TWI777646B - System, method and vehicle for vheicle warning - Google Patents

Abstract

This application discloses a system, method and vehicle for vehicle waming. The vehicle waming system includes a visual sensing unit. The visual sensing unit includes a first camera and a second camera. The first camera is arranged on a left A column of the vehicle to acquire a first image information. The second camera is arranged on a right A column of the vehicle to acquire a second image information. A pre-processing unit is coupled to the visual sensing unit for pre-processing the first image information and the second image information to generate an image pre-processing information. The system further includes an image processing unit, which is used for processing the image information, identifying obstacles in blind areas, thereby reducing a risk of traffic accidents.

Description

Vehicle warning system, method and automobile

The present application relates to the technical field of automobile safety, and in particular, to a vehicle warning system, method and automobile.

With the development of the economy and the advancement of technology, the car ownership is also increasing year by year. However, there are certain blind spots on the vehicle, so there is a greater safety hazard. At present, cars are often equipped with lane departure warning (Lane Departure Warning, LDW) systems and blind spot monitoring systems (Blind Spot Monitoring, BSM) to increase the driver's visible area, reduce accident injuries and driving burden. However, the LDW system and the BSM still have blind spots in the field of vision, and there are potential safety hazards.

In view of this, the present application provides a vehicle warning system, method and vehicle, which can collect information in the blind area of the driver's field of vision and improve the safety performance of the vehicle during driving.

The vehicle warning system of the present application includes: a visual sensing unit, the visual sensing unit includes a first camera and a second camera, the first camera is arranged on the left A-pillar of the car, and the first camera is used for acquiring first image information; the second camera is arranged on the right A-pillar of the car, and the second camera is used to acquire second image information; a preprocessing unit, the preprocessing unit is coupled to the visual a sensing unit for preprocessing the first image information and the second image information and an image processing unit, the image processing unit is coupled to the preprocessing unit and configured to generate obstacle identification information according to the image preprocessing information.

The vehicle warning method of the present application includes: acquiring first image information and second image information; preprocessing the first image information and the second image information to generate image preprocessing information; The image preprocessing information generates obstacle identification information; and the warning message is generated according to the obstacle identification information.

The automobile of the present application includes: the vehicle early warning system as described above.

The present application processes the image information through the image information in the blind area of the A-pillar of the vehicle, and can identify obstacles in the blind area, improve the safety of driving the vehicle, and reduce the risk of traffic accidents.

100: Vehicle warning system

110: Vision Sensing Unit

111: The first camera

112: Second camera

120: preprocessing unit

130: Image processing unit

140: Warning unit

150: Speed detection unit

160: Trajectory prediction unit

S100-S400: Steps

FIG. 1 is a schematic diagram of a vehicle blind spot in the related art.

FIG. 2 is a schematic diagram of a vehicle warning system.

FIG. 3 is a flow chart of a vehicle warning method.

In order to more clearly understand the above objects, features and advantages of the present application, the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features of the embodiments may be combined with each other unless there is conflict. Many specific details are set forth in the following description to facilitate a full understanding of the present application, and the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments.

It should be noted that although the logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a sequence different from that in the flowchart. The methods disclosed in the embodiments of the present application include one or more steps or actions for implementing the methods. Method steps and/or actions may be interchanged with each other without departing from the scope of the claimed items. In other words, unless a specific order of steps or actions is specified, the order and/or use of specific steps and/or actions may be modified without departing from the scope of the claims.

With the development of the economy and the advancement of technology, the car ownership is also increasing year by year. However, there are certain blind spots on the vehicle, so there is a greater safety hazard. At present, cars are often equipped with Lane Departure Warning (LDW) and Blind Spot Monitoring (BSM) to increase the driver's visible area and reduce accident injuries and driving burden. However, the LDW system and the BSM still have blind spots in the field of vision, and there are potential safety hazards. For example, please refer to FIG. 1 , which is a schematic diagram of a blind spot of a vehicle. Among them, the dotted area is the field of view of the LDW system and the field of view of the BSM system, and the shaded area is the blind area of the field of view. As shown in Figure 1, even a vehicle equipped with both LDW and BSM still has a blind spot. If the memory in the blind area of vision is located in the vehicle or other obstacles, the driver may not be able to make accurate judgments, which may lead to the occurrence of traffic accidents, which has a higher safety risk.

