Vehicle control method and device and vehicle

Abstract

The invention provides a vehicle control method and device and a vehicle. The method can be applied to the field of intelligent driving. The method comprises the steps that an image collected by a camera in a vehicle is obtained, the image comprises information of a reflective mirror in an intersection, the intersection is an intersection of a road section where the vehicle is located and other road sections where obstacles are located, and the reflective mirror is used for reflecting the obstacles in the other road sections; and controlling the vehicle at least according to the first image. The embodiment of the invention can be applied to an intelligent vehicle or an electric vehicle, the safety risk during vehicle meeting at the intersection can be reduced, and the driving safety of a user can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and more specifically, to a vehicle control method, device and vehicle. Background Art

[0002] Currently, vehicles can identify interactive vehicles at intersections through data collected by sensors such as cameras, millimeter-wave radars, and lidars, and achieve the function of slowing down and giving way at intersections. However, at blind intersections, due to the obstruction of obstacles (such as pillars, walls, etc.), the data collected by these sensors cannot identify interactive risks in advance, resulting in collisions with interactive vehicles when meeting at intersections. Summary of the invention

[0003] The present application provides a vehicle control method, device and vehicle, which are helpful to reduce the safety risks when meeting other vehicles at intersections, and also help to improve the driving safety of users.

[0004] In a first aspect, a vehicle control method is provided, the method comprising: acquiring a first image captured by a first camera in a vehicle, the first image comprising information of a reflector in an intersection, the intersection being an intersection of a first road section and a second road section, the vehicle being located in the first road section, and the reflector being used to reflect obstacles in the second road section; and controlling the vehicle at least based on the first image.

[0005] Based on the above technical solution, when a vehicle passes through an intersection, the camera can collect images including the reflectors to control the vehicle to pass through the intersection. In this way, the safety risk of the vehicle passing through the intersection can be reduced, which helps to improve the driving safety of users. At the same time, when the vehicle is in the automatic driving state, the camera collects images including the reflectors, which can make the vehicle's decision-making results more human-like, helping to improve the intelligence of the vehicle.

[0006] In some possible implementations, controlling the vehicle at least based on the first image includes: determining at least based on the first image that there is no obstacle of a preset type in the second road section; when the vehicle is in an automatic driving state, controlling the vehicle to pass through the intersection according to a previously planned path (for example, a previously planned driving speed); or, when the vehicle is in a manual driving state, controlling the prompt device not to prompt the user.

[0007] In some possible implementations, when the vehicle is in an underground garage, the preset types of obstacles include other vehicles, motorcycles, bicycles, pedestrians, etc.

[0008] In some possible implementations, when the vehicle is in a mountainous area, the preset type of obstacles includes other vehicles, motorcycles, bicycles, pedestrians, or stationary obstacles on the ground (e.g., fallen rocks, cones, water barriers, etc.).

[0009] In some possible implementations, the vehicle is controlled at least based on the first image, including: determining at least based on the first image that an obstacle of a preset type exists in the second road section and that the obstacle of the preset type has not moved toward the intersection; when the vehicle is in an automatic driving state, controlling the vehicle to pass through the intersection along a previously planned path, or, when the vehicle is in a manual driving state, controlling a prompt device not to prompt the user.

[0010] In combination with the first aspect, in certain implementations of the first aspect, the first image includes a first frame image and a second frame image, and the vehicle is controlled at least based on the first image, including: determining the moving direction of the first obstacle in the second road section at least based on the first frame image and the second frame image; when the moving direction indicates that the first obstacle is moving toward the intersection, controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down.

[0011] Based on the above technical solution, when it is determined through the information of the reflector that the first obstacle is moving towards the intersection, the vehicle can be controlled to give way to the first obstacle or the prompt device can be controlled to prompt the user to slow down, which can reduce the safety risks when the vehicle passes through the intersection and help improve the driving safety of the user.

[0012] In some possible implementations, the moving direction of the first obstacle in the second road section is determined based on at least the first frame image and the second frame image, including: inputting the first frame image and the second frame image into an inference model to obtain the moving direction of the first obstacle, the moving direction of the first obstacle including the first obstacle moving toward the intersection, the first obstacle being stationary, or the first obstacle moving away from the intersection; wherein the inference model is trained by a sample data set, and the sample training set includes at least two frames of images collected by a sample vehicle and the moving direction of the sample obstacle.

[0013] Based on the above technical solution, at least two frames of images including the reflector can be input into the inference model to obtain the moving direction of the obstacle, which helps to improve the speed at which the vehicle recognizes the moving direction of the obstacle and reduce the end-to-end delay from camera image acquisition to braking by the braking device. It helps to reduce the safety risks of the vehicle when passing through the intersection and also helps to improve the driving safety of users.

[0014] In some possible implementations, the first frame image and the second frame image are input into an inference model to obtain the moving direction of the first obstacle, including: inputting the speed of the vehicle, the first frame image, and the second frame image into an inference model to obtain the moving direction of the first obstacle, wherein the sample data set also includes the speed of the sample vehicle.

[0015] In some possible implementations, the output result of the inference model also includes the distance between the first obstacle and the intersection, wherein the sample data set also includes the distance between the sample obstacle and the intersection, and before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method also includes: determining that the distance between the first obstacle and the intersection is less than or equal to a preset distance.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the moving direction of the first obstacle in the second road section is determined at least based on the first frame image and the second frame image, including: determining the moving direction of the first obstacle based at least on the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0017] The above information of the reflector may include the information of the first reference object.

[0018] Based on the above technical solution, the moving direction of the obstacle can be obtained by comparing the relative position relationship between the obstacle and the reference object in the two frames of images, which helps to reduce the safety risks when the vehicle passes through the intersection and also helps to improve the driving safety of the user.

[0019] In combination with the first aspect, in certain implementations of the first aspect, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method also includes: determining that the moving speed of the first obstacle is greater than or equal to a first preset speed based on at least the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0020] Based on the above technical solution, the vehicle can also determine the moving speed of the obstacle by the relative position relationship between the obstacle and the reference object in the two frames of images. When the moving speed is greater than or equal to the first preset speed, the vehicle is controlled to slow down and give way to the obstacle or the prompt device is controlled to prompt the user to slow down. In this way, it is helpful to improve the accuracy of vehicle control when passing through the intersection, help reduce the safety risks of the vehicle when passing through the intersection, and also help improve the driving safety of users.

[0021] In some possible implementations, the method further includes: determining that the moving speed of the first obstacle is less than a first preset speed based at least on the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image; when the vehicle is in an automatic driving state, controlling the vehicle to pass through the intersection according to a previously planned path (for example, a previously planned driving speed) or controlling the vehicle to accelerate through the intersection, or, when the vehicle is in a manual driving state, controlling the prompt device not to prompt the user or controlling the prompt device to prompt the user to accelerate through the intersection.

[0022] In combination with the first aspect, in certain implementations of the first aspect, the intersection is located in an underground garage, and the first reference object includes at least one of a parking space line, other vehicles parked in the parking space, a pillar, and a wall.

[0023] In some possible implementations, the intersection is located in a mountainous area, and the first reference object includes a speed limit sign, a guardrail, etc.

[0024] In some possible implementations, the method also includes: determining the lane where the first obstacle is located based on at least the first image; controlling the vehicle to give way to the first obstacle, including: when the lane where the first obstacle is located is the same lane as the lane where the vehicle is located, controlling the vehicle to decelerate according to a first deceleration; or, when the lane where the first obstacle is located is different from the lane where the vehicle is located, controlling the vehicle to decelerate according to a second deceleration; wherein the first deceleration is greater than the second deceleration.

