WO2020186522A1

WO2020186522A1 - Anti-halation vehicle assistant driving system

Info

Publication number: WO2020186522A1
Application number: PCT/CN2019/079101
Authority: WO
Inventors: 王星泽; 闫静; 舒远
Original assignee: 合刃科技（深圳）有限公司
Priority date: 2019-03-21
Filing date: 2019-03-21
Publication date: 2020-09-24
Also published as: CN111344169A

Abstract

An anti-halation vehicle assistant driving system, comprising a binocular camera device (210), an image processing unit (220), a control unit (230) and a dimming glass (240). The binocular camera device (210) is used to collect a target image from the perspective of a driver; the image processing unit (220) is used to obtain plane coordinates of a target light point in the target image according to the target image; the control unit is used to calculate spatial coordinates of the target dimming point on the dimming glass (240) according to planar coordinates of the target light point, obtain a target glass area where the target dimming point is located, obtain a target transmittance required by the target dimming point according to the target image, and send a command to change the transmittance of the target glass area to the dimming glass (240); and the dimming glass (240) is used to adjust the transmittance of the target glass area to a target transmittance according to the command to change the transmittance of the target glass area.

Description

Anti-blooming vehicle auxiliary driving system

Technical field

This application relates to the field of artificial intelligence, and in particular to an anti-blooming vehicle assisted driving system.

Background technique

The glare of a car during a meeting at night is a key factor and an important issue that affects driving safety, especially if the party with weak headlights is strongly illuminated by the other's headlights, a blind spot is formed during the meeting, and you can't see yourself at all. The road conditions are very dangerous, and major traffic accidents often occur as a result. Even if both parties use high beams, the glare still exists, and the result may be mutual harm and affect driving safety.

In order to achieve the effect of anti-blooming, plant isolation belts or light barriers are often set in the middle of two-way lanes to block the blooming caused by the high beams of oncoming vehicles, but such methods are often restricted by urban construction planning and economic conditions. Another way is to add an active near-infrared or passive far-infrared night vision anti-blooming system to the vehicle, but this system is currently only equipped in high-end models, and the infrared night vision anti-blooming mode imaging effect is poor.

Summary of the invention

The present application provides an anti-glare vehicle assisted driving system, which can change the light transmittance of the dimming glass according to the change of light intensity, prevent the occurrence of halo in the driver's field of vision, and thereby improve the safety of the driver.

In the first aspect, the present application provides an anti-blooming vehicle assisted driving system, including: a binocular camera device, an image processing unit, a control unit, and a dimming glass, wherein,

The binocular camera device is used to collect a target picture from the driver's perspective, wherein the target picture includes a target light spot, the target light spot includes at least one of a strong light spot and a weak light spot, and the target light The point is the mapping of the real light point of the natural target in the target picture;

The image processing unit is configured to obtain the plane coordinates of the target light point in the target picture according to the target picture;

The control unit is used to calculate the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light point, and obtain the target glass area where the target dimming point is located, according to the The target picture obtains the target light transmittance required by the target dimming point, and sends an instruction to change the light transmittance of the target glass area to the dimming glass, wherein the dimming glass is divided into a plurality of glass areas;

The dimming glass is used to adjust the light transmittance of the target glass area to the target light transmittance according to an instruction to change the light transmittance of the target glass area.

Optionally, the binocular camera device includes a left camera and a right camera, and the distance between the optical axis of the left camera and the center point of the driver's head is the same as the optical axis of the right camera to the driver's head The distance between the center points is the same, the optical centers of the left camera and the right camera are on the same horizontal line, and the imaging planes of the left camera and the right camera are on the same plane and are the same as those of the left camera. The optical axes of the side camera and the right camera are vertical, and the internal parameters and external parameters of the left camera and the right camera are completely the same.

Optionally, the control unit is specifically configured to: obtain the plane coordinates of multiple vertices of the dimming glass and the plane coordinates of the target light point in the target picture according to the target picture; Formula to obtain the space coordinates of the multiple vertices of the dimming glass and the space coordinates of the target real light point in the target picture to obtain the first parameter equation of the dimming glass plane; according to the target real light point The space coordinates and the space coordinates of the center point of the driver’s head are calculated to calculate the second parameter equation of the straight line formed between the center point of the driver’s head and the target real light point; according to the first parameter equation and the first parameter equation A two-parameter equation is used to calculate the spatial coordinates of the target dimming point on the dimming glass, where the target dimming point is the line formed by the center point of the driver’s head and the target real light point intersecting at the The intersection of the dimming glass planes; according to the spatial coordinates of the target dimming point, the target glass area where the target dimming point is located is obtained.

Optionally, the space coordinate conversion formula is:

Among them, O ₁ (X, Y, Z) is a point in the space coordinate system, (u ₁ , v ₁ ) is the plane coordinate of O ₁ in the image captured by the left camera, (u ₂ , v ₂ ) is the plane coordinates of point O ₁ in the image captured by the right camera, B is the distance between the left camera and the right camera, and f is the left camera and the right camera. The focal length of the side camera, z is the vertical distance between the left camera or the right camera and the dimming glass.

Optionally, the control unit is further configured to obtain the plane coordinates of the multiple vertices of the dimming glass and the plane coordinates of the target light point in the target picture according to the target picture: The target model information of the vehicle and the target distance information between the driver’s seat and the dimming glass; download calibration data, the calibration data includes the vehicle model information, the driver’s seat and the dimming glass Distance information and corresponding first parameter equation information of the dimming glass plane; when the calibration data includes the target vehicle type information and target distance information, the first parameter equation of the dimming glass plane is obtained.

Optionally, the control unit is further configured to obtain external information before sending an instruction to change the light transmittance of the target glass area to the dimming glass, where the external information includes light intensity, position information, temperature information, and One or more of humidity information; the controller is also used to input the external information and the target picture into the dimming model to obtain the target light transmittance required by the target glass area, wherein the dimming The model is a model obtained by pre-training the neural network using the first sample set. When the target light point in the input target picture is a strong light point, the output target light transmittance of the dimming model is lower than the target light point. The target light transmittance output when the light spot is weak, the first sample set includes a plurality of known external information, pictures known to contain the light spot, and corresponding known light transmittance information.

Optionally, the image processing unit is specifically configured to input the target picture into a light spot positioning model to obtain the plane coordinates of the target light spot in the target picture, wherein the light spot positioning model uses a second sample set A model obtained by training a convolutional neural network, and the second sample set includes a plurality of pictures marked with light point coordinates.

Optionally, when the number of the target dimming points is multiple, the method further includes: the control unit obtains the target glass area where each target dimming point is located and the corresponding target dimming point. Light rate; send an instruction to adjust the dimming rate of each target glass area to the corresponding target dimming rate to the dimming glass.

Optionally, the dimming glass is one of automobile windows, airplane glass windows, ship glass windows, building glass windows, automobile windshields, and automobile rearview mirrors.

