Vehicle intersection automatic driving method and system based on binocular camera

Abstract

The invention belongs to the technical field of vehicle automatic driving, and particularly relates to a vehicle intersection automatic driving method and system based on a binocular camera. The method comprises the steps that in the vehicle steering process, vehicle front environment information is obtained; determining whether there is an obstacle in front of the vehicle according to the vehicle front environment information; and when the obstacle exists in front of the side of the vehicle, the obstacle side front-view camera is controlled to rotate, so that the obstacle is located in the visual area of the obstacle side front-view camera. The front-view camera provided by the invention can realize self-adaptive follow-up steering in the curve driving process, expand the environment perception view field and improve the driving safety.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle automatic driving, and in particular relates to a vehicle automatic driving method and system at an intersection based on a binocular camera. Background Art

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

[0003] With the development of intelligent driving technology, more and more car companies have opened up the city navigation function. As users' awareness of the city navigation function increases, the disadvantages of city navigation in scenarios such as lane changing, turning, and U-turns are becoming more and more prominent. Therefore, how to make the vehicle pass through the intersection more safely and comfortably under the city navigation function, and how to adapt to more complex scenarios have become the focus of attention.

[0004] The common hardware components of the city navigation system are the vehicle domain controller, a front binocular camera, two side front cameras, two side rear cameras, a rear camera, five millimeter wave radars and a laser radar. The basic logic of a vehicle turning or making a U-turn is to determine that it is currently at a road intersection based on positioning and map information, and to know that it is about to make a turn or U-turn based on navigation information. The surrounding scene is determined based on the front binocular camera and side front cameras, and the drivable area is output, and the turn or U-turn is executed according to the planned control.

[0005] When turning or making a U-turn, the vehicle mainly relies on the forward-looking binocular and side front cameras to judge the surrounding environment information and output the drivable area. However, since the cameras are all in a fixed area, they can only detect the area directly in front of the camera in a straight line. In the turning or U-turn scenario, since the vehicle is not traveling in a straight line, it will inevitably have a blind spot in the turning area. Since there are many traffic participants in daily driving, if the vehicle's surrounding environment cannot be detected in real time, it will bring potential risks to the vehicle's driving and affect the safety of driving and other traffic participants. Summary of the invention

[0006] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a method and system for automatic driving of a vehicle at an intersection based on a binocular camera.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0008] A first aspect of the present invention provides a vehicle intersection automatic driving method based on a binocular camera, comprising:

[0009] During the vehicle steering process, obtain the environment information in front of the vehicle;

[0010] According to the environmental information in front of the vehicle, determine whether there is an obstacle in front of the vehicle;

[0011] When there is an obstacle in front of the vehicle, the obstacle side front view camera is controlled to rotate so that the obstacle is within the visual area of ​​the obstacle side front view camera.

[0012] Furthermore, during the vehicle steering process, the steering wheel steering angle and vehicle status information are obtained;

[0013] The rotation angle of the obstacle side front view camera is determined according to the steering wheel steering angle and vehicle status information.

[0014] Furthermore, when the vehicle completes turning, the front-view camera is restored to the front-view state.

[0015] Furthermore, during the driving process of the vehicle, the vehicle positioning and navigation information is obtained;

[0016] Determine whether the vehicle needs to turn based on the vehicle positioning and navigation information;

[0017] When it is determined that the vehicle is to turn, the vehicle is controlled to turn.

[0018] Furthermore, when it is determined that the vehicle is about to turn, the turn signal lamp on the inner side of the vehicle is controlled to turn on.

[0019] Furthermore, during the driving process of the vehicle, the vehicle's environment information is obtained in real time;

[0020] Determine the vehicle's driving trajectory based on the vehicle's environment information;

[0021] Control the vehicle to travel according to the vehicle's driving trajectory.