[0025] Based on the above technical solution, the vehicle can further determine the lane where the obstacle is located through the information from the reflector. For example, the lane in the underground garage is a two-way single lane, and the vehicle can further determine whether the lane where the obstacle is located is the same as the lane where the vehicle is located through the information from the reflector. If the lane where the obstacle is located is the same as the lane where the vehicle is located, it can be determined that the obstacle is traveling in the opposite direction. At this time, the risk of collision between the vehicle and the obstacle is greater. The vehicle can control the vehicle to decelerate at a greater deceleration rate, which helps to reduce the safety risk when the vehicle passes through the intersection and also helps to improve the driving safety of the user. If the lane where the obstacle is located is different from the lane where the vehicle is located, it can be determined that the obstacle is not traveling in the opposite direction. At this time, the vehicle can control the vehicle to decelerate and give way at a smaller deceleration rate, which helps to improve the driving comfort of the user.

[0026] In combination with the first aspect, in certain implementations of the first aspect, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method also includes: obtaining a third frame image and a fourth frame image captured by a second camera in the vehicle, the acquisition time of the third frame image is later than the acquisition time of the fourth frame image, the third frame image and the fourth frame image include information of a first area in the intersection, the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; determining that the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or determining that the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image.

[0027] Based on the above technical solution, the accuracy of judging whether an obstacle is moving toward the intersection can be further improved by observing the changes in light in the first area at the intersection, which helps reduce the safety risks when vehicles pass through the intersection and also helps improve the driving safety of users.

[0028] The first sub-region mentioned above may be referred to as a bright region, and the second sub-region may be referred to as a dark region.

[0029] In combination with the first aspect, in certain implementations of the first aspect, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method also includes: determining that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image.

[0030] Based on the above technical solution, by further combining the changes in light intensity in the bright area, the accuracy of judging whether an obstacle is moving toward an intersection can be improved, thereby helping to improve the accuracy of vehicle control.

[0031] In combination with the first aspect, in certain implementations of the first aspect, the dividing line between the first sub-area and the second sub-area is the first dividing line, and before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method also includes: determining, at least based on the third frame image and the fourth frame image, that the rotation speed of the first dividing line around a preset point is greater than or equal to a second preset speed.

[0032] Based on the above technical solution, the speed at which the obstacle moves toward the intersection can be determined by the speed at which the dividing line between the bright area and the dark area rotates. When it is determined that the speed at which the obstacle moves toward the intersection is too fast, the vehicle can be controlled to slow down in time or the prompt device can be controlled to prompt the user to slow down. This helps to improve the accuracy of vehicle control when passing through the intersection, helps to reduce the safety risks of the vehicle when passing through the intersection, and also helps to improve the driving safety of users.

[0033] In combination with the first aspect, in certain implementations of the first aspect, before determining the moving direction of the first obstacle in the second road section at least based on the first frame image and the second frame image, the method also includes: determining an obstacle of a preset type from the information of the reflector, and the preset type of obstacle includes the first obstacle.

[0034] Based on the above technical solution, obstacles of a preset type can be screened out from multiple obstacles through the information of the reflector, so as to determine the moving direction of the obstacles of the preset type, which helps to reduce the calculation overhead of the vehicle.

[0035] In a second aspect, a vehicle control method is provided, the method comprising: acquiring a second image captured by a second camera in a vehicle on a first road section, the second image including an image of a first area at an intersection, the first area including a first sub-area and a second sub-area, the light intensity of the first sub-area being greater than the light intensity of the second sub-area; determining a moving direction of a first obstacle in the second road section according to light changes in the first area, the intersection being an intersection of the first route and the second route; and controlling the vehicle according to the moving direction of the first obstacle.

[0036] Based on the above technical solution, the moving direction of the obstacle in the second section can be predicted by the light changes in the first area at the intersection, so that it can be determined whether the vehicle passes through the intersection normally or slows down to give way to the first obstacle, which helps to reduce the safety risks of the vehicle passing through the intersection and also helps to improve the driving safety of users. At the same time, when the vehicle is in the automatic driving state, the light changes in the first area are determined through the images collected by the camera to output the decision results, which can make the vehicle's decision results more human-like and help to improve the intelligence of the vehicle.

[0037] The first sub-region mentioned above may be referred to as a bright region, and the second sub-region may be referred to as a dark region.

[0038] In some possible implementations, the first vehicle is in a first road section, and the first sub-area and the second sub-area in the first area are generated by illumination of a lamp of a first obstacle in a second road section.

[0039] In some possible implementations, the length of the first area is half of the width of the first road section, and the width of the first area is a preset width (for example, 5 meters).

[0040] In combination with the second aspect, in certain implementations of the second aspect, the second image includes a third frame image and a fourth frame image, and the third frame image is acquired later than the fourth frame image. The moving direction of the first obstacle in the second road section is determined at least based on the light change in the first area, including: when the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image, it is determined that the first obstacle moves toward the intersection; wherein, controlling the vehicle includes: controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down.

[0041] Based on the above technical solution, when the area of ​​the bright area gradually increases or the area of ​​the dark area gradually decreases, it can be determined that the first obstacle is moving towards the intersection. In this way, by slowing down to give way to the obstacle or controlling the prompt device to prompt the user to slow down, it helps to reduce the safety risk of the vehicle passing through the intersection and also helps to improve the driving safety of the user.

[0042] In combination with the second aspect, in certain implementations of the second aspect, the method also includes: before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, determining that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image.

[0043] Based on the above technical solution, by further combining the changes in light intensity in the bright area, the accuracy of judging whether an obstacle is moving toward an intersection can be improved, thereby helping to improve the accuracy of vehicle control.

[0044] In combination with the second aspect, in certain implementations of the second aspect, the dividing line between the first sub-area and the second sub-area is the first dividing line, and before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method also includes: determining, at least based on the third frame image and the fourth frame image, that the rotation speed of the first dividing line around the preset point is greater than or equal to the second preset speed.

[0045] Based on the above technical solution, the speed at which the obstacle moves toward the intersection can be determined by the speed at which the dividing line between the bright area and the dark area rotates. When it is determined that the speed at which the obstacle moves toward the intersection is too fast, the vehicle can be controlled to slow down in time or the prompt device can be controlled to prompt the user to slow down. This helps to improve the accuracy of vehicle control when passing through the intersection, helps to reduce the safety risks of the vehicle when passing through the intersection, and also helps to improve the driving safety of users.

[0046] In a third aspect, a control device is provided, which includes: an acquisition unit, used to acquire a first image captured by a first camera in a vehicle, the first image including information of a reflector in an intersection, the intersection being an intersection of a first road section and a second road section, the vehicle is located in the first road section, and the reflector is used to reflect obstacles in the second road section; a control unit, used to control the vehicle at least based on the first image.

[0047] In combination with the third aspect, in certain implementations of the third aspect, the first image includes a first frame image and a second frame image, and the device also includes: a first determination unit, used to determine the moving direction of the first obstacle in the second road section based at least on the first frame image and the second frame image; wherein the control unit is used to: when the moving direction indicates that the first obstacle is moving toward the intersection, control the vehicle to give way to the first obstacle, or control the prompt device to prompt the user to slow down.

[0048] In combination with the third aspect, in certain implementations of the third aspect, the first determination unit is used to determine the moving direction of the first obstacle based at least on the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0049] In combination with the third aspect, in certain implementations of the third aspect, the first determination unit is also used to: before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, determine that the moving speed of the first obstacle is greater than or equal to the first preset speed, at least based on the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0050] In combination with the third aspect, in certain implementations of the third aspect, the intersection is located in an underground garage, and the first reference object includes at least one of a parking space line, other vehicles parked in the parking space, and a pillar.

[0051] In combination with the third aspect, in certain implementations of the third aspect, the device also includes a second determination unit, and the acquisition unit is also used to acquire a third frame image and a fourth frame image captured by a second camera in the vehicle before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, wherein the acquisition time of the third frame image is later than the acquisition time of the fourth frame image, and the third frame image and the fourth frame image include information of a first area in the intersection, the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; the second determination unit is used to determine that the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or to determine that the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image.