In a second aspect, a method for assisted driving of an anti-blooming vehicle is provided, and the method includes the following steps:

The binocular camera device collects a target picture from the driver’s perspective, where the target picture includes a target light spot, the target light spot includes at least one of a strong light spot and a weak light spot, and the target light spot is natural Mapping of real light points in the target picture;

The image processing unit obtains the plane coordinates of the target light point in the target picture according to the target picture;

The control unit calculates the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light spot, obtains the target glass area where the target dimming point is located, and obtains all the coordinates according to the target picture The target light transmittance required by the target dimming point, and an instruction to change the light transmittance of the target glass area is sent to the dimming glass, wherein the dimming glass is divided into a plurality of glass areas;

The dimming glass adjusts the light transmittance of the target glass area to the target light transmittance according to an instruction to change the light transmittance of the target glass area.

Optionally, the control unit calculates the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light point, and obtaining the target glass area where the target dimming point is located includes: According to the target picture, obtain the plane coordinates of the multiple vertices of the dimming glass and the plane coordinates of the target light point in the target picture; obtain the dimming glass in the target picture through a space coordinate transformation formula The space coordinates of the multiple vertices and the space coordinates of the target real light point are obtained to obtain the first parameter equation of the dimming glass plane; according to the space coordinates of the target real light point and the space coordinates of the driver’s head center point, calculate The second parameter equation of the straight line formed between the center point of the driver’s head and the target real light point is calculated; according to the first parameter equation and the second parameter equation, the The space coordinates of the target dimming point, the target dimming point is the intersection of the line formed by the center point of the driver’s head and the target light point intersecting the dimming glass plane; according to the space coordinates of the target dimming point To obtain the target glass area where the target dimming point is located.

Optionally, the space coordinate conversion formula is:

Among them, O ₁ (X, Y, Z) is a point in the space coordinate system, (u ₁ , v ₁ ) is the plane coordinate of the O ₁ point in the image taken by the left camera, (u ₂ , v ₂ ) Is the plane coordinate of point O ₁ in the image captured by the right camera, B is the distance between the left camera and the right camera, f is the left camera and the right camera The focal length of z is the vertical distance between the left camera or the right camera and the dimming glass.

Optionally, before the obtaining the plane coordinates of the multiple vertices of the dimming glass and the plane coordinates of the target light spot in the target picture, the method further includes: obtaining target model information of the vehicle And target distance information between the driver’s seat and the dimming glass; download calibration data, the calibration data including the vehicle’s model information, the distance information between the driver’s seat and the dimming glass, and the corresponding The first parameter equation information of the dimming glass plane; when the calibration data includes the target vehicle type information and target distance information, the first parameter equation of the dimming glass plane is obtained.

Optionally, obtaining the target light transmittance required for the target dimming point according to the target picture includes: the control unit obtaining external information, where the external information includes light intensity, position information, temperature information, and humidity One or more of the information; input the external information and the target picture into the dimming model to obtain the target light transmittance required by the target glass area, wherein the dimming model uses a second sample set in advance The model obtained by training the neural network, the obtained model, the dimming model outputs when the target light spot in the input target picture is a strong light spot, and the output target light transmittance is lower than when the target light spot is a weak light spot The target light transmittance of the second sample set includes a plurality of known external information, pictures known to contain light spots, and corresponding known light transmittance information.

Optionally, the image processing unit obtaining the plane coordinates of the target light spot in the target picture according to the target picture includes: the image processing unit inputs the target picture into a light spot positioning model to obtain the target light in the target picture. The plane coordinates of the points, wherein the light point positioning model is a model obtained by training a convolutional neural network using a first sample set, and the first sample set includes a plurality of pictures marked with light point coordinates.

In a third aspect, an electronic device is provided, including a processor, an input device, an output device, and a memory, the processor, input device, output device, and memory are connected to each other, wherein the memory is used to store a computer program, The computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method described in the second aspect above

In a fourth aspect, a computer-readable storage medium is provided. The computer non-transitory storage medium stores a computer program. The computer program includes program instructions that, when executed by a processor, cause the processor to Perform the method of the second aspect above.

Based on the vehicle assisted driving system provided by this application, a binocular camera device is used to collect a target picture from the driver’s perspective, and then an image processing unit is used to obtain the plane coordinates of the target light point in the target picture according to the target picture. Use the control unit to calculate the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light point, obtain the target glass area where the target dimming point is located, and obtain it according to the target picture The target light transmittance required by the target dimming point, and an instruction to change the light transmittance of the target glass area is sent to the dimming glass, so that the dimming glass changes the light transmittance of the target glass area according to the instruction to change the light transmittance of the target glass area. The light transmittance of the target glass area is adjusted to the target light transmittance. When a strong light spot or a weak light spot appears in the driver's field of vision, due to the change in the light transmittance of the target glass area in the dimming glass, the driver's field of view will no longer occur halo phenomenon, thereby improving the driver's driving safety Sex.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative work, other drawings can be obtained from these drawings.

FIG. 1 is a comparison diagram of the effect of a vehicle window dimming glass provided by the present application under power-on and power-off conditions;

Figure 2 is a schematic structural diagram of an anti-blooming vehicle assisted driving system provided by the present application;

Fig. 3 is a schematic structural diagram of a binocular camera device provided by the present application;

4 is a schematic diagram of the principle of calculating a target light transmission point by a control unit provided by the present application;

Fig. 5 is a schematic diagram of a calculation principle of dimming point coordinates provided by the present application;

Fig. 6 is a schematic diagram of adjusting a dimming glass area provided by the present application;

FIG. 7 is a comparison diagram of effects before and after dimming of an anti-blooming rearview mirror provided by the present application;

FIG. 8 is a schematic flowchart of a method for assisted driving of an anti-glare vehicle provided by the present application;

Fig. 9 is a schematic structural diagram of an electronic device provided by the present application.

detailed description

In order to make this application better understood, the following briefly introduces the existing dimming glass.

Light-transmitting glass (Light-transmitting glass) is a new type of special photoelectric glass product with a sandwich structure that combines a liquid crystal film into the middle of two layers of glass, and is integrated by high temperature and high pressure. The user controls the transparent and opaque state of the glass by controlling the on and off of the current. The glass itself not only has all the characteristics of safety glass, but also has the privacy protection function to control whether the glass is transparent or not. Dimmable glass has many advantages, such as: transparent when power is on, opaque when power off, free switching, simple and convenient; The temperature and light changes, by rotating the pressure regulating button, the light intensity and infrared transmittance are automatically adjusted to achieve the effect of temperature and light adjustment; the double-layer laminated technology is safe and firm, with the excellent quality of safety glass, and Sound insulation and heat insulation, strong anti-noise ability; diversified control methods, switch, light control, sound control, temperature control, remote control, remote network control, etc.

