in | represents the absolute difference in light intensity inside and outside the entrance and exit, L out represents the light intensity outside the entrance and exit, L in represents the light intensity inside the entrance and exit, L ref represents the light value, which can be set as the average of the internal and external light, that is

[0080] Furthermore, according to the distance, vehicle speed, etc. that change dynamically at each moment, the target light transmittance is calculated. At the same time, the light transmittance adjustment rate is determined based on the difference in internal and external light intensities. This intensity difference is proportional to the light transmittance adjustment rate. When the difference in internal and external light intensities is small, the light transmittance is adjusted gently and slightly. On the contrary, when the difference in internal and external light intensities is large, the adjustment rate of the light transmittance is accelerated. In this way, the window color gradually changes from the current light transmittance to the target light transmittance, and the dimming rate is proportional to the difference in internal and external light intensities to ensure that the light transmittance is stable when arriving at the entrance; then, based on the current light transmittance and the target light transmittance, combined with the light transmittance adjustment rate, the time required for the adjustment to be completed is determined. At the same time, the time when the vehicle enters the tunnel is determined based on the real-time distance and vehicle speed. Based on these two times, the optimal time point can be determined. For example, when the time required for the adjustment to be completed is determined to be T1 and the time when the vehicle enters the tunnel is T2, then at the latest at the moment (T2 - T1), the light transmittance of the electrochromic glass of the window is dynamically adjusted to gradually change the light intensity inside the vehicle to be consistent with the light intensity in the upcoming area, so as to ensure the timeliness of the color change adjustment.

[0081] Preferably, a threshold value of the window light transmittance can be set in advance on the display screen. This threshold value has a minimum limit for ensuring safety. The display screen can display the dimming process and give visual prompts, such as through a gradient progress bar for prompting.

[0082] Further, it is judged according to the real-time position of the vehicle and the position of the entrance and exit of the located site. When it is detected that the vehicle passes a set distance from the entrance and exit of the site (set to 50 m in this embodiment), the light transmittance of the electrochromic glass of the window is restored to the initial light transmittance. That is, when the vehicle completely enters and exits the tunnel, the light transmittance is immediately adjusted to the initial light transmittance. Since the light intensity inside the vehicle has been adjusted to be consistent with the illumination in the tunnel before entering the tunnel, the light transmittance of the window glass can be directly adjusted to the initial value after entering the tunnel. After adjustment, since the vehicle is already in the tunnel, the light intensity inside the vehicle remains unchanged at this time, thereby avoiding the change of light and darkness and the occurrence of visual interference.

[0083] Preferably, when it is detected that the visibility is low in rainy, snowy, foggy days, etc., the dynamic regulation function of the window can be automatically turned off and the driver is prompted that it has been turned off; or the dynamic regulation function of the window can also be manually turned off in bright weather; the function can also be automatically turned off based on safety intervention, that is, judged according to the real-time speed of the vehicle. If the vehicle makes an emergency brake, the dynamic regulation function of the window is automatically turned off, and the light transmittance of the electrochromic glass of the window is restored to the initial light transmittance to avoid the occurrence of other unexpected situations. Among them, the above priority is safety intervention > automatic adjustment > manual operation.

[0084] Embodiment 2

[0085] This embodiment provides a window dynamic regulation system based on electrochromic glass, as Figure 2 shown, including:

[0086] An identification and detection module, including an in-vehicle navigation system for generating a map navigation route and locating landmark site entrances and exits, a binocular vision camera for acquiring an image of the scene in front of the vehicle, a radar for detecting the distance of the vehicle from the site entrance and exit, and a vehicle speed sensor for acquiring the vehicle speed;

[0087] An operation and processing module, including a vehicle controller, for executing the method for dynamically regulating the window based on electrochromic glass proposed in the first aspect to obtain the target light transmittance;

[0088] An execution module, including a window color change controller, for dynamically adjusting the color of the electrochromic glass of the window according to the target light transmittance to adjust the light transmittance.

[0089] Specifically, through the GPS navigation in the recognition and detection module, the forward road is automatically generated according to the destination input by the driver. The iconic sites with large light changes such as tunnels on this route are recognized. According to the actual distance, the dynamic regulation function of the window is turned on, and the driver is prompted to drive carefully. The binocular vision camera and radar are used for detection to accurately measure the distance to the tunnel entrance and the actual light intensity at the entrance. At the same time, the current vehicle speed is obtained by using the vehicle speed sensor. The above information is input into the operation and processing module. The operation and processing module processes the data according to the current input, receives the vehicle speed and distance signals, calculates the time to reach the tunnel entrance, compares it with the change time of the window color change and light transmittance reduction in the vehicle parameters, determines whether to start the color change, and generates a color change control instruction to the execution module to perform the final operation, so that the vehicle completes the dynamic color change of the window and the change of light transmittance reduction before entering the tunnel, reducing the driver's visual obstacle and avoiding the occurrence of traffic accidents.

[0090] Embodiment 3

[0091] This embodiment provides a vehicle, including the window dynamic regulation system based on electrochromic glass proposed in Embodiment 2, or completing the window dynamic regulation method based on electrochromic glass proposed in Embodiment 1.

[0092] The steps and method embodiments involved in Embodiments 2 to 3 above correspond to those in Embodiment 1. For specific implementation manners, reference can be made to the relevant description part of Embodiment 1.

[0093] Those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computer device. Optionally, they can be implemented by program codes executable by the computing device, so that they can be stored in the storage device and executed by the computing device, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps among them can be made into a single integrated circuit module to implement. The present invention is not limited to any specific combination of hardware and software.