[0052] In combination with the third aspect, in certain implementations of the third aspect, the second determination unit is also used to determine that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

[0053] In combination with the third aspect, in certain implementations of the third aspect, the dividing line between the first sub-area and the second sub-area is the first dividing line, and the second determination unit is further used to determine, at least based on the third frame image and the fourth frame image, that the rotation speed of the first dividing line around a preset point is greater than or equal to a second preset speed before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

[0054] In combination with the third aspect, in certain implementations of the third aspect, the first determination unit is further used to determine an obstacle of a preset type from the information of the reflector before determining the moving direction of the first obstacle, and the preset type of obstacles includes the first obstacle.

[0055] In a fourth aspect, a control device is provided, the method comprising: an acquisition unit, used to acquire a second image captured by a second camera in a vehicle on a first section of road, the second image including an image of a first area at an intersection, the first area including a first sub-area and a second sub-area, the light intensity of the first sub-area being greater than the light intensity of the second sub-area; a determination unit, used to determine a moving direction of a first obstacle in the second section of road at least based on light changes in the first area, the intersection being the intersection of the first route and the second route; and a control unit, used to control the vehicle at least based on the moving direction of the first obstacle.

[0056] In combination with the fourth aspect, in certain implementations of the fourth aspect, the second image includes a third frame image and a fourth frame image, and the acquisition time of the third frame image is later than the acquisition time of the fourth frame image, and the determination unit is used to: determine that the first obstacle moves toward the intersection when the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image; wherein the control unit is used to: control the vehicle to give way to the first obstacle, or control the prompt device to prompt the user to slow down.

[0057] In combination with the fourth aspect, in certain implementations of the fourth aspect, the determination unit is also used to: before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, determine that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image.

[0058] In combination with the fourth aspect, in certain implementations of the fourth aspect, the dividing line between the first sub-area and the second sub-area is the first dividing line, and the determination unit is further used to: before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, determine that the rotation speed of the first dividing line around the preset point is greater than or equal to the second preset speed, at least based on the third frame image and the fourth frame image.

[0059] In a fifth aspect, a control device is provided, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes any possible vehicle control method in the first aspect or the second aspect.

[0060] In a sixth aspect, the present application provides a control system comprising a camera and a computing platform, wherein the computing platform comprises any possible control device in the third aspect, or comprises the control device described in the fourth aspect, or comprises the control device described in the fifth aspect.

[0061] In a seventh aspect, the present application provides a vehicle comprising any possible control device in the third aspect, or comprising the control device described in the fourth aspect, or comprising the control device described in the fifth aspect, or comprising the control system described in the sixth aspect.

[0062] In an eighth aspect, the present application provides a server, which includes any possible control device in the third aspect, the fourth aspect or the fifth aspect.

[0063] In a ninth aspect, the present application provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute any possible vehicle control method in the first or second aspect above.

[0064] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or separately packaged with the processor, and the embodiments of the present application do not specifically limit this.

[0065] In a tenth aspect, the present application provides a computer-readable medium storing a program code, and when the computer program code runs on a computer, the computer executes any possible vehicle control method in the first aspect or the second aspect.

[0066] In an eleventh aspect, the present application provides a chip, comprising a circuit for executing any possible vehicle control method in the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a functional block diagram of a vehicle provided in an embodiment of the present application.

[0068] Figure 2 It is a schematic diagram of an application scenario provided by an embodiment of the present application.

[0069] Figure 3 It is a schematic flow chart of the vehicle control method provided in an embodiment of the present application.

[0070] Figure 4 It is another schematic diagram of the application scenario provided by the embodiment of the present application.

[0071] Figure 5 It is the positional relationship between the vehicle 2 and the pillar in the reflector information of different images provided in the embodiment of the present application.

[0072] Figure 6 It is another schematic flow chart of the vehicle control method provided in an embodiment of the present application.

[0073] Figure 7 It is another schematic diagram of the application scenario provided by the embodiment of the present application.

[0074] Figure 8 It is another schematic flow chart of the vehicle control method provided in an embodiment of the present application.

[0075] Fig. 9 It is another schematic flow chart of the vehicle control method provided in an embodiment of the present application.

[0076] Fig.10 It is a schematic block diagram of a control device provided in an embodiment of the present application.

[0077] Fig.11 It is another schematic block diagram of a control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0078] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships can exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. "At least one" means one or more. For example, "at least one of A and B" is similar to "A and / or B", describing the association relationship of associated objects, indicating that three relationships can exist, for example, at least one of A and B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0079] In the embodiments of the present application, prefixes such as "first" and "second" are used only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present application does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "multiple" is two or more.

[0080] Figure 1 It is a functional block diagram of the vehicle 100 provided in an embodiment of the present application. The vehicle 100 may include a perception system 110 and a computing platform 120, wherein the perception system 110 may include one or more sensors for sensing information about the environment surrounding the vehicle 100. For example, the perception system 110 may include one or more collision sensors. For another example, the perception system 110 may include a positioning system, and the positioning system may be a global positioning system (GPS), or a Beidou system or other positioning systems. For another example, the perception system 110 may include one or more of an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera device.

[0081] Some or all functions of the vehicle 100 may be controlled by the computing platform 120. The computing platform 120 may include one or more processors, such as processors 121 to 12n (n is a positive integer). The processor is a circuit with signal processing capability. In one implementation, the processor may be a circuit with instruction reading and execution capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by a processor as an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor may also be a hardware circuit designed for artificial intelligence, which may be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 120 may also include a memory, the memory is used to store instructions, and some or all of the processors 121 to 12n may call instructions in the memory to implement corresponding functions.

[0082] The vehicle in the present application is a vehicle in a broad sense, which can be a means of transportation (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as mowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of the present application do not specifically limit the type of vehicle.

[0083] Currently, vehicles can identify interactive vehicles at intersections through data collected by sensors such as cameras, millimeter-wave radars, and lidars, and achieve the function of slowing down and giving way at intersections. However, at blind intersections, due to the obstruction of obstacles (such as pillars, walls, etc.), the data collected by these sensors cannot identify interactive risks in advance, resulting in collisions with interactive vehicles when meeting at intersections.

[0084] For example, Figure 2 A schematic diagram of an application scenario provided by an embodiment of the present application is shown. When a vehicle passes through an intersection, due to the presence of obstacles (e.g., walls), the data collected by the vehicle through sensors (e.g., cameras, laser radars, millimeter-wave radars, etc.) cannot identify the information of obstacles in the blind spot in advance, which may lead to safety accidents.

[0085] The present application provides a vehicle control method, device and vehicle, which are helpful to reduce the safety risks when meeting other vehicles at intersections, and also help to improve the driving safety of users.

[0086] Figure 3 FIG. 3 is a schematic flow chart of a vehicle control method 300 provided in an embodiment of the present application. Figure 3 As shown, the method 300 includes:

[0087] S310, acquiring image data collected by a camera in the vehicle.

[0088] Exemplarily, the image data may include multiple frames of images or videos.

[0089] In one embodiment, before acquiring image data collected by a camera in the vehicle, the method 300 further includes: determining that the distance between the vehicle and the intersection is less than or equal to a preset distance.

[0090] Exemplarily, the preset distance may be 20 meters.

[0091] S320, obtaining information of a reflector in an intersection through the image data detection, the intersection being an intersection of a first road section and a second road section, the vehicle being located in the first road section, and the reflector being used to reflect obstacles in the second road section.

[0092] For example, Figure 4 Another schematic diagram of an application scenario provided by an embodiment of the present application is shown.

[0093] Vehicle 1 can collect image data of intersection 1 through a front camera (e.g., a camera located on the roof), and the image data includes information of the reflector. Vehicle 1 can be located at section 1, and vehicle 2 can be located at section 2. The intersection of section 1 and section 2 is intersection 1. Vehicle 1 can determine obstacles in section 2 through image data including the reflector.

[0094] The information of the reflector in the above intersection may include the information of the road section 2 emitted by the reflector.

[0095] S330: Determine whether there is an obstacle of a preset type in the second road section at least based on the information of the reflector.