Dimming glass has been widely used due to its many advantages. At present, smart dimming glass has been installed in the windows of some brand vehicles to improve safety. Cars equipped with dimming glass are opaque when they are parked and not in use. The thief cannot drive the car away even if they open the door. Because the glass is opaque, the thief cannot see the road ahead. At this time, this type of dimming glass It can also play a role in preventing theft. Secondly, the occlusion of the dimming glass can protect the interior plastic parts of the car, avoid the accelerated aging caused by direct sunlight in the hot summer, and can also achieve the purpose of cooling down and lowering the temperature of the car body, which is more comfortable for its driving. Great benefit. For example, FIG. 1 is a comparison diagram of the effect of a vehicle window dimming glass provided in the present application under power-on and power-off conditions.

The anti-blooming vehicle assisted driving system provided by this application can be used in many fields, such as automobile manufacturing, construction, ship manufacturing, aviation and other fields, and can be used for anti-blooming of automobile windshield and anti-blooming of rearview mirror. The light transmittance of glass windows can be adjusted according to actual conditions, such as anti-blooming for aircraft glass windows, anti-blooming for ship glass windows, and anti-blooming for glass windows of buildings. This application does not make specific decisions regarding the use. However, in order to better understand the present application, the following description will take the anti-blooming of a car windshield as an example.

Fig. 2 is a schematic structural diagram of an anti-glare vehicle assisted driving system provided by the present application, which is applied to the windshield of an automobile. As shown in FIG. 1, the anti-blooming vehicle assisted driving system provided by the present application at least includes: a binocular camera 210, an image processing unit 220, a control unit 230, and a dimming glass 240. Among them, the output terminal of the binocular camera 210 It is connected to the image processing unit 220 and the controller 230, the output end of the image processing unit 220 is connected to the control end 230, and the output end of the controller 230 is connected to the dimming glass 240. It should be understood that the anti-blooming vehicle assisted driving system shown in FIG. 2 may also include more or fewer accessories, which are not specifically limited here.

The binocular camera device 210 is used to collect a target picture from the driver's perspective, where the target picture includes a target light spot, and the target light spot includes at least one of a strong light spot and a weak light spot. The light spot is the mapping of the real light spot in the natural world in the target picture.

In an embodiment, the binocular camera device 210 may include a left camera and a right camera, and the distance between the optical axis of the left camera and the center point of the driver's head is the same as that of the right camera. The distance between the optical axis and the center point of the driver’s head is the same, the optical centers of the left camera and the right camera are on the same horizontal line, and the imaging planes of the left camera and the right camera are on the same horizontal line. On a plane and perpendicular to the optical axes of the left camera and the right camera, the internal parameters and external parameters of the left camera and the right camera are completely the same. That is to say, the binocular camera device can be a parallel binocular stereo vision system structure. In this system, two cameras used to shoot a unified scene are placed horizontally parallel to the optical axis and the imaging plane is placed on the same plane. The interrelationships of two cameras are easier to calculate.

Specifically, FIG. 3 is a schematic structural diagram of a binocular camera device provided by the present application, in which the dimming glass 214 is an automobile windshield. As shown in FIG. 3, the binocular camera device 210 includes a left camera 211 and a right camera 212. The distance between the optical axis of the left camera 211 and the center point O of the driver's head is B/2, and the right The distance between the optical axis of the camera 212 and the center point O of the driver's head is also B/2, where B is the distance (baseline distance) between the centers of the two cameras. The internal parameters and external parameters of the left camera 211 and the right camera 212 are exactly the same. The two cameras are placed horizontally in parallel and their optical axes are parallel to each other. The imaging plane A1 of the left camera 211 and the imaging plane A2 of the right camera 212 are at the same On the plane, it is covered with the dimmer glass 214, which is the plane O ₁ O ₂ O ₄ O ₃ shown in FIG. 2. It should be understood that the dimming glass 214 in the example shown in FIG. 3 is a car windshield and is located directly in front of the driver's line of sight. Therefore, the binocular camera device is placed on both sides of the driver's line of sight, and two cameras can be used instead of human eyes to capture In contrast, after the analysis and processing of related algorithms such as stereo matching, the binocular parallax of the target in the driver's field of vision can be obtained, so as to further obtain the depth information of the target light point and the three-dimensional space coordinate information, which is convenient for the subsequent image processing unit 220 and The control unit 230 performs further processing and analysis.

The image processing unit 220 is configured to obtain the plane coordinates of the target light point in the target picture according to the target picture.

In an embodiment, the image processing unit 220 is specifically configured to input a target picture into a light spot positioning model to obtain the plane coordinates of the target light spot in the target picture, wherein the light spot positioning model uses a second sample A model obtained by training a convolutional neural network is set, and the second sample set includes a plurality of pictures marked with light point coordinates. In other words, the light spot positioning model is used to mark the target light spot in the target picture taken by the binocular camera device 210. Wherein, the second sample set used when training the light spot positioning model may include a first vector set as an input vector and a second vector set as an output vector, and the first vector set includes an unlabeled picture containing the target light spot , The second vector set includes pictures marked with target light spots, and there is a corresponding relationship between the input vector and the output vector, that is, each picture to be marked containing the target light spot corresponds to a picture with the target light spot marked. It should be understood that after marking the target spot using the spot positioning model, the plane coordinates of the target spot located in the picture can be obtained, where the plane coordinate system is the picture coordinate system, and the origin can be the center of the picture or a certain picture. At the top, this application is not specifically limited. However, the pictures taken by either the left camera or the right camera use a unified plane coordinate system for subsequent unified spatial coordinate conversion.

The control unit 230 is configured to calculate the spatial coordinates of the target dimming point on the dimming glass 240 according to the plane coordinates of the target light point, and obtain the target glass area where the target dimming point is located, according to The target picture obtains the target light transmittance required by the target dimming point, and sends an instruction to change the light transmittance of the target glass area to the dimming glass, wherein the dimming glass is divided into a plurality of glass areas .

In an embodiment, the control unit 230 is specifically configured to: obtain the plane coordinates of multiple vertices of the dimming glass 240 in the target picture and the plane coordinates of the target light point according to the target picture; and through the target space coordinate transformation formula, Obtain the space coordinates of the multiple vertices of the dimming glass in the target picture and the space coordinates of the target real light point, and obtain the first parameter equation of the 2 plane of the dimming glass; according to the space coordinates of the target real light point and driving The space coordinates of the center point of the driver’s head are calculated, and the second parameter equation of the straight line formed between the center point of the driver’s head and the target light point is calculated; according to the first parameter equation and the second parameter equation, the The space coordinates of the target dimming point on the dimming glass, the target dimming point is the intersection of the line formed by the center point of the driver’s head and the target light point intersecting the plane of the dimming glass; The spatial coordinates of the light point are obtained to obtain the target glass area where the target dimming point is located. In other words, the control unit 230 is mainly used to calculate the target glass area of the dimming glass 240 that needs to be dimmed according to the plane coordinates of the target light spot sent by the image processing unit 220.