Therefore, the embodiments of the present application provide a vehicle warning system, method, storage medium, and automobile, which can detect obstacles in the blind area of the vehicle's field of vision, and issue a warning.

Some embodiments of the application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments may be combined with each other without conflict.

2 is a schematic diagram of the connection of a vehicle warning system 100 provided by an embodiment of the present application, which at least includes the following parts: a visual sensing unit 110, a preprocessing unit 120, an image processing unit 130, an warning unit 140, a speed detection unit 150, and a trajectory prediction unit unit 160.

In this embodiment of the present application, the visual sensing unit 110 includes a first camera 111 and a second camera 112 . The first camera 111 is arranged on the left A-pillar of the car, and is used to obtain the left A-pillar of the car. image message later. The second camera 112 is disposed on the right A-pillar of the vehicle, and is used for acquiring image information behind the A-pillar on the right side of the vehicle.

In the embodiment of the present application, the preprocessing unit 120 is coupled (eg, electrically connected) with the first camera 111 and the second camera 112, and is used to convert the image information behind the A-pillar on the left side of the vehicle and the image behind the A-pillar on the right side of the vehicle. The message format of the message is converted into image preprocessing information that can be recognized by the machine vision algorithm, so that the image processing unit 130 can recognize and process the image preprocessing information.

In the embodiment of the present application, the image processing unit 130 is coupled to the preprocessing unit 120 for generating obstacle identification information according to a machine vision algorithm. The obstacle identification information includes, but is not limited to, obstacle type, obstacle trajectory, and obstacle relative speed. For example, in one embodiment, the image processing unit 130 may generate obstacle categories according to the machine vision algorithm. The obstacle categories include: vehicles, pedestrians, bicycles, motorcycles, battery cars and other obstacles.

It can be understood that after identifying the obstacle type, the image processing unit 130 is further configured to locate the obstacle according to the identified obstacle type and the wheel detection algorithm. For example, if the detected category of the obstacle is a category including wheels (eg, vehicle, bicycle, motorcycle, battery car), the obstacle is located according to the wheel detection algorithm.

It can be understood that if the type of the obstacle is a vehicle, the image processing unit 130 is further configured to determine whether the obstacle contains a window according to the window detection algorithm, and locate the vehicle according to the position of the window.

It can be understood that, in the embodiment of the present application, after the image processing unit 130 detects an obstacle in the blind area, the image processing unit 130 can determine whether the type of the obstacle is a vehicle through wheel detection. For example, the image processing unit 130 may detect the received image information from the visual sensing unit 110 by using a circle or ellipse detection algorithm to determine whether the detected obstacle is a vehicle. Since the wheels appear to be round or oval when a vehicle traverses the scene, the wheel can be detected by a round or oval detection algorithm to determine whether an obstacle is a vehicle based on the wheel.

Of course, in other embodiments, the wheel is not limited to be detected by the circular or elliptical detection algorithm, and the wheel can also be detected by using the V-transform algorithm or other algorithms or methods. For example, the vehicle may be detected by one or more of tire detection, rim detection, spoke detection, and/or hub detection.

It can be understood that, as described above, when it is determined that the type of the obstacle is a vehicle, the image processing unit 130 is further configured to determine whether the obstacle contains a window according to the window detection algorithm, and locate the vehicle according to the position of the window. For example, car window detection using color differences or line effects. Of course, in other embodiments, the image processing unit 130 is not limited to use the above-mentioned color difference or straight line special effects to perform vehicle window detection, but can also perform vehicle window detection through other detection methods, which are not specifically limited herein.

The speed detection unit 150 is coupled to the visual sensing unit 110 for receiving the image of the visual sensing unit 110 . The speed detection unit 150 performs speed detection according to the image of the visual sensing unit 110 and a high-speed visual algorithm, so as to obtain the relative speed between the obstacle and the vehicle. Of course, in other embodiments, the speed detection unit 150 can also be connected to a radar, an infrared range finder and other devices in the car to calculate the relative speed according to the relative displacement and time between the car and the obstacle.