[0096] Exemplarily, taking the intersection being located in an underground garage as an example, the preset types of obstacles include vehicles, motorcycles, bicycles or pedestrians.

[0097] Exemplarily, taking the intersection being located in a mountainous area as an example, the preset types of obstacles include vehicles, motorcycles, bicycles, pedestrians, and stationary obstacles (eg, fallen rocks, cones, water barriers, etc.).

[0098] When it is determined that there is no obstacle of the preset type in the second section, S360 may be executed, that is, the vehicle passes the intersection normally. When it is determined that there is an obstacle of the preset type in the second section, S340 may be executed.

[0099] S340: Determine whether the obstacle of the preset type moves toward the intersection at least based on the image data.

[0100] When it is determined that the obstacle of the preset type moves toward the intersection, execute S350; otherwise, execute S360.

[0101] In one embodiment, determining whether the obstacle of the preset type moves toward the intersection at least based on the image data includes: determining whether the obstacle of the preset type moves toward the intersection at least based on at least two frames of images in the image data.

[0102] For example, the at least two frames of images include a first frame of image and a second frame of image. The vehicle can determine a first relative position relationship between a preset type of obstacle and a reference object based on information from a reflector in the first frame of image, and determine a second relative position relationship between the preset type of obstacle and the reference object based on information from the reflector in the second frame of image; the vehicle can determine whether an obstacle of the preset type moves toward the intersection based at least on the first relative position relationship and the second relative position relationship.

[0103] like Figure 4 As shown, taking vehicle 1 in an underground garage as an example, the preset type of obstacle may be vehicle 2. Vehicle 1 may determine the moving direction of vehicle 2 based on at least two frames of the image data collected by the camera. 1 At time T, the vehicle obtains image 1 through the camera and 1 T after time 2 Image 2 is acquired at this moment.

[0104] Figure 5The positional relationship between the vehicle 2 and the pillar in the mirror information of different images provided by the embodiment of the present application is shown. Figure 5 As shown in (a) in the figure, taking the reference object as a pillar as an example, vehicle 1 can extract the information of the reflector through image 1, and at least based on the information of the reflector, the relative position relationship between vehicle 2 and the pillar can be determined, such as the front position of vehicle 2 (for example, the front bumper of vehicle 2) is aligned with the side of the pillar.

[0105] like Figure 5 As shown in (b), vehicle 1 can extract the information of the reflector through image 2, and at least based on the information of the reflector, the relative position relationship between vehicle 2 and the pillar can be determined, such as the rear position of vehicle 2 (for example, the rear bumper of vehicle 2) is aligned with the side of the pillar.

[0106] By analyzing the information of the reflective mirrors in the above different frame images to obtain the relative position relationship between the vehicle 2 and the pillar, it can be determined that the vehicle 2 is moving towards the intersection.

[0107] S350, controlling the vehicle to decelerate, and / or controlling a prompting device to prompt the driver to decelerate.

[0108] For example, when vehicle 1 is in an automatic driving state (for example, the vehicle has the automated valet parking (AVP) function turned on), the vehicle can control the vehicle to decelerate, thereby giving way to vehicle 2.

[0109] For example, when vehicle 1 is in manual driving state, vehicle 1 can control the prompt device to prompt the user to slow down. For example, vehicle 1 can control the display screen (e.g., instrument screen) to display the prompt message "Another vehicle is detected moving towards the intersection, please slow down and give way." For another example, vehicle 1 can control the speaker to emit a prompt sound "A blind spot vehicle is detected moving towards the intersection, please slow down and give way." For another example, vehicle 1 can control the color of the ambient light in the cabin to be red. For another example, vehicle 1 can control the steering wheel to vibrate.

[0110] In one embodiment, the method 300 further includes: determining a moving speed of an obstacle of a preset type toward the intersection at least based on the image data; and controlling the vehicle based on the moving speed.

[0111] In one embodiment, taking the case where the vehicle is in an automatic driving state as an example, when it is determined that the preset type of obstacle is moving toward the intersection, the method 300 further includes: determining the moving speed of the preset type of obstacle toward the intersection based on at least two frames of images in the image data; when the moving speed is greater than or equal to a first preset speed, controlling the vehicle to slow down and give way and / or controlling a prompt device to prompt the driver to slow down; or, when the moving speed is less than the first preset speed, controlling the vehicle to rush through the intersection.

[0112] Exemplarily, the first preset speed may be 6 km / h.

[0113] For example, the vehicle can determine the moving speed of a preset type of obstacle toward the intersection based on the first relative position relationship and the second relative position relationship. Figure 5 As shown in (a) and (b) in FIG. 1 , vehicle 1 can determine that the type of obstacle traveling on road section 2 is a vehicle through the information of the reflector, and thus can determine that its length is 4.8 meters. Figure 5 As shown in (a) of FIG. 1 , the front bumper of the vehicle 2 and the side of the pillar are located on the same horizontal plane. Figure 5 As shown in (b), the rear bumper of vehicle 2 is located on the same horizontal plane as the side of the pillar. Vehicle 1 can determine that during the time from when the camera captures image 1 to when the camera captures image 2, vehicle 2 moves 4.8 meters toward the intersection.

[0114] For example, Table 1 shows information on the lengths of different types of obstacles.

[0115] Table 1

[0116] type length vehicle 4.8 m bike 1.6 m motorcycle 2 meters … …

[0117] For example, if the time between the camera capturing image 1 and image 2 is 1 second, vehicle 1 can determine that the speed of vehicle 2 is 17.28 km / h. Since the speed of vehicle 2 is greater than 6 km / h, vehicle 1 can control vehicle 1 to slow down and yield and / or control the prompt device to prompt the driver to slow down.

[0118] For example, if the time between the camera capturing image 1 and image 2 is 3 seconds, then vehicle 1 can determine that the speed of vehicle 2 is 5.76 km / h. Since the speed of vehicle 2 is less than 6 km / h, vehicle 1 can control vehicle 1 to pass through the intersection normally or rush through the intersection, or vehicle 1 can control the prompt device to prompt the user to pass through the intersection quickly. For example, vehicle 1 can control the display screen to prompt the user "A vehicle in the blind spot is detected to give way, please pass through the intersection as soon as possible." For another example, vehicle 1 can control the speaker to issue a prompt sound "A vehicle in the blind spot is detected to give way, please pass through the intersection as soon as possible."

[0119] In one embodiment, when determining that the preset type of obstacle is moving toward an intersection, the vehicle can input the at least two frames of images into an inference model to obtain a result of whether the preset type of obstacle is moving toward the intersection; wherein the inference model is trained by a sample training set, and the sample training set includes images including reflectors captured by the camera of the sample vehicle and the moving direction of the sample obstacle.

[0120] In one embodiment, when determining that the preset type of obstacle is moving toward the intersection, the vehicle can input the speed of the vehicle and the at least two frames of images into an inference model to obtain the moving direction and moving speed of the preset type of obstacle; wherein the inference model is trained by a sample training set, and the sample training set includes the moving speed of the sample vehicle, the image including the reflector captured by the camera of the sample vehicle, the moving direction of the sample obstacle, and the moving speed of the sample obstacle.

[0121] Exemplarily, in the model training stage, the sample training set includes images captured by the camera when the sample vehicle moves toward the intersection at a certain speed, and the images are labeled with the moving direction and speed of the sample obstacle. For example, the sample data set includes images captured by the camera of the sample vehicle when the sample vehicle moves toward the intersection at a speed of 15km / h. The image can be labeled with information that the sample obstacle moves toward the intersection and the speed of the sample obstacle is 10km / h; the sample training set also includes images captured by the camera of the sample vehicle when the sample vehicle moves toward the intersection at a speed of 15km / h. The image can be labeled with information that the sample obstacle moves toward the intersection and the speed of the sample obstacle is 15km / h; the sample training set also includes images captured by the camera of the sample vehicle when the sample vehicle moves toward the intersection at a speed of 15km / h. The image can be labeled with information that the sample obstacle moves toward the intersection and the speed of the sample obstacle is 20km / h, etc. The inference model can be trained using the above sample training data sets. In the model inference stage, vehicle 1 can 1 To T 2 The average speed at time T 1 To T 2 The image collected by the camera at the time is input into the reasoning model to obtain the speed of vehicle 2.