For example, FIG. 4 is a schematic diagram of the principle of calculating the target light point by the control unit provided by the present application. After receiving the plane coordinates of the target light point sent by the image processing unit 220, the control unit 230 obtains the target light point according to the coordinate conversion formula. The spatial coordinates of is W(X,Y,Z), and the spatial coordinates of the center point of the driver’s head are O(X ₀ ,Y ₀ ,Z ₀ ). According to the coordinates of the two points, the linear equation formed between the center point of the driver's head and the target light point can be calculated, that is, the second parameter equation. Then according to the plane coordinates of the driver’s head center point and the more than 240 vertices of the windshield, that is, the plane coordinates of any three vertices in O ₁ O ₂ O ₄ O ₃ shown in Figure 4, the coordinate conversion formula is used Then the space coordinates corresponding to the three vertices can be obtained, and the plane equation of a plane can be determined according to the three points, that is, the first parameter equation. Therefore, after obtaining the plane equation and the straight line equation, the coordinates of the intersection point of the plane and the straight line can be calculated immediately through the combination of the two equations, that is, the coordinates of the target dimming point. The dimming point calculation method shown in FIG. 4 is only used for illustration, and other methods for calculating the intersection point of a straight line and a plane may also be used in this application, which is not specifically limited.

In an embodiment, the space coordinate conversion formula is:

Among them, O ₁ (X, Y, Z) is a point in the space coordinate system, (u ₁ , v ₁ ) is the plane coordinate of the O ₁ point in the image taken by the left camera, (u ₂ , v ₂ ) Is the plane coordinate of point O ₁ in the image taken by the right camera, B is the distance between the left camera and the right camera, f is the focal length of the left camera and the right camera, and z is the left camera Or the vertical distance between the right camera and the dimming glass.

The derivation method of the coordinate conversion formula will be described below. Taking the structure of the binocular camera device shown in FIG. 3 as an example, the control unit 230 calculates the target glass area according to the plane coordinates of the target light point. As shown, FIG. 5 is a schematic diagram of the calculation principle of dimming point coordinates provided by the present application. The structure of the binocular camera device shown in FIG. 5 is exactly the same as that of FIG. 3. The distance between the center of the two camera lenses (baseline distance ) Is B, the driver’s head is at the center point of the left and right cameras, the vertical distance between the left camera or the right camera and the dimming glass is z, and the focal lengths of both cameras are f . Suppose the coordinate system of the left camera and the right camera are O ₁ x ₁ y ₁ z ₁ and O ₂ x ₂ y ₂ z _{2 respectively} . For a vertex O _{1 of the} windshield, set this point in the left camera coordinate system and the right camera The coordinates in the coordinate system are (x ₁ , y ₁ , z ₁ ) and (x ₂ , y ₂ , z ₂ ), and the plane coordinates of point O ₁ in the image taken by the left camera are (u ₁ , v ₁ ), the image coordinates of O ₁ point in the image taken by the right camera are (u ₂ , v ₂ ), then (u ₁ -u ₂ ) is called the disparity value of O ₁ point in the visual system, and the left camera The coordinate system is a space coordinate system. According to the space coordinates of O ₁ point as (x ₁ , y ₁ , z ₁ ), the relationship between the plane coordinate system and the space coordinate system at this time can be obtained as:

among them,

Substitute it into formula (2) and formula (3) to obtain the coordinate conversion formula (1) provided by this application, namely:

It should be understood that in the calculation process, since the focal length f and the baseline distance B are generally in millimeter units, and (u ₁ -u ₂ ) are pixel units, the calculation can be carried out according to the parameter unit, or the focal length f and the baseline distance B are The calibrated value after unit conversion directly according to the pixel unit. Therefore, according to formula (1), as long as the plane coordinates of a certain point in the images captured by the left and right cameras are obtained, its spatial coordinates can be obtained, so the spatial coordinates of other vertices of the windshield can be calculated. In this way, the plane equation of the dimmer glass plane O ₁ O ₂ O ₄ O ₃ in the space coordinate system is determined. If the real light point W of the target is detected in the camera images on the left and right sides, after obtaining the plane coordinates of W, the space coordinates of point W can be calculated according to formula (1), and the space of the center point O of the driver’s head is known Coordinates, two points can determine the linear equation of a straight line OW, the intersection of the straight line OW and the light-adjusting glass plane O ₁ O ₂ O ₄ O ₃ is the projection point W', W of the target real light point W on the light-adjusting glass 'The target glass area is the area where the dimming glass needs to be dimmed. After reducing the light transmittance of the area that needs to be dimmed, the strong light generated by the target real light point W will be blocked by the target glass area in the dimming glass, and other glass areas are still in the state of high light transmittance, thereby preventing The halo phenomenon occurs in the driver's field of vision, which makes the ambient light seen by the driver softer. This process does not require any manual intervention, which can ensure the driver's driving safety to the greatest extent.

In an embodiment, the control unit is further configured to obtain the target model information of the vehicle before obtaining the plane coordinates of multiple vertices of the dimming glass and the plane coordinates of the target light points in the target picture according to the target picture And the target distance information between the driver's seat and the dimming glass; download calibration data, the calibration data includes the vehicle model information, the distance information between the driver's seat and the dimming glass, and the corresponding dimming glass plane The first parameter equation information; when the calibration data includes the target vehicle type information and target distance information, the first parameter equation of the dimming glass plane is obtained. It is understandable that because the windshield of the same model of car has the same size, if the distance between the driver’s seat and the dimming glass is the same, in other words, when the driver’s seat selects the same gear, the left camera and the The distance B between the cameras on the right, the focal length f selected by the camera, and the vertical distance z between the dimming glass of the camera can all be the same, and the car models are the same models, and the car windshield has a fixed size. Therefore, the calibration data can be downloaded directly at this time, without recalculating the first parameter equation information of the dimming glass plane. It should be understood that the same vehicle can also be downloaded directly without recalculating the first parameter equation of the dimming glass plane and the space coordinates of the driver's head center.

In an embodiment, the control unit 230 is further configured to obtain external information before sending an instruction to change the light transmittance of the target glass area to the dimming glass 240, where the external information includes light intensity and position information. One or more of temperature information and humidity information; the controller is also used to input the external information and the target picture into the dimming model to obtain the target light transmittance required by the target glass area, wherein: The dimming model is a model obtained by pre-training the neural network using the first sample set. When the target light point in the input target picture is a strong light point, the output target light transmittance of the dimming model is lower than The target light transmittance output when the target light spot is a weak light spot, and the first sample set includes a plurality of known external information, pictures known to include the light spot, and corresponding known light transmittance information. In other words, the control unit 230 is used to calculate the coordinates of the target dimming point, and is also used to calculate the target light transmittance to be modified by the target dimming point. Wherein, the target light transmittance can be obtained through a dimming model, and the dimming model can be a model obtained by training a neural network using the first sample set. Here, the first sample set used when training the dimming model may contain multiple known external information as input vectors, pictures known to contain light spots, and multiple transmittance information as output vectors. And there is a corresponding relationship between the input vector and the output vector, that is, each picture containing a light spot and external information corresponds to a light transmittance. The trained dimming model can enable the control unit 230 to automatically control the dimming glass 240 to adjust the light transmittance of each glass area according to external information such as external temperature, light intensity, geographic location and humidity, thereby improving the safety of the driver. Not affected by ambient light.