In this embodiment of the present application, the trajectory prediction unit 160 is coupled to the speed detection unit 150 , and is configured to predict the running trajectory of the obstacle according to the relative speed detected by the speed detection unit 150 . In one of the embodiments, the trajectory prediction unit 160 may also be coupled to the first camera 111 and the second camera 112, so as to be used according to the image information collected from the first camera 111 and the second camera 112 and from the speed detection unit 150. The relative velocity is used to predict the obstacle trajectory. Of course, in other embodiments, the trajectory prediction unit 160 can be connected to other information collection devices in the vehicle to predict the trajectory of obstacles. For example, the trajectory prediction unit 160 can obtain the distance between the obstacle and the car according to the on-board radar The distance between the obstacles and the car is calculated according to the distance and the position of the two obstacles measured by the on-board radar.

It can be understood that, in this embodiment of the present application, the image processing unit 130 is further coupled to the trajectory prediction unit 160 . The image processing unit 130 is used for receiving the running trajectory of the obstacle transmitted by the trajectory prediction unit 160, and judging whether there is a risk of a traffic accident according to the running trajectory and the relative speed of the obstacle. If the image processing unit 130 determines that there is a risk of sending a traffic accident according to the running track and relative speed of the obstacle, it controls the warning unit 140 to generate a warning message.

In a possible implementation manner of the present application, the warning messages include sound and light warnings, warning messages displayed on the center console, steering wheel vibrations, etc., which are not limited in this application.

It can be understood that the image processing unit 130 may further grade the warning message. For example, when the risk level is low, the image processing unit 130 may control the warning unit 140 to only light up the warning. When the risk level is high, the image processing unit 130 can control the warning unit 140 to give a sound warning. When the risk level is the highest, the image processing unit 130 can control the warning unit 140 to perform a sound warning prompt and a steering wheel vibration prompt to ensure that the driver can receive the warning message and take timely action.

In another possible implementation, the image processing unit 130 is further configured to, after receiving the obstacle trajectory prediction information transmitted by the trajectory prediction unit 160 , if it is determined that the vehicle still needs to turn or merge when the vehicle in the blind spot memory is on the obstacle, Then, the warning unit 140 is controlled to give a warning. For example, when the image processing unit 130 obtains from the trajectory prediction unit 160 that there is a vehicle in the blind spot on the left side of the vehicle and still wants to turn left, the warning unit 140 can be controlled to issue a sound warning or steering wheel vibration to warn.

In the embodiment of the present application, the warning unit 140 may include a sound, a display screen, a warning light, and the like. The warning unit 140 is coupled to the image processing unit 130 for displaying a corresponding warning message after receiving the obstacle identification information transmitted by the image processing unit 130 . For example, in one of the embodiments, the warning unit 140 may be disposed on the left and right side mirrors of the vehicle. In this way, after detecting the left side of the vehicle When the blind spot memory is in an obstacle, the image processing unit 130 can control the warning unit 140 to display a warning sign in the left rearview mirror.

In another possible implementation, the warning unit 140 may also be disposed in the center console of the vehicle or inside the A-pillar of the vehicle. In this way, after the image processing unit 130 detects that there is a vehicle in the blind spot, a warning message is displayed on the vehicle center console or the inner side of the A-pillar. For example, if the image processing unit 130 detects an obstacle in the blind spot memory on the left side of the car, the warning unit can display a warning message on the inner side of the left A-pillar of the car.

In the embodiment of the present application, the vehicle warning system 100 proposed in the present application can be used in combination with a lane departure warning system and a blind spot monitoring system. As shown in FIG. 1 , the lane departure warning system is used for monitoring obstacles in front of the vehicle, the vehicle warning system 100 is used for monitoring obstacles on the side of the vehicle, and the blind spot monitoring system is used for monitoring obstacles behind the vehicle. The combination of the three vehicle monitoring systems can realize all-round monitoring of the vehicle, eliminate the blind spot of vision, and improve the safety factor of the vehicle during operation.

FIG. 3 is a schematic flowchart of a vehicle warning method provided by an embodiment of the present application. The warning method shown in FIG. 3 is applied to the above-mentioned vehicle warning system 100 .

S100: Acquire first image information and second image information.

In the embodiment of the present application, the vehicle warning system 100 obtains the first image information through the first camera 111 , and obtains the second image information through the second camera 112 .

S200: Preprocess the first image information and the second image information to generate image preprocessing information.