[0122] The above-mentioned driving speed of the sample vehicles may be the average speed of the camera of the sample vehicles during the process of collecting images, and the speed of the sample obstacles may be the average speed of the camera of the sample vehicles during the process of collecting images.

[0123] In one embodiment, the vehicle may input the at least two frames of images and the speed of the vehicle into an inference model to obtain the moving speed of the preset type of obstacle toward the intersection and the distance between the preset type of obstacle and the intersection, wherein the sample training data set also includes the distance between the sample obstacle and the intersection. The vehicle may control the vehicle according to the speed of the vehicle, the distance between the vehicle and the intersection, the speed of the preset type of obstacle, and the distance between the preset type of obstacle and the intersection.

[0124] In one embodiment, when the time difference between a first time duration determined according to the moving speed of an obstacle of the preset type and the distance between the obstacle of the preset type and the intersection and a second time duration determined according to the moving speed of the vehicle and the distance between the vehicle and the intersection is less than or equal to a preset difference, the vehicle is controlled to slow down and give way and / or a prompt device is controlled to prompt the driver to slow down.

[0125] In the above model training stage, the loss function of the model can be a regression loss function such as mean squared error (MSE); or, the loss function can be a classification loss function such as cross entropy loss (cross entropy loss).

[0126] The above model can be a neural network (NN), such as transformer, multi-layer perceptron (MLP), residual neural network (ResNet), recurrent neural network (RNN); or, it can also be other machine learning algorithms, such as support vector machine (SVM) or decision tree.

[0127] S360, control vehicles to pass through the intersection normally.

[0128] For example, if the vehicle is in an automatic driving state (for example, the vehicle has the AVP function turned on), the vehicle can continue to drive along the planned path and park in the target parking space; for another example, if the vehicle is in a manual driving state, the vehicle may not prompt the user.

[0129] Figure 6 FIG. 6 is a schematic flow chart of a vehicle control method 600 provided in an embodiment of the present application. Figure 6 As shown, the method 600 includes:

[0130] S610, acquiring image data collected by a camera in a vehicle, wherein the image data includes an image of an intersection.

[0131] The above S610 may refer to the description in the above S310, which will not be repeated here.

[0132] S620, determining an observation area at least based on the image data.

[0133] For example, Figure 7 Another schematic diagram of an application scenario provided by an embodiment of the present application is shown.

[0134] like Figure 7 As shown in (a), vehicle 1 is at T 3 The image including the intersection 1 is collected at all times. The intersection 1 is the intersection of the road section 1 and the road section 2. For example, the intersection 1 formed by the road section 1 and the road section 2 is a rectangular area ABCD. The observation area can be a rectangular area EFGH. Among them, the length of the side EF is half of the width of the intersection (for example, 3.5 meters), and the length of the side FG is a preset length (for example, 5 meters). The side EF in the rectangular area EFGH coincides with the side CD in the intersection 1 close to the road section 1. Among them, due to the illumination of the headlights of the blind spot obstacle (for example, vehicle 2), a bright area and a dark area can be formed in the rectangular area EFGH. The light intensity of the bright area is greater than the light intensity of the dark area. Among them, the boundary between the bright area and the dark area is FO, S 亮 is the area of ​​the bright area, S 暗 is the area of ​​the dark region. 3 Moment, S 亮 is the area of ​​the triangle FEO.

[0135] S630, determine S in the observation area 亮 Is the area gradually increasing?

[0136] If the S 亮 If the area gradually increases, the vehicle executes S640; otherwise, the vehicle executes S650.

[0137] like Figure 7 As shown in (b), vehicle 1 is at T 4 The image including intersection 1 is collected at time T 4 Time later than T 3 As the blind spot obstacle moves toward the intersection, the boundary between the bright area and the dark area changes from FO to FO'. At this time, S 亮 is the area of ​​quadrilateral FEHO'. It can be seen that T 4 The area of ​​the bright area at time T is greater than 3 The area of ​​the bright area at each moment, so that the vehicle 1 can determine that the blind spot obstacle is moving toward the intersection.

[0138] In the above S630, it is determined that 亮The area of ​​S is gradually increasing, and the embodiment of the present application is not limited thereto. For example, the vehicle 1 may also determine whether S 暗 The area of ​​S is gradually decreasing. 暗 If the area gradually increases, the vehicle executes S640; otherwise, the vehicle executes S650.

[0139] S640, controlling the vehicle to decelerate, and / or controlling the prompting device to prompt the user to decelerate.

[0140] For example, when vehicle 1 is in an automatic driving state (for example, the vehicle has the AVP function turned on), the vehicle can control the vehicle to slow down, thereby giving way to vehicle 2.

[0141] In one embodiment, before controlling the vehicle to decelerate and / or controlling the prompting device to prompt the user to decelerate, the method 600 further includes: determining that the illumination intensity of the bright area gradually increases.

[0142] S650, control the vehicle to pass through the intersection normally.

[0143] For example, if the vehicle is in an automatic driving state (for example, the vehicle has the AVP function turned on), the vehicle can continue to drive along the planned path and park in the target parking space; for another example, if the vehicle is in a manual driving state, the vehicle may not prompt the user.

[0144] In the above method 600, S is determined. 亮 The example of determining that the obstacle is moving toward the intersection by the area of ​​the rectangular area EFGH gradually increasing, so that the vehicle can slow down to give way or the prompt device can be controlled to prompt the user to slow down is described, and the embodiments of the present application are not limited to this. For example, the moving speed of the obstacle toward the intersection can also be determined by the light conditions of the rectangular area EFGH; when the moving speed is greater than or equal to the preset speed, the vehicle can be controlled to slow down to give way and / or the prompt device can be controlled to prompt the user to slow down.

[0145] For example, taking the basement as a two-way single lane (for example, the width of each lane is 3.5 meters) as an example, whether the speed of the obstacle is too fast can be determined by the relationship between the rotation speed (for example, angular velocity) of the dividing line between the bright area and the dark area around the point F and the preset angular velocity threshold. For example, if the angular velocity of the dividing line rotating around the point F is greater than or equal to 8 rad / s, it can be determined that the speed of the obstacle moving toward the intersection is too fast, so the vehicle can be controlled to slow down and give way, or the prompt device can be controlled to prompt the user to slow down.

[0146] Figure 8 A schematic flow chart of a vehicle control method 800 provided in an embodiment of the present application is shown. The method 800 includes:

[0147] S810, obtaining a first image captured by a first camera in the vehicle, the first image including information of a reflector in an intersection, the intersection being an intersection of a first road section and a second road section, the vehicle being located in the first road section, and the reflector being used to reflect obstacles in the second road section.

[0148] For example, Figure 4 As shown, the vehicle may be the above-mentioned vehicle 1, and the first road section may be the above-mentioned road section 1; the obstacle may be the above-mentioned vehicle 2, and the second road section may be the road section 2.

[0149] S820: Control the vehicle at least according to the first image.

[0150] Optionally, controlling the vehicle at least based on the first image includes: determining that no obstacle of a preset type exists in the second road section at least based on information from the reflector; and controlling the vehicle to travel normally.

[0151] Optionally, controlling the vehicle at least based on the first image includes: determining, at least based on the information of the reflector, that an obstacle of a preset type exists in the second road section and that the moving direction of the obstacle of the preset type is not toward the intersection; and controlling the vehicle to drive normally.

[0152] The above control of the vehicle to travel normally may include: when the vehicle is in an automatic driving state, controlling the vehicle to continue traveling along a previously planned path; or, when the vehicle is in a manual driving state, controlling the vehicle not to prompt the user.