In an embodiment, when the number of the target dimming points is multiple, the control unit 230 is further configured to: obtain the target glass area where each target dimming point is located and the corresponding target Dimming rate: Send an instruction to adjust the dimming rate of each target glass area to the corresponding target dimming rate to the dimming glass 240. It should be understood that the dimming glass 240 can be divided into hundreds of glass areas, each glass area has a corresponding area number, and the light transmittance of each glass area can be controlled by connecting to an external circuit according to the area number. The unit 230 is independently controlled, that is, each area can be set to a different light transmittance. For example, FIG. 6 is a schematic diagram of the adjustment of a dimming glass area provided by the present application, in which light point A is a projection point of a strong light point on the light-transmitting glass, and light point B is a weak light point on the light-transmitting glass According to the dimming model, the control unit can obtain the target light transmittance of light point A as A1, the target light transmittance of light point B is B1, and the glass area to which the strong light point A belongs is area 1-9 , The glass area to which the weak light point B belongs is area 10. Therefore, the control unit can send an instruction to adjust the light transmittance of glass area 1-9 to A1 and adjust the light transmittance of glass area 10 to B1 to the dimming glass , While the light transmittance of other areas remains unchanged, that is, the glass in other areas is still transparent. It is understandable that because the dimming state of each area of the light-transmitting glass is completely independent, the image of the driver's entire field of view is clear, which ensures that the driver's field of view is not strong without affecting the driver's field of view. The presence of light spots avoids the halo phenomenon and improves the safety of the driver in driving the vehicle.

In an embodiment, the method for the control unit 230 to control the dimming glass 240 may be one or more of a switch, voice control, remote control, remote network, or multi-sensor control method, which is not specifically limited in this application.

The dimming glass 240 is used to adjust the light transmittance of the target glass area to the target light transmittance according to an instruction to change the light transmittance of the target glass area. Among them, the dimming glass can be car windows, aircraft glass windows, ship glass windows, building glass windows, etc., and can also be applied to other application scenarios where the transmittance of the dimming glass needs to be adjusted according to light conditions. This application There is no specific limitation.

For example, the dimming glass 240 provided in the present application can also be a vehicle rearview mirror as shown in FIG. 7. When the headlights of the rear car shine on the interior rearview mirror, the binocular camera device obtains the target light spot After the image processing unit obtains the plane coordinates of the target light spot, the control unit calculates the target dimming area in the vehicle rearview mirror according to the plane coordinates of the target light spot, and sends to the vehicle rearview mirror to modify the light transmission of the target dimming area The speed command makes the rearview mirror adjust the liquid crystal layer of the mirror surface of the target dimming area, and the color of the rearview mirror becomes darker. The strong light generated by the following car can be absorbed by the mirror surface, so that the light in the driver’s line of sight becomes soft and improves The driving safety of the driver. The effect of the rearview mirror before and after dimming can be shown in Figure 7. It should be understood that the above examples are only for illustration, and this application does not make specific limitations.

In the above system, the target picture of the driver’s perspective is collected by using a binocular camera device, and then the image processing unit is used to obtain the plane coordinates of the target light point in the target picture according to the target picture, and then the control unit is used according to the The plane coordinates of the target light spot, the spatial coordinates of the target dimming point on the dimming glass are calculated, the target glass area where the target dimming point is obtained, and the target dimming point is obtained according to the target picture The required target light transmittance, and send an instruction to change the light transmittance of the target glass area to the dimming glass, so that the dimming glass transmits the light of the target glass area according to the instruction to change the light transmittance of the target glass area The rate is adjusted to the target light transmittance. Through the above system, when a strong light spot or a weak light spot appears in the driver's field of vision, because the light transmittance of the target glass area in the dimming glass has changed, the driver's field of vision no longer occurs halo phenomenon, thereby improving driving The safety of the driver.

FIG. 8 is a schematic flowchart of a method for assisted driving of an anti-blooming vehicle provided by the present application. The method includes the following steps:

S801: The binocular camera device collects a target picture from the driver's perspective, where the target picture includes a target light spot, the target light spot includes at least one of a strong light spot and a weak light spot, and the target light spot is The mapping of natural light points in the target picture.

In an embodiment, the binocular camera device may include a left camera and a right camera, and the distance between the optical axis of the left camera and the center point of the driver's head is equal to that of the right camera. The distance between the axis and the center point of the driver’s head is the same, the optical centers of the left camera and the right camera are on the same horizontal line, and the imaging planes of the left camera and the right camera are on the same plane Above and perpendicular to the optical axes of the left camera and the right camera, the internal parameters and external parameters of the left camera and the right camera are completely the same. That is to say, the binocular camera device can be a parallel binocular stereo vision system structure. In this system, two cameras used to shoot a unified scene are placed horizontally parallel to the optical axis and the imaging plane is placed on the same plane. The interrelationships of two cameras are easier to calculate.

Specifically, FIG. 3 is a schematic structural diagram of a binocular camera device provided by the present application, in which the dimming glass is an automobile windshield. As shown in FIG. 3, the binocular camera device 210 includes a left camera 211 and a right camera 212. The distance between the optical axis of the left camera 211 and the center point O of the driver's head is B/2, and the right The distance between the optical axis of the camera 212 and the center point O of the driver's head is also B/2, where B is the distance (baseline distance) between the centers of the two cameras. The internal parameters and external parameters of the left camera 211 and the right camera 212 are exactly the same. The two cameras are placed horizontally in parallel and their optical axes are parallel to each other. The imaging plane A1 of the left camera 211 and the imaging plane A2 of the right camera 212 are at the same The plane is covered with dimming glass, which is the plane O ₁ O ₂ O ₄ O ₃ shown in FIG. 2. It should be understood that the dimming glass in the example shown in Figure 3 is a car windshield, which is located directly in front of the driver’s line of sight. Therefore, the binocular camera device is placed on both sides of the driver’s line of sight, and two cameras can be used instead of the human eye to collect images. In contrast, after the analysis and processing of related algorithms such as stereo matching, the binocular parallax of the driver's field of view scene target can be obtained, so as to further obtain the depth information of the target light spot and the three-dimensional space coordinate information, which is convenient for the subsequent image processing unit and control unit For further processing and analysis.

S802: The image processing unit obtains the plane coordinates of the target light point in the target picture according to the target picture.