In this embodiment of the present application, the preprocessing unit 120 may process the first image information and the second image information to generate image preprocessing information. For example, the information format of the first image information and the second image information can be converted into image preprocessing information that can be recognized by the machine vision algorithm through the preprocessing unit 120, so that the image processing unit 130 can recognize and process the image. Preprocessed messages.

S300: Generate obstacle identification information according to the image preprocessing information.

In the embodiment of the present application, the image processing unit 130 can be used to classify obstacles according to the image preprocessing information and the machine vision algorithm.

S400: Generate a warning message according to the obstacle identification information.

In the embodiment of the present application, the image processing unit 130 determines whether an alert message needs to be generated through the alert unit 140 according to the identification result of the obstacle. If an alert message needs to be generated, the image processing unit 130 controls the alert unit 140 to generate an alert message.

In the embodiment of the present application, the method may further include performing speed detection according to a high-speed visual algorithm and the first image information or the second image information, so as to obtain the relative speed between the obstacle and the vehicle. Specifically, the speed detection unit 150 can be coupled to the visual sensing unit 110, and the speed detection unit 150 can perform speed detection according to the first image information or the second image information, so as to obtain the distance between the obstacle and the vehicle. the relative speed.

In the embodiment of the present application, the method may further include predicting the running trajectory of the obstacle according to the relative speed. Specifically, the trajectory prediction between the obstacle and the vehicle can be obtained through the trajectory prediction unit 160 .

In the embodiment of the present application, the method may further include generating a warning message according to the trajectory prediction between the obstacle and the vehicle. Specifically, the image processing unit 130 is coupled to the trajectory prediction unit 160 and the warning unit 140 . After acquiring the trajectory prediction information from the trajectory prediction unit 160, the image processing unit 130 determines whether there is a collision risk, and controls the warning unit 140 to generate a warning message if there is a collision risk. It can be understood that the above-mentioned image processing unit 130 may be a single chip. For example, the image processing unit 130 may be a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), or a System On Chip (SoC). , can also be a central processing unit (Central Processor Unit, CPU), can also be a network processor (Network Processor, NP), can also be a coefficient bit signal processing circuit (Digital Signal Processor, DSP), can also be a microcontroller (Micro Controller Unit, MCU), can also be a Programmable Logic Device (Programmable Logic Device, PLD) or other integrated chips.

It can be understood that, each step of the above-mentioned method can be completed by a hardware integrated logic circuit in the image processing unit 130 or an instruction in the form of software. The steps of the methods disclosed in conjunction with the embodiments of the present application can be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the image processing unit 130 . The software module can be located in random memory, flash memory, read-only memory, programmable read-only memory or electrically readable and writable programmable memory, registers and other mature storage media in the field.

It can be understood that, the image processing unit 130 in the embodiment of the present application may be an integrated circuit chip, which has signal processing capability. In the implementation process, each step of the above-mentioned method embodiments can be completed by the hardware integrated logic circuit in the processor or the instructions in the form of software. The aforementioned processors may be general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices , Discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the methods disclosed in conjunction with the embodiments of the present application can be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can be located in random memory, flash memory, read-only memory, programmable read-only memory or electrically readable and writable programmable memory, registers and other mature storage media in the field. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.

It can be understood that the first camera 111 and the second camera 112 in the visual sensing unit 110 are used to collect visual images of the blind spot of the vehicle. The working principle of the first camera 111 and the second camera 112 is to capture images through the lens, and then the captured images are processed by the internal photosensitive elements and control elements. After processing, it is converted into a digital signal that can be recognized by other systems; other systems obtain the digital signal through the transmission ports of the first camera 111 and the second camera 112, and then perform image restoration to obtain an image consistent with the actual scene. In practical applications, the field of view of the camera to collect image data, and the installation quantity and installation position of the camera can be further designed according to actual needs. The embodiments of the present application do not specifically limit the field of view, installation quantity, and installation position of the cameras.

It can be understood that the types of the first camera 111 and the second camera 112 can be selected according to different needs of users, as long as they can realize basic functions such as video recording, broadcasting and still image capturing. For example, the camera may be one or more types of commonly used in-vehicle cameras, such as a binocular camera and a monocular camera.