[0153] Optionally, the first image includes multiple frames of images, and controlling the vehicle at least based on the first image includes: determining the moving direction of the first obstacle in the second road section at least based on the multiple frames of images; when the moving direction indicates that the first obstacle is moving toward the intersection, controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down.

[0154] Optionally, determining the moving direction of the first obstacle in the second road section at least based on the multiple frames of images includes: inputting the multiple frames of images into an inference model to obtain the moving direction of the first obstacle. The above training and inference process of the inference model can refer to the description in the above embodiment, which will not be repeated here.

[0155] Optionally, the multiple-frame images include a first frame image and a second frame image, and the moving direction of the first obstacle in the second road section is determined at least based on the multiple-frame images, including: determining the moving direction of the first obstacle based at least on the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0156] The above information of the reflector includes the information of the first reference object.

[0157] For example, Figure 5 As shown in (a) and (b) of FIG. 1 , the first reference object may be a pillar. By comparing the relative position relationship between the vehicle 2 and the pillar in the two frames of images, it can be determined that the vehicle 2 moves toward the intersection.

[0158] Optionally, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 800 also includes: determining that the moving speed of the first obstacle is greater than or equal to a first preset speed based on at least the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0159] Exemplarily, the first preset speed is 6 km / h.

[0160] For example, Figure 5 As shown in (a) of FIG. 1 , the front bumper of the vehicle 2 is located on the same horizontal plane as one side of the pillar. Figure 5 As shown in (b), the rear bumper of vehicle 2 is on the same horizontal plane as one side of the pillar. Vehicle 1 can determine that vehicle 2 has moved 4.8 meters toward the intersection from the time the camera captures image 1 to the time the camera captures image 2. If the time between the first camera capturing image 1 and image 2 is 1 second, then vehicle 1 can determine that the speed of vehicle 2 is 17.28 km / h. Since the speed of vehicle 2 is greater than 6 km / h, vehicle 1 can control vehicle 1 to slow down and / or control the prompt device to prompt the driver to slow down.

[0161] Optionally, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 800 also includes: inputting the multiple frames of images into an inference model to obtain the moving speed of the first obstacle; and determining that the moving speed of the first obstacle is greater than or equal to a first preset speed.

[0162] Optionally, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 800 also includes: inputting the multiple frames of images into an inference model to obtain the moving direction of the first obstacle as moving toward the intersection, the moving speed of the first obstacle, and the distance between the first obstacle and the intersection; wherein, controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, includes: when the time difference between a first time length determined according to the moving speed of the preset type of obstacle and the distance between the preset type of obstacle and the intersection and a second time length determined according to the moving speed of the vehicle and the distance between the vehicle and the intersection is less than or equal to a preset difference, controlling the vehicle to slow down and / or controlling the prompt device to prompt the driver to slow down.

[0163] Exemplarily, the preset difference is 2 seconds.

[0164] Optionally, the intersection is located in an underground garage, and the first reference object includes at least one of a parking space line, other vehicles parked in the parking space, a pillar, and a wall.

[0165] Optionally, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 800 also includes: obtaining a third frame image and a fourth frame image captured by a second camera in the vehicle, the third frame image is acquired later than the fourth frame image, the third frame image and the fourth frame image include information of a first area in the intersection, the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; determining that the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or determining that the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image.

[0166] The first area may be the observation area in S620 above.

[0167] The first camera and the second camera may be the same camera. For example, the first camera and the second camera may be cameras located on the roof of the vehicle, or cameras located on the front bumper (or the air intake grille).

[0168] Alternatively, different cameras may be used. For example, the first camera is a camera located on the roof, and the second camera may be a camera located on the front bumper (or, air intake grille).

[0169] For example, Figure 7As shown in (a) of FIG. 1 , when vehicle 2 passes through an intersection, the illumination of the vehicle 2's lamps will generate a rectangular area EFGH in front of vehicle 1. The rectangular area EFGH includes a bright area and a dark area. Figure 7 As shown in (b), vehicle 1 determines that the area of ​​the bright area in the next frame of image captured by the second camera is greater than the area of ​​the bright area in the previous frame of image, then it can be determined that the obstacle in section 2 is moving toward the intersection. In this way, when it is determined that the obstacle is moving toward the intersection by combining the first image including the reflector and the second image including the first area, the vehicle can be controlled to slow down or the prompt device can be controlled to prompt the user to slow down, which helps to ensure the accuracy of vehicle control, helps to further reduce the safety risks when meeting at the intersection, and also helps to improve the driving safety of users.

[0170] Optionally, before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 800 also includes: determining that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image.

[0171] For example, in Figure 7 The light intensity of the bright area shown in (b) is greater than that of Figure 7 When the illumination intensity of the bright area shown in (a) is greater than that of the vehicle 1, the vehicle 1 can further determine that the obstacle is moving toward the intersection.

[0172] Optionally, the dividing line between the first sub-area and the second sub-area is the first dividing line, and before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 800 also includes: determining, at least based on the third frame image and the fourth frame image, that the rotation speed of the first dividing line around the preset point is greater than or equal to the second preset speed.

[0173] Exemplarily, the preset point is the above Figure 7 Point F shown in (a) and (b). Figure 7 The dividing line shown in (a) is FO, Figure 7 The dividing line shown in (b) is FO'. The angular velocity of the dividing line rotating around point F can be determined by the angle of the dividing line rotating around point F and the time between the third frame image and the fourth frame image captured by the second camera. For example, if the angular velocity of the dividing line rotating around point F is 10 rad / s, it can be determined that the obstacle is moving too fast toward the intersection, and vehicle 1 can control vehicle 1 to slow down and yield or control the prompt device to prompt the user to slow down.

[0174] Optionally, before determining the moving direction of the first obstacle in the second road section at least based on the first frame image and the second frame image, the method further includes: determining obstacles of a preset type from the first image, the preset type of obstacles including the first obstacle.

[0175] Fig. 9 A schematic flow chart of a vehicle control method 900 provided in an embodiment of the present application is shown. The method 900 includes:

[0176] S910, obtaining a second image captured by a second camera in a vehicle on a first road section, wherein the second image includes an image of a first area at an intersection, wherein the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area.

[0177] The first sub-region mentioned above may be referred to as a bright region, and the second sub-region may be referred to as a dark region.

[0178] Optionally, the first vehicle is in a first road section, and the first sub-area and the second sub-area in the first area are generated by illumination of a lamp of a first obstacle in a second road section.

[0179] Optionally, the length of the first area is half of the width of the first road section (for example, 3.5 meters), and the width of the first area is a preset width (for example, 5 meters).

[0180] S920, determining a moving direction of the first obstacle in the second section at least according to a change in light in the first area, the intersection being an intersection of the first route and the second route.

[0181] Optionally, determining the moving direction of the first obstacle in the second road section at least based on the light changes in the first area includes: when the light intensity generated by the obstacle's lamps in the first area gradually increases, determining that the first obstacle is moving toward the intersection.

[0182] Optionally, the second image includes a third frame image and a fourth frame image, and the third frame image is acquired later than the fourth frame image. The moving direction of the first obstacle in the second road section is determined at least based on the light change in the first area, including: when the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image, it is determined that the first obstacle moves toward the intersection.

[0183] Optionally, the moving direction of the first obstacle includes the first obstacle moving toward the intersection, the first obstacle being stationary, or the first obstacle moving in a direction away from the intersection.

[0184] S930: Control the vehicle at least according to the moving direction of the first obstacle.

[0185] Optionally, when the first obstacle moves toward the intersection, the vehicle is controlled at least according to the moving direction of the first obstacle, including: controlling the vehicle to give way to the first obstacle, or controlling a prompt device to prompt a user to slow down.

[0186] Optionally, the method 900 also includes: before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, determining that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image.

[0187] Optionally, the dividing line between the first sub-area and the second sub-area is the first dividing line, and before controlling the vehicle to give way to the first obstacle, or controlling the prompt device to prompt the user to slow down, the method 900 also includes: determining, at least based on the third frame image and the fourth frame image, that the rotation speed of the first dividing line around the preset point is greater than or equal to the second preset speed.