In an embodiment, the image processing unit obtaining the plane coordinates of the target light spot in the target picture according to the target picture includes: the image processing unit inputs the target picture into a light spot positioning model to obtain the target picture The plane coordinates of the target light point, wherein the light point positioning model is a model obtained by training a convolutional neural network using a first sample set, and the first sample set includes a plurality of pictures marked with light point coordinates . In other words, the light spot positioning model is used to mark the target light spot in the target picture taken by the binocular camera device. Wherein, the second sample set used when training the light spot positioning model may include a first vector set as an input vector and a second vector set as an output vector, and the first vector set includes an unlabeled picture containing the target light spot , The second vector set includes pictures marked with target light spots, and there is a corresponding relationship between the input vector and the output vector, that is, each picture to be marked containing the target light spot corresponds to a picture with the target light spot marked. It should be understood that after marking the target spot using the spot positioning model, the plane coordinates of the target spot located in the picture can be obtained, where the plane coordinate system is the picture coordinate system, and the origin can be the center of the picture or a certain picture. At the top, this application is not specifically limited. However, the pictures taken by either the left camera or the right camera use a unified plane coordinate system for subsequent unified spatial coordinate conversion.

S803: The control unit calculates the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light point, obtains the target glass area where the target dimming point is located, and obtains all the coordinates according to the target picture. The target light transmittance required by the target dimming point is described, and an instruction to change the light transmittance of the target glass region is sent to the dimming glass, wherein the dimming glass is divided into a plurality of glass regions.

In an embodiment, the control unit calculates the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light point, and obtains the target glass area where the target dimming point is located include:

According to the target picture, the plane coordinates of the multiple vertices of the dimming glass in the target picture and the plane coordinates of the target light point are obtained; through the space coordinate transformation formula, the spatial coordinates of the multiple vertices of the dimming glass and all the points in the target picture are obtained. According to the space coordinates of the real light point of the target, the first parameter equation of the dimming glass plane is obtained; according to the space coordinates of the real light point of the target and the space coordinates of the driver’s head center point, the driver’s head center point and The second parameter equation of the straight line formed between the target real light points; according to the first parameter equation and the second parameter equation, the spatial coordinates of the target light adjustment point on the dimming glass are calculated, so The target dimming point is the intersection of the straight line formed by the center point of the driver's head and the target light point intersecting the dimming glass plane; according to the spatial coordinates of the target dimming point, the target dimming point is obtained The target glass area. In other words, the control unit is mainly used to calculate the area of the target glass that needs to be dimmed for the dimming glass according to the plane coordinates of the target light spot sent by the image processing unit.

For example, FIG. 4 is a schematic diagram of the principle of calculating the target light transmission point by the control unit provided by the present application. After the control unit receives the plane coordinates of the target light point sent by the image processing unit, it obtains the space of the target light point according to the coordinate conversion formula. The coordinates are W(X,Y,Z), and the space coordinates of the center point of the driver's head are O(X ₀ ,Y ₀ ,Z ₀ ). According to the coordinates of the two points, the linear equation formed between the center point of the driver's head and the target light point can be calculated, that is, the second parameter equation. According to the plane coordinates of the center point of the driver's head and the multiple vertices of the windshield, that is, the plane coordinates of any three vertices in O ₁ O ₂ O ₄ O ₃ shown in Figure 4, the coordinate conversion formula is used. The space coordinates corresponding to the three vertices can be obtained, and the plane equation of a plane can be determined according to the three points, that is, the first parameter equation. Therefore, after obtaining the plane equation and the straight line equation, the coordinates of the intersection point of the plane and the straight line can be calculated immediately through the combination of the two equations, that is, the coordinates of the target dimming point. The dimming point calculation method shown in FIG. 4 is only used for illustration, and other methods for calculating the intersection point of a straight line and a plane may also be used in this application, which is not specifically limited.

In one embodiment, the space coordinate conversion formula is formula (1), where O ₁ (X, Y, Z) is a point in the space coordinate system, (u ₁ , v ₁ ) is O ₁ point on the left The plane coordinates in the image captured by the side camera, (u ₂ , v ₂ ) is the plane coordinate of the O ₁ point in the image captured by the right camera, B is the distance between the left camera and the right camera, f Is the focal length of the left camera and the right camera, and z is the vertical distance between the left camera or the right camera and the dimming glass.

The derivation method of the coordinate conversion formula will be described below. Taking the structure of the binocular camera device shown in FIG. 3 as an example, the control unit 230 calculates the target glass area according to the plane coordinates of the target light point. As shown, FIG. 5 is a schematic diagram of the calculation principle of dimming point coordinates provided by the present application. The structure of the binocular camera device shown in FIG. 5 is exactly the same as that of FIG. 3. The distance between the center of the two camera lenses (baseline distance ) Is B, the driver’s head is at the center point of the left and right cameras, the vertical distance between the left camera or the right camera and the dimming glass is z, and the focal lengths of both cameras are f . Suppose the coordinate system of the left camera and the right camera are O ₁ x ₁ y ₁ z ₁ and O ₂ x ₂ y ₂ z _{2 respectively} . For a vertex O _{1 of the} windshield, set this point in the left camera coordinate system and the right camera The coordinates in the coordinate system are (x ₁ , y ₁ , z ₁ ) and (x ₂ , y ₂ , z ₂ ), and the plane coordinates of point O ₁ in the image taken by the left camera are (u ₁ , v ₁ ), the image coordinates of point O ₁ in the image captured by the right camera are (u ₂ , v ₂ ), and the coordinate system of the left camera is the spatial coordinate system, then the spatial coordinates of point O ₁ are (x ₁ , y ₁ , Z ₁ ), so the relationship between the plane coordinate system and the space coordinate system at this time can be obtained as formula (2), where,

Put it into formula (2) and formula (3) to obtain the coordinate conversion formula provided by this application, that is, formula (1). It should be understood that in the calculation process, since the focal length f and the baseline distance B are generally in millimeter units, and (u ₁ -u ₂ ) are pixel units, the calculation can be carried out according to the parameter unit, or the focal length f and the baseline distance B are The calibrated value after unit conversion directly according to the pixel unit. Therefore, according to formula (1), as long as the plane coordinates of a certain point in the images captured by the left and right cameras are obtained, its spatial coordinates can be obtained, so the spatial coordinates of other vertices of the windshield can be calculated. In this way, the plane equation of the dimmer glass plane O ₁ O ₂ O ₄ O ₃ in the space coordinate system is determined. If the real light point W of the target is detected in the camera images on the left and right sides, after obtaining the plane coordinates of W, the space coordinates of point W can be calculated according to formula (1), and the space of the center point O of the driver’s head is known Coordinates, two points can determine the linear equation of a straight line OW, the intersection of the straight line OW and the light-adjusting glass plane O ₁ O ₂ O ₄ O ₃ is the projection point W', W of the target real light point W on the light-adjusting glass 'The target glass area is the area where the dimming glass needs to be dimmed. After reducing the light transmittance of the area that needs to be dimmed, the strong light generated by the target real light point W will be blocked by the target glass area in the dimming glass, and other glass areas are still in the state of high light transmittance, thereby preventing The halo phenomenon occurs in the driver's field of vision, which makes the ambient light seen by the driver softer. This process does not require any manual intervention, which can ensure the driver's driving safety to the greatest extent.