[0022] A second aspect of the present invention provides a vehicle intersection automatic driving system based on a binocular camera, comprising: two front-view cameras and a domain controller; the two front-view cameras are installed on both sides of the front of the vehicle;

[0023] A front-view camera, used to obtain images in front of the vehicle;

[0024] The domain controller is used to obtain the environment information in front of the vehicle based on the image in front of the vehicle; determine whether there is an obstacle in front of the vehicle based on the environment information in front of the vehicle; when there is an obstacle in front of the vehicle, control the front-view camera on the obstacle side to rotate so that the obstacle is within the visual area of ​​the front-view camera on the obstacle side.

[0025] A third aspect of the present invention provides a computer device, the device comprising:

[0026] a processor adapted to execute a computer program;

[0027] A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, a vehicle intersection automatic driving method based on a binocular camera proposed in the first aspect is implemented.

[0028] The fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program is suitable for being loaded by a processor and executing a vehicle intersection automatic driving method based on a binocular camera proposed in the first aspect.

[0029] A fifth aspect of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements a vehicle intersection automatic driving method based on a binocular camera proposed in the first aspect.

[0030] One or more of the above technical solutions have the following beneficial effects:

[0031] The present invention installs two front-view cameras on the front windshield of the vehicle, and monitors whether there is an obstacle in front of the side of the vehicle during the turning process of the vehicle. When the obstacle is detected in front of the side of the vehicle, the front-view camera on the side of the obstacle is controlled to rotate, and the obstacle is locked in the visual area of ​​the front-view camera, so as to prevent the vehicle from having a visual blind spot during the turning process, thereby affecting the safe driving of the vehicle. At the same time, by arranging two front-view cameras in front of the vehicle, when one of the front-view cameras rotates, the two front-view cameras can still monitor the environment in front of the vehicle through cooperation, thereby improving driving safety and solving the problem of blind spots in turning areas.

[0032] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 The present invention is a flow chart of a method for autonomous driving at an intersection of a vehicle based on a binocular camera disclosed in an embodiment.

[0035] Figure 2 This is a schematic diagram of a straight-ahead scenario disclosed in an embodiment.

[0036] Figure 3 This is a schematic diagram of a steering scenario disclosed in an embodiment.

[0037] Figure 4The present invention is a structural diagram of an application system of a binocular camera-based vehicle intersection automatic driving method disclosed in an embodiment. DETAILED DESCRIPTION

[0038] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0039] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0040] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0041] In order to prevent the occurrence of visual blind spots during vehicle steering, thereby affecting driving safety, this embodiment proposes a vehicle intersection automatic driving method based on a binocular camera. The method is applied to vehicles with intelligent driving functions, such as Figure 4 As shown, the vehicle includes a self-driving domain controller, a smart camera, a surround-view camera, a steering control module, a braking control module, a body control module and a navigation and positioning module.

[0042] Self-driving domain controller: determines the vehicle's location at the traffic intersection based on navigation / positioning related information, and infers that the vehicle is about to make a turn, U-turn, or other turning action based on the navigation information; plans the vehicle's driving trajectory based on the surrounding environment input by the new intelligent camera and the surround camera, and controls the vehicle to perform corresponding turn signal control and control the vehicle to perform corresponding steering and braking.

[0043] The smart camera is a dual-camera front-view camera, which is installed on both sides of the front windshield of the vehicle to obtain the image in front of the vehicle. With the vehicle centerline angle as 0°, each front-view camera can rotate between -90° and +90°, and the rotation response time should be <500ms. Each camera can be controlled separately. The camera detection distance is >200m, and the field of view is >120°. The rotation and start and stop of the front-view camera are controlled by the self-driving domain controller, and the image in front of the vehicle obtained is input into the self-driving domain controller.

[0044] The surround-view camera is used to perceive the close-range environment around the vehicle and output video information to the self-driving domain controller. Together with the new smart camera, it inputs perception information into the self-driving domain controller and helps the vehicle plan its trajectory.

[0045] The navigation and positioning module is used to obtain the vehicle's driving path and send the vehicle's driving path to the self-driving domain controller.

[0046] The steering control module is used to respond to the steering request of the self-driving domain controller in real time according to the vehicle driving trajectory calculated by the self-driving domain controller.

[0047] The braking control module is used to respond to the braking request of the self-driving domain controller in real time according to the vehicle driving trajectory calculated by the self-driving domain controller.