[0188] The above method 300, method 600, method 800 or method 900 can be performed by the above Figure 1 The method 300, method 600, method 800 or method 900 may be executed by the above-mentioned computing platform 120, or the method 300, method 600, method 800 or method 900 may be executed by a system consisting of a computing platform 120 and a camera, or the method 300, method 600, method 800 or method 900 may be executed by a system-on-chip (SoC) in the above-mentioned computing platform 120, or the method 300, method 600, method 800 or method 900 may be executed by a processor, circuit or chip in the computing platform 120, or the method 300, method 600, method 800 may be executed by a server.

[0189] The above method 300, method 600, method 800 or method 900 may be independent embodiments, or the method 300, method 600, method 800 or method 900 may be combined with each other.

[0190] For example, when it is determined that an obstacle is moving toward an intersection through the information of a reflector in an image captured by a camera and that the obstacle is moving toward an intersection through a change in the area of ​​a bright area in an observation region, the vehicle may be controlled to slow down and yield, or a prompt device may be controlled to prompt the user to slow down.

[0191] For another example, when it is determined through the information of the reflector in the image captured by the camera that an obstacle is moving toward the intersection and the information of the reflector in the image captured by the camera determines that the moving speed of the obstacle is greater than or equal to a first preset speed, and it is determined through the image captured by the camera that the area of ​​the bright area in the observation area is gradually increasing, the vehicle can be controlled to slow down and give way, or the prompt device can be controlled to prompt the user to slow down.

[0192] For another example, when it is determined through the information of the reflector in the image captured by the camera that the obstacle is moving toward the intersection and it is determined through the image captured by the camera that the area of ​​the bright area in the observation area is gradually increasing and the rotation speed of the interface between the bright area and the dark area around point F is greater than or equal to the second preset speed, the vehicle can be controlled to slow down and give way, or the prompt device can be controlled to prompt the user to slow down.

[0193] Fig.10 FIG. 1 is a schematic block diagram of a control device 1000 provided in an embodiment of the present application. Fig.10 As shown, the device 1000 includes: an acquisition unit 1010, used to acquire a first image captured by a first camera in a vehicle, the first image including information of a reflector in an intersection, the intersection being an intersection of a first section and a second section, the vehicle being located in the first section, and the reflector being used to reflect obstacles in the second section; a control unit 1020, used to control the vehicle at least based on the first image.

[0194] Optionally, the first image includes a first frame image and a second frame image, and the device 1000 also includes: a first determination unit, used to determine the moving direction of the first obstacle in the second road section based on at least the first frame image and the second frame image; wherein the control unit 1020 is used to: when the moving direction indicates that the first obstacle is moving towards the intersection, control the vehicle to give way to the first obstacle, or control the prompt device to prompt the user to slow down.

[0195] Optionally, the first determination unit is used to determine the moving direction of the first obstacle based at least on a relative position relationship between the first obstacle and the first reference object in the first frame image and a relative position relationship between the first obstacle and the first reference object in the second frame image.

[0196] Optionally, the first determination unit is also used to: before the control unit 1020 controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, determine that the moving speed of the first obstacle is greater than or equal to the first preset speed, at least based on the relative position relationship between the first obstacle and the first reference object in the first frame image, and the relative position relationship between the first obstacle and the first reference object in the second frame image.

[0197] Optionally, the intersection is located in an underground garage, and the first reference object includes at least one of a parking space line, other vehicles parked in the parking space, and a pillar.

[0198] Optionally, the device also includes a second determination unit, and the acquisition unit 1010 is also used to acquire a third frame image and a fourth frame image captured by the second camera in the vehicle before the control unit 1020 controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, wherein the acquisition time of the third frame image is later than the acquisition time of the fourth frame image, and the third frame image and the fourth frame image include information of a first area in the intersection, the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; the second determination unit is used to determine that the area of ​​the first sub-area in the third frame image is larger than the area of ​​the first sub-area in the fourth frame image, or to determine that the area of ​​the second sub-area in the third frame image is smaller than the area of ​​the second sub-area in the fourth frame image.

[0199] Optionally, the second determination unit is also used to determine that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image before the control unit 1020 controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

[0200] Optionally, the dividing line between the first sub-area and the second sub-area is the first dividing line, and the second determination unit is further used to determine that the rotation speed of the first dividing line around a preset point is greater than or equal to a second preset speed, at least based on the third frame image and the fourth frame image, before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

[0201] Optionally, the first determining unit is further configured to determine an obstacle of a preset type from the first image before determining the moving direction of the first obstacle, the obstacles of the preset type including the first obstacle.

[0202] For example, the acquisition unit 1010 may be Figure 1 The computing platform or the processing circuit, processor or controller in the computing platform. Taking the acquisition unit 1010 as the processor 121 in the computing platform as an example, the processor 121 can acquire the first image acquired by the first camera, or the processor 121 can acquire the second image acquired by the second camera.

[0203] For another example, the control unit 1020 may be Figure 1The computing platform in the computing platform or the processing circuit, processor or controller in the computing platform. Taking the control unit 1020 as the processor 122 in the computing platform as an example, the processor 122 can obtain the image obtained by the processor 121 to control the vehicle. For example, the processor 122 can determine whether there is an obstacle of a preset type in the second section based on the image including the reflector obtained by the processor 121. For another example, the processor 122 can determine the moving speed of the obstacle of the preset type toward the intersection and the distance between the obstacle of the preset type and the intersection based on the image including the reflector obtained by the processor 121. For another example, when the processor 122 determines that the obstacle is moving toward the intersection based on the image including the reflector obtained by the processor 121, the processor 122 sends an instruction to the braking device, the instruction is used to instruct the braking device to control the vehicle to decelerate, or the processor 122 can control the display screen to display a prompt message, the prompt message is used to prompt the user to decelerate.

[0204] The functions implemented by the above acquisition unit 1010 and the functions implemented by the control unit 1020 can be implemented by different processors respectively, or all functions can be implemented by the same processor, which is not limited in the embodiment of the present application.

[0205] Fig.11 A schematic block diagram of a control device 1100 provided in an embodiment of the present application is shown, and the device 1100 includes: an acquisition unit 1110, used to acquire a second image captured by a second camera in a vehicle on a first section, the second image including an image of a first area at an intersection, the first area including a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; a determination unit 1120, used to determine a moving direction of a first obstacle in the second section at least based on light changes in the first area, the intersection being an intersection of the first route and the second route; a control unit 1130, used to control the vehicle at least based on the moving direction of the first obstacle.

[0206] Optionally, the second image includes a third frame image and a fourth frame image, and the third frame image is acquired later than the fourth frame image. The determination unit 1120 is used to: determine that the first obstacle is moving toward the intersection when the area of ​​the first sub-region in the third frame image is larger than the area of ​​the first sub-region in the fourth frame image, or the area of ​​the second sub-region in the third frame image is smaller than the area of ​​the second sub-region in the fourth frame image; wherein the control unit 1130 is used to: control the vehicle to give way to the first obstacle, or control the prompt device to prompt the user to slow down.

[0207] Optionally, the determination unit is further used to determine that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image before the control unit 1130 controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

[0208] Optionally, the dividing line between the first sub-area and the second sub-area is the first dividing line, and the determination unit 1120 is further used to: before the control unit 1130 controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, determine that the rotation speed of the dividing line around the preset point is greater than or equal to the second preset speed, at least based on the third frame image and the fourth frame image.

[0209] It should be understood that the division of the units in the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. In addition, the units in the device can be implemented in the form of a processor calling software; for example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of the units of the device, wherein the processor is, for example, a general-purpose processor, such as a CPU or a microprocessor, and the memory is a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD. Taking FPGA as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured through the configuration file, so as to realize the functions of some or all of the above units. All units of the above device may be implemented entirely in the form of a processor calling software, or entirely in the form of a hardware circuit, or partially in the form of a processor calling software and the rest in the form of a hardware circuit.