In an embodiment, before the obtaining the plane coordinates of the multiple vertices of the dimming glass and the plane coordinates of the target light point in the target picture, the method further includes:

Acquire the target model information of the vehicle and the target distance information between the driver's seat and the dimming glass; download calibration data, the calibration data includes the vehicle's model information, the distance between the driver's seat and the dimming glass Information and the corresponding first parameter equation information of the dimming glass plane; when the calibration data includes the target vehicle type information and target distance information, the first parameter equation of the dimming glass plane is obtained. It is understandable that because the windshield of the same model of car has the same size, if the distance between the driver’s seat and the dimming glass is the same, in other words, when the driver’s seat selects the same gear, the left camera and the The distance B between the right cameras and the focal length f selected by the camera can be the same, and the car model is the same model, and the car windshield is a fixed size, so the calibration data can be downloaded directly without recalculating the dimming glass The first parameter equation information of the plane. It should be understood that the same vehicle can also be downloaded directly without recalculating the first parameter equation of the dimming glass plane and the space coordinates of the driver's head center.

In an embodiment, obtaining the target light transmittance required for the target dimming point according to the target picture includes: the control unit obtaining external information, wherein the external information includes light intensity, position information, and temperature information And one or more of humidity information; input the external information and the target picture into the dimming model to obtain the target light transmittance required by the target glass area, wherein the dimming model uses the second The model obtained by training the neural network on the sample set, and the obtained model. When the target light spot in the input target picture is a strong light spot, the dimming model outputs a target light transmittance lower than the target light spot as a weak light spot The second sample set includes a plurality of known external information, pictures known to contain light spots, and corresponding known light transmittance information. That is to say, the control unit is used to calculate the coordinates of the target dimming point, and also used to calculate the target light transmittance to be modified by the target dimming point. Wherein, the target light transmittance can be obtained through a dimming model, and the dimming model can be a model obtained by training a neural network using the first sample set. Here, the first sample set used when training the dimming model may contain multiple known external information as input vectors, pictures known to contain light spots, and multiple transmittance information as output vectors. And there is a corresponding relationship between the input vector and the output vector, that is, each picture containing a light spot and external information corresponds to a light transmittance. The trained dimming model can enable the control unit to automatically control the dimming glass to adjust the light transmittance of each glass area according to external information such as external temperature, light intensity, geographic location and humidity, thereby improving the safety of the driver’s driving. The influence of ambient light.

In an embodiment, when the number of the target dimming points is multiple, the method further includes: the control unit obtains the target glass area where each target dimming point is located and the corresponding Target dimming rate; sending an instruction to adjust the dimming rate of each target glass area to a corresponding target dimming rate to the dimming glass. It should be understood that the dimming glass can be divided into hundreds to thousands of glass areas, each glass area has a corresponding area number, and the light transmittance of each glass area can be independently controlled by an external circuit according to the area number. That is, each area can be set to different light transmittance. For example, FIG. 6 is a schematic diagram of the adjustment of a dimming glass area provided by the present application, in which light point A is a projection point of a strong light point on the light-transmitting glass, and light point B is a weak light point on the light-transmitting glass According to the dimming model, the control unit can obtain the target light transmittance of light point A as A1, the target light transmittance of light point B is B1, and the glass area to which the strong light point A belongs is area 1-9 , The glass area to which the weak light point B belongs is area 10. Therefore, the control unit can send an instruction to adjust the light transmittance of glass area 1-9 to A1 and adjust the light transmittance of glass area 10 to B1 to the dimming glass , While the light transmittance of other areas remains unchanged, that is, the glass in other areas is still transparent. It is understandable that because the dimming state of each area of the light-transmitting glass is completely independent, the image of the driver's entire field of view is clear, which ensures that the driver's field of view is not strong without affecting the driver's field of view. The presence of light spots avoids the halo phenomenon and improves the safety of the driver in driving the vehicle.

In an embodiment, the method for the control unit to control the dimming glass may be one or more of a switch, voice control, remote control, remote network or multi-sensor control method, which is not specifically limited in this application.

S804: The dimming glass adjusts the light transmittance of the target glass area to the target light transmittance according to the instruction for changing the light transmittance of the target glass area.

In an embodiment, the dimming glass can be car windows, aircraft glass windows, ship glass windows, building glass windows, etc., and can also be used in other applications that need to adjust the transmittance of the dimming glass according to light conditions The scenario is not specifically limited in this application.

For example, the dimming glass provided by the present application can also be a vehicle rearview mirror as shown in FIG. 7. When the headlights of the rear car shine on the interior rearview mirror, the binocular camera device obtains the target light spot. Picture, after the image processing unit obtains the plane coordinates of the target light spot, the control unit calculates the target dimming area in the vehicle rearview mirror according to the plane coordinates of the target light spot, and sends it to the vehicle rearview mirror to modify the light transmittance of the target dimming area The command makes the rearview mirror adjust the liquid crystal layer of the mirror surface of the target dimming area, and the color of the rearview mirror becomes darker. The strong light generated by the following car can be absorbed by the mirror surface, so that the light in the driver’s line of sight becomes soft and improves driving The safety of the driver. The effect of the rearview mirror before and after dimming can be shown in Figure 7. It should be understood that the above examples are only for illustration, and this application does not make specific limitations.

In the above method, the target picture of the driver’s perspective is collected by using a binocular camera device, and then the image processing unit is used to obtain the plane coordinates of the target light point in the target picture according to the target picture, and then the control unit is used according to the The plane coordinates of the target light spot, the spatial coordinates of the target dimming point on the dimming glass are calculated, the target glass area where the target dimming point is obtained, and the target dimming point is obtained according to the target picture The required target light transmittance, and send an instruction to change the light transmittance of the target glass area to the dimming glass, so that the dimming glass transmits the light of the target glass area according to the instruction to change the light transmittance of the target glass area The rate is adjusted to the target light transmittance. Through the above method, when a strong light spot or a weak light spot appears in the driver's field of view, because the light transmittance of the target glass area in the dimming glass has changed, the driver's field of view will no longer occur halo phenomenon, thereby improving driving The safety of the driver.

FIG. 9 is a schematic block diagram of the structure of an electronic device according to an embodiment of the present application. As shown in FIG. 9, the electronic device in this embodiment may include: one or more processors 901; one or more input devices 902, one or more output devices 903, and a memory 904. The aforementioned processor 901, input device 902, output device 903, and memory 904 are connected via a bus 905. The memory 902 is configured to store a computer program, and the computer program includes program instructions, and the processor 901 is configured to execute the program instructions stored in the memory 902.

In the embodiment of this application, the processor 901 may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, DSPs, application specific integrated circuits (ASICs), Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The input device 902 may include a touch panel, a fingerprint sensor (used to collect user fingerprint information and fingerprint orientation information), a microphone, etc., and the output device 903 may include a display (LCD, etc.), a speaker, and the like.