It can be understood that, if selected according to the signal type, the first camera 111 and the second camera 112 can also be one or both types of digital cameras and analog cameras. The digital camera converts the captured analog signal into a digital signal for storage, while the analog camera uses a specific video capture card to convert the analog signal into digital mode, compress it and store it. If divided according to the image sensor type in the camera, the camera can also be one of the complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor, CMOS) type of camera and the charge-coupled device (Charge-Coupled Device, CCD) type of camera. or both.

It can be understood that, if divided according to the interface type, the first camera 111 and the second camera 112 can also be one of serial port, parallel port, Universal Serial Bus (USB) and FireWire interface (IEEE1394) or one of them. Many types. The embodiment of the present application also does not specifically limit the type of the camera.

An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned vehicle warning method is implemented.

The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or transistor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

An embodiment of the present application provides a vehicle, including the above-mentioned vehicle warning system 100, or, the above-mentioned computer-readable storage medium.

In the embodiments of the present application, the automobiles include vehicles such as gasoline vehicles, electric vehicles, and fuel cell vehicles, or may also be vehicles such as motorized two-wheeled vehicles and motorized three-wheeled vehicles.

Those skilled in the art should realize that the above embodiments are only used to illustrate the present application, but not to limit the present application. Appropriate changes and variations fall within the scope of protection claimed in this application.

100: Vehicle warning system

110: Vision Sensing Unit

111: The first camera

112: Second camera

120: preprocessing unit

130: Image processing unit

140: Warning unit

150: Speed detection unit

160: Trajectory prediction unit

Claims (10)

A vehicle warning system, applied to an automobile, is improved in that the system includes: a visual sensing unit, the visual sensing unit includes a first camera and a second camera, and the first camera is arranged on the left side of the automobile A-pillar, the first camera is used to obtain the first image information; the second camera is arranged on the right A-pillar of the car, and the second camera is used to obtain the second image information; the preprocessing unit, The preprocessing unit is coupled to the visual sensing unit for preprocessing the first image information and the second image information to generate image preprocessing information; and an image processing unit, the The image processing unit is coupled to the preprocessing unit, and is used for generating obstacle identification information according to the image preprocessing information, where the obstacle identification information includes an obstacle type; determining that the obstacle type is a vehicle, and according to the vehicle window The detection algorithm determines that the obstacle contains a window, and locates the vehicle based on the position of the window. The vehicle warning system according to claim 1, wherein the system further comprises a warning unit; the warning unit is coupled to the image processing unit, and is configured to generate a warning message according to the control of the image processing unit. The vehicle warning system of claim 1, wherein the image processing unit generates an obstacle identification message according to a machine vision algorithm. The vehicle warning system according to claim 3, wherein the obstacle identification information further includes: obstacle trajectory and obstacle relative speed. The vehicle warning system according to claim 4, wherein the types of obstacles include: vehicles, pedestrians, bicycles, motorcycles, battery cars and other obstacles. The vehicle warning system of claim 4, wherein the vehicle warns The system further includes a speed detection unit, the speed detection unit is coupled to the visual sensing unit, and is used for acquiring relative speed information between the vehicle and the obstacle according to the first image information and the second image information ; a trajectory prediction unit, the trajectory prediction unit is coupled to the speed detection unit and the image processing unit for predicting the running trajectory of the obstacle according to the relative speed information; the image processing unit is also used for The warning message is generated by the running track and relative speed of the obstacle. A vehicle warning method, which is improved by: acquiring first image information and second image information; preprocessing the first image information and the second image information to generate image preprocessing information ; Generate obstacle identification information according to the image preprocessing information, and the obstacle identification information includes an obstacle category; determine that the obstacle category is a vehicle, determine that the obstacle includes a car window according to the window detection algorithm, and according to The position of the vehicle window is used to locate the vehicle; and a warning message is generated according to the obstacle identification information. The vehicle warning method according to claim 7, wherein the obstacle identification information further comprises: obstacle trajectory and obstacle relative speed. The vehicle warning method according to claim 8, wherein the method further comprises: acquiring relative speed information between the vehicle and the obstacle according to the first image information and the second image information; The relative speed information predicts the running track of the obstacle; the warning message is generated according to the running track and the relative speed of the obstacle. An automobile improved by comprising: A vehicle warning system as claimed in any one of claims 1 to 6.

Images