[0048] The body control module is used to respond to the headlight control of the self-driving domain controller in real time according to the vehicle's driving trajectory calculated by the self-driving domain controller.

[0049] The application scenario of the vehicle intersection automatic driving method based on a binocular camera proposed in this embodiment is that in the process of intelligent driving, it is necessary to perceive the surrounding environment of the vehicle through the camera and then control the vehicle. However, since the camera can only obtain the image of the area directly in front of the camera in a straight line, when the vehicle turns, there will be a vehicle visual blind spot, affecting the safe driving of the vehicle.

[0050] In order to minimize the visual blind spots of the vehicle and ensure driving safety during the turning process, this embodiment proposes an automatic driving method for a vehicle at an intersection based on a binocular camera, which is applied to a vehicle with intelligent driving.

[0051] Next, a method for automatic driving at vehicle intersections based on a binocular camera proposed in this embodiment is described in detail.

[0052] This embodiment proposes a vehicle intersection automatic driving method based on a binocular camera, such as Figure 1-Figure 3 As shown, including:

[0053] During the vehicle steering process, obtain the environment information in front of the vehicle;

[0054] Determine whether there is an obstacle in front of the vehicle based on the environment information in front of the vehicle;

[0055] When there is an obstacle in front of the vehicle, the obstacle side front view camera is controlled to rotate so that the obstacle is within the visual area of ​​the obstacle side front view camera.

[0056] In this embodiment, during the vehicle steering process, the steering wheel steering angle and vehicle status information are obtained;

[0057] The rotation angle of the obstacle side front view camera is determined according to the steering wheel steering angle and vehicle status information.

[0058] Among them, the vehicle status information includes vehicle speed and basic vehicle parameters.

[0059] In this embodiment, when the vehicle completes turning, the front-view camera is restored to the front-view state.

[0060] In addition, when the obstacle in front of the vehicle leaves the visual area of ​​the front-view camera taking into account the rotation angle, the front-view camera is controlled to return to the forward-looking state.

[0061] The forward-looking state of the front-looking camera means that the front-looking camera faces the front of the vehicle and can obtain the scene image in front of the vehicle.

[0062] The visual area considering the rotation angle refers to the area where the front-view camera can capture images through the rotation angle.

[0063] This embodiment also obtains vehicle positioning and navigation information during vehicle driving;

[0064] Determine whether the vehicle needs to turn based on the vehicle positioning and navigation information;

[0065] When it is determined that the vehicle is to turn, the vehicle is controlled to turn.

[0066] In addition, when it is determined that the vehicle is about to turn, the turn signal on the inner side of the vehicle is turned on to alert surrounding vehicles and pedestrians.

[0067] This embodiment also obtains the vehicle's environment information in real time during the vehicle's driving process;

[0068] Determine the vehicle's driving trajectory based on the vehicle's environment information;

[0069] Control the vehicle to travel according to the vehicle's driving trajectory.

[0070] During driving, the vehicle's surrounding obstacle status is determined based on the vehicle's surrounding environment information, and the vehicle is braked and controlled based on the surrounding obstacle status.

[0071] In this embodiment, when the vehicle is moving straight ahead according to the vehicle positioning navigation information, Figure 2 As shown, the vehicle steering wheel has a small change in angle. At this time, the front camera's field of view is directly in front of the vehicle's direction of travel. In this scenario, the front camera is linked according to the steering wheel angle, that is, the angle of the front camera is controlled accordingly according to the steering wheel angle.

[0072] When the vehicle is about to turn or make a U-turn, it monitors whether there is an obstacle in front of the vehicle. Figure 3As shown, the front-view camera on one side of the obstacle is controlled to rotate, and the obstacle is locked in the visual area of ​​the front-view camera, so as to prevent the vehicle from having a visual blind spot during the turning process, which affects the safe driving of the vehicle. The front-view camera on the inside of the turn or U-turn can be adjusted at a small angle according to the steering wheel angle, and the front-view camera on the outside of the turn or U-turn can be rotated at a larger angle between the front side of the vehicle body and the driving direction as needed. At the same time, this embodiment sets two front-view cameras in front of the vehicle. When one of the front-view cameras rotates, the two front-view cameras can still monitor the environment in front of the vehicle, improve driving safety, solve the problem of blind spots in the turning area, and help the vehicle to safely complete the turn or lane change.