The memory 904 may include volatile memory, such as RAM; the memory may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk (HDD), or solid-state hard disk. (Solid-State Drive, SSD), the storage may also include a combination of the foregoing types of storage. The memory 904 may adopt centralized storage or distributed storage, which is not specifically limited here. It is understandable that the memory 904 is used to store computer programs, such as computer program instructions. In the embodiment of the present application, the memory 904 may provide instructions and data to the processor 901.

In specific implementation, the processor 901, the input device 902, the output device 903, the memory 904, and the bus 905 described in the embodiments of the present application can execute any of the embodiments of the anti-blooming vehicle assisted driving method provided in the present application. The described implementation method will not be repeated here.

In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, the present application is implemented. The implementation described in any embodiment of the provided anti-blooming vehicle assisted driving method will not be repeated here.

The computer-readable storage medium may be the internal storage unit of the terminal described in any of the foregoing embodiments, such as the hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a Smart Media Card (SMC), or a Secure Digital (SD) card , Flash Card, etc. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

A person of ordinary skill in the art may realize that the units and algorithm steps of the examples described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two, in order to clearly illustrate the hardware and software Interchangeability. In the above description, the composition and steps of each example have been generally described in terms of function. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

In the several embodiments provided in this application, it should be understood that the disclosed electronic device, system, and method may be implemented in other ways. For example, the electronic device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined. Or it can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments of the present application.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of this application is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium It includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory, random access memory, magnetic disk or optical disk and other media that can store program codes.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application.

Claims

An anti-blooming vehicle auxiliary driving system, which is characterized by comprising: a binocular camera device, an image processing unit, a control unit and a dimming glass,

The binocular camera device is used to collect a target picture from the driver's perspective, wherein the target picture includes a target light spot, the target light spot includes at least one of a strong light spot and a weak light spot, and the target light The point is the mapping of the real light point of the natural target in the target picture;

The image processing unit is configured to obtain the plane coordinates of the target light point in the target picture according to the target picture;

The control unit is used to calculate the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light point, and obtain the target glass area where the target dimming point is located, according to the The target picture obtains the target light transmittance required by the target dimming point, and sends an instruction to change the light transmittance of the target glass area to the dimming glass, wherein the dimming glass is divided into a plurality of glass areas;

The dimming glass is used to adjust the light transmittance of the target glass area to the target light transmittance according to an instruction to change the light transmittance of the target glass area.
The system according to claim 1, wherein the binocular camera device comprises a left camera and a right camera, and the distance between the optical axis of the left camera and the center point of the driver’s head is the same as that of the right camera. The distance between the optical axis of the side camera and the center point of the driver’s head is the same, the optical centers of the left camera and the right camera are on the same horizontal line, and the imaging planes of the left camera and the right camera On the same plane and perpendicular to the optical axes of the left camera and the right camera, the internal parameters and external parameters of the left camera and the right camera are completely the same.
The system according to claim 1, wherein the control unit is specifically configured to:

Obtaining, according to the target picture, the plane coordinates of the multiple vertices of the dimming glass and the plane coordinates of the target light point in the target picture;

Obtain the spatial coordinates of the multiple vertices of the dimming glass in the target picture and the space coordinates of the real light points of the target through the space coordinate transformation formula, and obtain the first parameter equation of the dimming glass plane;

According to the space coordinates of the target real light point and the space coordinates of the driver's head center point, calculate the second parameter equation of the straight line formed between the driver's head center point and the target real light point;

According to the first parameter equation and the second parameter equation, the spatial coordinates of the target dimming point on the dimming glass are calculated, and the target dimming point is the center point of the driver’s head and the The straight line formed by the real light spot of the target intersects the intersection of the plane of the dimming glass;

Obtain the target glass area where the target dimming point is located according to the spatial coordinates of the target dimming point.
The system according to claim 3, wherein the spatial coordinate conversion formula is:

Among them, O 1 (X, Y, Z) is a point in the space coordinate system, (u 1 , v 1 ) is the plane coordinate of O 1 in the image captured by the left camera, (u 2 , v 2 ) is the plane coordinates of point O 1 in the image captured by the right camera, B is the distance between the left camera and the right camera, and f is the left camera and the right camera. The focal length of the side camera, z is the vertical distance between the left camera or the right camera and the dimming glass.
The system according to claim 3, wherein the control unit is further configured to obtain the plane coordinates of multiple vertices of the dimming glass and the target light in the target picture according to the target picture. Before the plane coordinates of the point:

Acquiring target model information of the vehicle and target distance information between the driver's seat and the dimming glass;

Download calibration data, the calibration data including vehicle model information, distance information between the driver's seat and the dimming glass, and corresponding first parameter equation information of the dimming glass plane;

When the calibration data includes the target vehicle type information and the target distance information, the first parameter equation of the dimming glass plane is obtained.
The system of claim 4, wherein:

The control unit is also used to obtain external information before sending an instruction to change the light transmittance of the target glass area to the dimming glass, where the external information includes light intensity, position information, temperature information, and humidity information. One or more

The controller is also used to input the external information and the target picture into a dimming model to obtain the target light transmittance required by the target glass area, wherein the dimming model uses the first sample in advance A model obtained by training a neural network, the dimming model when the target light spot in the input target picture is a strong light spot, and the output target light transmittance is lower than the target light spot, which is weak light The target light transmittance output at the point of time, the first sample set includes a plurality of known external information, pictures known to contain light points, and corresponding known light transmittance information.
The system according to claim 1, wherein the image processing unit is specifically configured to input a target picture into a light spot positioning model to obtain the plane coordinates of the target light spot in the target picture, wherein the light The point positioning model is a model obtained by training a convolutional neural network using a second sample set, and the second sample set includes a plurality of pictures marked with light point coordinates.
An anti-blooming vehicle assisted driving method, characterized in that the method includes:

The binocular camera device collects a target picture from the driver’s perspective, where the target picture includes a target light spot, the target light spot includes at least one of a strong light spot and a weak light spot, and the target light spot is natural Mapping of real light points in the target picture;

The image processing unit obtains the plane coordinates of the target light point in the target picture according to the target picture;

The control unit calculates the spatial coordinates of the target dimming point on the dimming glass according to the plane coordinates of the target light spot, obtains the target glass area where the target dimming point is located, and obtains all the coordinates according to the target picture The target light transmittance required by the target dimming point, and an instruction to change the light transmittance of the target glass area is sent to the dimming glass, wherein the dimming glass is divided into a plurality of glass areas;

The dimming glass adjusts the light transmittance of the target glass area to the target light transmittance according to an instruction to change the light transmittance of the target glass area.
An electronic device, characterized in that the electronic device includes a processor and a memory; the memory is used to store instructions; the processor is used to call instructions in the memory to execute the method described in claim 8 above.
A computer non-transitory storage medium, wherein the computer non-transitory storage medium stores a computer program, wherein the computer program is executed by a computing device to implement the method according to claim 8.