[0210] Each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0211] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of SoC. The SoC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0212] An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps executed by the above embodiment.

[0213] Alternatively, if the device is located in a vehicle, the processing unit may be Figure 1 Processors 121-12n are shown.

[0214] An embodiment of the present application further provides a control system, which includes a computing platform and one or more collision sensors, wherein the computing platform includes the above-mentioned device 1000 or device 1100.

[0215] An embodiment of the present application further provides a vehicle, which may include the above-mentioned device 1000, or include the above-mentioned device 1100, or include the above-mentioned control system.

[0216] An embodiment of the present application further provides a server, which may include the above-mentioned device 1000 or device 1100.

[0217] An embodiment of the present application further provides a computer program product, which includes: a computer program code, and when the computer program code is run on a computer, the computer executes the above-mentioned vehicle control method.

[0218] An embodiment of the present application also provides a computer-readable medium, which stores a program code. When the computer program code runs on a computer, the computer executes the above-mentioned vehicle control method.

[0219] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0220] It should be understood that in the embodiment of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.

[0221] It should also be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0222] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0223] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0224] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0225] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0226] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0227] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0228] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered. Within the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A vehicle control method, characterized in that: include: Acquire a first image captured by a first camera in a vehicle, the first image including information of a reflector in an intersection, the intersection being an intersection of a first road section and a second road section, the vehicle being located in the first road section, and the reflector being used to reflect obstacles in the second road section; The vehicle is controlled based on at least the first image.

2. The method according to claim 1, characterized in that: The first image includes a first frame image and a second frame image, and the controlling the vehicle at least according to the first image includes: Determine a moving direction of a first obstacle in the second road section at least based on the first frame image and the second frame image; When the moving direction indicates that the first obstacle moves toward the intersection, the vehicle is controlled to give way to the first obstacle, or a prompting device is controlled to prompt a user to slow down.

3. The method according to claim 2, characterized in that The determining the moving direction of the first obstacle in the second road section at least based on the first frame image and the second frame image includes: The moving direction of the first obstacle is determined at least according to the relative position relationship between the first obstacle and the first reference object in the first frame image and the relative position relationship between the first obstacle and the first reference object in the second frame image.

4. The method according to claim 3, characterized in that Before controlling the vehicle to yield to the first obstacle, or controlling the prompting device to prompt the user to slow down, the method further includes: At least based on the relative position relationship between the first obstacle and the first reference object in the first frame image and the relative position relationship between the first obstacle and the first reference object in the second frame image, it is determined that the moving speed of the first obstacle is greater than or equal to a first preset speed.

5. The method according to claim 3 or 4, characterized in that: The intersection is located in an underground garage, and the first reference object includes at least one of a parking space line, other vehicles parked in the parking space, a pillar, and a wall.

6. The method according to any one of claims 2 to 5, characterized in that Before controlling the vehicle to yield to the first obstacle, or controlling the prompting device to prompt the user to slow down, the method further includes: Acquire a third frame image and a fourth frame image captured by a second camera in the vehicle, wherein the acquisition time of the third frame image is later than the acquisition time of the fourth frame image, the third frame image and the fourth frame image include information of a first area in the intersection, the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; Determine that the area of ​​the first sub-region in the third frame image is larger than the area of ​​the first sub-region in the fourth frame image, or determine that the area of ​​the second sub-region in the third frame image is smaller than the area of ​​the second sub-region in the fourth frame image.

7. The method according to claim 6, characterized in that Before controlling the vehicle to yield to the first obstacle, or controlling the prompting device to prompt the user to slow down, the method further includes: It is determined that the illumination intensity of the first sub-area in the third frame image is greater than the illumination intensity of the first sub-area in the fourth frame image.

8. The method according to claim 6 or 7, characterized in that: The boundary between the first sub-area and the second sub-area is a first boundary, and before the step of controlling the vehicle to yield to the first obstacle or controlling the prompting device to prompt the user to slow down, the method further includes: At least based on the third frame image and the fourth frame image, it is determined that the rotation speed of the first dividing line around the preset point is greater than or equal to a second preset speed.

9. The method according to any one of claims 2 to 8, characterized in that Before determining the moving direction of the first obstacle in the second road section at least based on the first frame image and the second frame image, the method further includes: Obstacles of a preset type are determined from the information of the reflector, and the obstacles of the preset type include the first obstacle.

10. A vehicle control device, characterized in that: include: an acquisition unit, configured to acquire a first image captured by a first camera in a vehicle, wherein the first image includes information of a reflector in an intersection, wherein the intersection is an intersection of a first road section and a second road section, the vehicle is located in the first road section, and the reflector is configured to reflect obstacles in the second road section; A control unit is used to control the vehicle at least according to the first image.

11. The device according to claim 10, characterized in that The first image includes a first frame image and a second frame image, and the device further includes: A first determining unit, configured to determine a moving direction of a first obstacle in the second road section at least based on the first frame image and the second frame image; Wherein, the control unit is used for: When the moving direction indicates that the first obstacle moves toward the intersection, the vehicle is controlled to give way to the first obstacle, or a prompting device is controlled to prompt a user to slow down.

12. The device according to claim 11, characterized in that The first determining unit is configured to: The moving direction of the first obstacle is determined at least according to the relative position relationship between the first obstacle and the first reference object in the first frame image and the relative position relationship between the first obstacle and the first reference object in the second frame image.

13. The device according to claim 12, characterized in that The first determining unit is further configured to: Before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down, it is determined that the moving speed of the first obstacle is greater than or equal to a first preset speed based on at least the relative position relationship between the first obstacle and the first reference object in the first frame image and the relative position relationship between the first obstacle and the first reference object in the second frame image.

14. The device according to claim 12 or 13, characterized in that The intersection is located in an underground garage, and the first reference object includes at least one of a parking space line, other vehicles parked in the parking space, and a pillar.

15. The device according to any one of claims 11 to 14, characterized in that The device further comprises a second determining unit, The acquisition unit is further used for acquiring a third frame image and a fourth frame image captured by a second camera in the vehicle before the control unit controls the vehicle to yield to the first obstacle, or controls the prompting device to prompt the user to slow down, wherein the acquisition time of the third frame image is later than the acquisition time of the fourth frame image, and the third frame image and the fourth frame image include information of a first area in the intersection, the first area includes a first sub-area and a second sub-area, and the light intensity of the first sub-area is greater than the light intensity of the second sub-area; The second determination unit is used to determine that the area of ​​the first sub-region in the third frame image is larger than the area of ​​the first sub-region in the fourth frame image, or to determine that the area of ​​the second sub-region in the third frame image is smaller than the area of ​​the second sub-region in the fourth frame image.

16. The device according to claim 15, characterized in that The second determination unit is further used to determine that the light intensity of the first sub-area in the third frame image is greater than the light intensity of the first sub-area in the fourth frame image before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

17. The device according to claim 15 or 16, characterized in that The boundary between the first sub-region and the second sub-region is a first boundary, The second determination unit is also used to determine that the rotation speed of the first dividing line around the preset point is greater than or equal to a second preset speed, at least based on the third frame image and the fourth frame image, before the control unit controls the vehicle to give way to the first obstacle, or controls the prompt device to prompt the user to slow down.

18. The device according to any one of claims 11 to 17, characterized in that The first determining unit is further configured to determine obstacles of a preset type from the information of the reflector before determining the moving direction of the first obstacle, wherein the obstacles of the preset type include the first obstacle.

19. A control device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 9.

20. A control system, characterized in that: It comprises a camera and a computing platform, wherein the computing platform comprises a control device as described in any one of claims 10 to 19.

21. A vehicle, characterized in that: The method comprises a control device as claimed in any one of claims 10 to 19, or a control system as claimed in claim 20.

22. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a computer, the method according to any one of claims 1 to 9 is implemented.

23. A chip, characterized in that: include: A circuit for executing the method according to any one of claims 1 to 9.

Images