[0094] The above are only the preferred embodiments of the present invention. Although the specific implementation manners of the present invention are described in conjunction with the drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that on the basis of the technical solutions of the present invention, various modifications or deformations that can be made without creative labor by those skilled in the art are still within the protection scope of the present invention.

Claims

1. A method for dynamically regulating a vehicle window based on electrochromic glass, characterized in that, Including: Based on the map navigation route generated by the in-vehicle navigation system, identify the light conversion landmark sites on the route and locate the entrances and exits of the sites; Obtain the real-time position of the vehicle, calculate the distance between the vehicle and the entrance / exit of the site, and judge whether to activate the window dynamic regulation function according to the distance and the driving direction of the vehicle; When the function is activated, obtain the real-time scene image in front of the vehicle, identify the landmark site in front of the vehicle and the light intensity inside and outside the entrance / exit of the site, and at the same time obtain the distance between the vehicle and the entrance / exit of the site and the vehicle speed in real time; According to the real-time distance, vehicle speed, and light intensity inside and outside the entrance / exit of the site, calculate the target light transmittance, determine the optimal adjustment time range in combination with the light transmittance adjustment rate, and dynamically adjust the light transmittance of the electrochromic glass of the window within this time range, so that the light intensity inside the vehicle gradually changes to be consistent with the light intensity in the upcoming area.

2. The window dynamic regulation method based on electrochromic glass according to claim 1, characterized in that, Judging whether to activate the window dynamic regulation function according to the distance and the driving direction of the vehicle, including: When the distance between the vehicle and the entrance / exit of the site is less than the set distance value and the driving direction of the vehicle is towards the entrance / exit of the site, activate the window dynamic regulation function; otherwise, do not activate the window dynamic regulation function yet.

3. The window dynamic regulation method based on electrochromic glass according to claim 1, wherein, Obtain the real-time scene image in front of the vehicle in real time, and identify the landmark site in front of the vehicle and the light intensity inside and outside the entrance / exit of the site, including: According to the real-time obtained scene image in front of the vehicle, use the YOLO object detection algorithm to identify the landmark site in front of the vehicle and extract the regional image of the landmark site; For the regional image of the landmark site, after image preprocessing, adopt the image region segmentation method of adaptive clustering to divide the overall region into two partial regions, calculate the average brightness according to the pixel point brightness of the two partial regions respectively, and take the average brightness of the two partial regions inside and outside the entrance / exit of the landmark site as the light intensity.

4. The dynamic regulation method of a vehicle window based on electrochromic glass according to claim 3, wherein Image region segmentation includes: Taking the regional image of the landmark site as the image to be segmented, convert the image to be segmented from RGB to the LAB color space; Using Sobel edge detection, extract the high-density edge region in the image to be segmented as the candidate region, and select two pixel points in the candidate region as the initial clustering centers; Based on the initial clustering centers, use the improved K-means clustering algorithm to cluster all pixel points to form two clustering regions; Continuously iterate and update the clustering centers until the silhouette coefficient of the two clustering regions reaches the set value or the number of iterations reaches the set value, and complete the region segmentation.

5. The dynamic regulation method of a vehicle window based on electrochromic glass according to claim 1, characterized in that, The calculation formula of the target light transmittance is: T = T min +(T max -T min )×e -k·D / V ; Among them, T min is the lowest light transmittance, T max is the highest light transmittance, k is the environmental attenuation coefficient, D represents the distance, and V represents the vehicle speed.

6. The dynamic regulation method for a vehicle window based on electrochromic glass according to claim 5, wherein, The environmental attenuation coefficient is dynamically corrected according to the difference in the detected light intensity inside and outside the entrance / exit, and the calculation formula of this environmental attenuation coefficient is: Among them, k0 represents the reference coefficient, α is the adjustment coefficient, and ΔL = |L out -L in | represents the absolute difference in light intensity inside and outside the entrance and exit, L out represents the light intensity outside the entrance and exit, L in represents the light intensity inside the entrance and exit, L ref represents the light value.

7. The dynamic regulation method of a vehicle window based on electrochromic glass according to claim 1, wherein, Judge according to the real-time position of the vehicle and the located position of the entrance / exit of the site. If it is detected that the vehicle passes the set distance of the entrance / exit of the site, restore the light transmittance of the electrochromic glass of the window to the initial light transmittance.

8. A method for dynamically controlling a vehicle window based on electrochromic glass as claimed in claim 1, wherein Judge according to the real-time speed of the vehicle. If the vehicle brakes emergently, automatically turn off the window dynamic regulation function and restore the light transmittance of the electrochromic glass of the window to the initial light transmittance.

9. A window dynamic regulation system based on electrochromic glass, characterized in that, Including: The recognition and detection module includes a vehicle navigation system for generating a map navigation route and locating the entrance and exit of a landmark site, a binocular vision camera for acquiring the image of the scene in front of the vehicle, a radar for detecting the distance between the vehicle and the entrance and exit of the site, and a vehicle speed sensor for acquiring the vehicle speed; The operation and processing module includes a vehicle controller for executing the window dynamic regulation method based on electrochromic glass as described in any one of claims 1-8 to obtain the target light transmittance; The execution module includes a window color change controller for dynamically adjusting the color of the electrochromic glass of the window according to the target light transmittance to adjust the light transmittance.

10. A vehicle, characterized in that, It includes the window dynamic regulation system based on electrochromic glass as described in claim 9, or completes the window dynamic regulation method based on electrochromic glass as described in any one of claims 1-8.

Images