[0073] The embodiment of the present application also proposes a vehicle intersection automatic driving system based on a binocular camera, comprising: two front-view cameras and a domain controller; the two front-view cameras are installed on both sides of the front of the vehicle;

[0074] A front-view camera, used to obtain images in front of the vehicle;

[0075] The domain controller is used to obtain the environment information in front of the vehicle based on the image in front of the vehicle; determine whether there is an obstacle in front of the vehicle based on the environment information in front of the vehicle; when there is an obstacle in front of the vehicle, control the front-view camera on the obstacle side to rotate so that the obstacle is within the visual area of ​​the front-view camera on the obstacle side.

[0076] The present application also provides a computer device, the device comprising:

[0077] a processor adapted to execute a computer program;

[0078] A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the method for automatic driving at an intersection of a vehicle based on a binocular camera is implemented.

[0079] An embodiment of the present application also proposes a computer-readable storage medium, which stores a computer program, and the computer program is suitable for being loaded by a processor and executing the method for autonomous driving at a vehicle intersection based on a binocular camera.

[0080] An embodiment of the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method for automatic driving at a vehicle intersection based on a binocular camera.

[0081] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0082] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A vehicle intersection automatic driving method based on a binocular camera, characterized in that: include: During the vehicle steering process, obtain the environment information in front of the vehicle; According to the environmental information in front of the vehicle, determine whether there is an obstacle in front of the vehicle; When there is an obstacle in front of the vehicle, the obstacle side front view camera is controlled to rotate so that the obstacle is within the visual area of ​​the obstacle side front view camera.

2. The method for automatic driving at an intersection based on a binocular camera according to claim 1, characterized in that: During the vehicle steering process, obtain the steering wheel steering angle and vehicle status information; The rotation angle of the obstacle side front view camera is determined according to the steering wheel steering angle and vehicle status information.

3. The method for automatic driving at an intersection based on a binocular camera according to claim 1, characterized in that: When the vehicle completes the turn, the front view camera is restored to the front view state.

4. The method for automatic driving at an intersection based on a binocular camera according to claim 1, characterized in that: During the driving process of the vehicle, obtain the vehicle positioning and navigation information; Determine whether the vehicle needs to turn based on the vehicle positioning and navigation information; When it is determined that the vehicle is to turn, the vehicle is controlled to turn.

5. The method for automatic driving at an intersection based on a binocular camera as claimed in claim 4, characterized in that: When it is determined that the vehicle is about to turn, the turn signal lamp on the inner side of the vehicle is turned on.

6. The method for automatic driving at an intersection based on a binocular camera as claimed in claim 4, characterized in that: During the driving process of the vehicle, real-time information about the vehicle's environment is obtained; Determine the vehicle's driving trajectory based on the vehicle's environment information; Control the vehicle to travel according to the vehicle's driving trajectory.

7. A vehicle intersection automatic driving system based on a binocular camera, characterized in that: include: two forward-looking cameras and domain controller; Two forward-looking cameras are installed on both sides of the front of the vehicle; A front-view camera, used to obtain images in front of the vehicle; A domain controller is used to obtain the environment information in front of the vehicle based on the image in front of the vehicle; Based on the environmental information in front of the vehicle, determine whether there is an obstacle in front of the vehicle; when there is an obstacle in front of the vehicle, control the obstacle side front view camera to rotate so that the obstacle is within the visual area of ​​the obstacle side front view camera.

8. A computer device, characterized in that: The device comprises: a processor adapted to execute a computer program; A computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by the processor, implements a vehicle intersection automatic driving method based on a binocular camera as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing a vehicle intersection automatic driving method based on a binocular camera as described in any one of claims 1-6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the vehicle intersection automatic driving method based on a binocular camera as described in any one of claims 1-6.

Images