Vehicle-mounted early warning system and vehicle-mounted early warning method

Abstract

The invention provides a vehicle-mounted early warning system and a vehicle-mounted early warning method. The method comprises the following steps: scanning a first detection area by a detector to generate a detection result; obtaining a rate from a controller area network bus of the vehicle; judging whether the rate is greater than a threshold; in response to the rate being greater than the threshold, scanning, by the detector, a second detection area different from the first detection area to update the detection result; and controlling the carrier according to the detection result. Therefore, the range of the detection area can be adjusted according to the speed of the carrier.

Description

TECHNICAL FIELD

[0001] The present application relates to a collision warning system, and in particular, to a vehicle collision warning system and a vehicle collision warning method. BACKGROUND

[0002] Conventional collision warning systems detect other vehicles around a vehicle using a sensor with a fixed sensing range, and determine whether to alert the driver or intervene in the control of the vehicle based on the detection results. When the vehicle is in a low-speed state (e.g., a vehicle is trapped in a vehicle array), the collision warning system with a fixed sensing range is prone to false alarms. In addition, the fixed sensing range is also difficult to adapt to various complex road environments. SUMMARY

[0003] The present application provides a vehicle collision warning system and a vehicle collision warning method, which can adjust the range of the detection area according to the speed of the vehicle.

[0004] A vehicle collision warning system for a vehicle according to the present application includes a transceiver, a detector, and a processor. The transceiver is communicatively connected to a controller area network bus of the vehicle. The detector scans a first detection area to generate a detection result. The processor is coupled to the transceiver and the detector, wherein the processor is configured to perform: obtaining a speed from the controller area network bus; determining whether the speed is greater than a threshold; in response to the speed being greater than the threshold, scanning a second detection area by the detector to update the detection result, wherein the second detection area is different from the first detection area; and controlling the vehicle according to the detection result.

[0005] In an embodiment of the present application, the processor is further configured to perform: determining whether the speed is less than or equal to the threshold; and in response to the speed being less than or equal to the threshold, stopping scanning the second detection area.

[0006] In an embodiment of the present application, the vehicle collision warning system further includes a human-machine interface. The human-machine interface is coupled to the processor, wherein the processor receives a user operation through the human-machine interface, and configures the second detection area according to the user operation.

[0007] In an embodiment of the present application, the detector includes an image capturing device, wherein the processor is further configured to perform: obtaining a perspective image through the detector; and performing inverse perspective projection on the perspective image to generate a top view, and outputting the top view through the human-machine interface.

[0008] In an embodiment of the present application, the processor is further configured to perform: in response to outputting the top view, receiving a user operation for the top view through the human-machine interface.

[0009] In an embodiment of the present disclosure, the detector includes an image capturing device, and the processor is further configured to: obtain a perspective image by the detector; and input a portion of the perspective image to the machine learning model to generate or update the detection result, wherein the portion corresponds to the first detection region or the second detection region.

[0010] In an embodiment of the present disclosure, the size of the second detection region is positively correlated with the speed.

[0011] In an embodiment of the present disclosure, the first detection region includes a first sub-region and a second sub-region, and the processor is further configured to: determine whether the target object invades the first sub-region or the second sub-region according to the detection result; control the vehicle to perform emergency braking and output warning information in response to determining that the target object invades the first sub-region; and control the vehicle to output warning information in response to determining that the target object invades the second sub-region.

[0012] In an embodiment of the present disclosure, the second detection region includes a first sub-region and a second sub-region, and the processor is further configured to: determine whether the target object invades the first sub-region or the second sub-region according to the detection result; control the vehicle to perform pre-braking and output warning information in response to determining that the target object invades the first sub-region; and control the vehicle to output warning information in response to determining that the target object invades the second sub-region.

[0013] In an embodiment of the present disclosure, a virtual straight line passes through the detector, a first point in the first detection region, and a second point in the second detection region, wherein a first distance between the first point and the detector is less than a second distance between the second point and the detector.

[0014] A vehicle pre-warning method for a vehicle includes: scanning a first detection region by a detector to generate a detection result; obtaining a speed from a controller area network bus of the vehicle; determining whether the speed is greater than a threshold; in response to the speed being greater than the threshold, scanning a second detection region by the detector to update the detection result, wherein the second detection region is different from the first detection region; and controlling the vehicle according to the detection result.

[0015] Based on the above, the vehicle pre-warning system of the present disclosure can further scan an additional detection region that is more peripheral according to the speed of the vehicle in addition to scanning the main detection region. The additional detection region can help the vehicle pre-warning system to discover a target approaching the vehicle at an early stage and perform a response measure in advance to avoid a collision. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A schematic diagram of a vehicle pre-warning system according to an embodiment of the present disclosure is shown.

[0017] Figure 2 A flowchart of a method of vehicle warning according to an embodiment of the present application is shown.

[0018] Figure 3 A top view of a detection area according to an embodiment of the present application is shown.

[0019] Figure 4 A perspective image of a detection area according to an embodiment of the present application is shown.

[0020] Figure 5 A schematic diagram of a method of vehicle warning according to an embodiment of the present application is shown.

[0021] Brief description of the drawings

[0022] 100: vehicle warning system; 11: data acquisition module; 110: processor; 12: main detection area module; 120: storage medium; 13: additional detection area module; 130: transceiver; 14: human-machine interface module; 140: detector; 15: control module; 16: communication module; 150: human-machine interface; 30: top view; 31: main detection area; 32: additional detection area; 311, 321: point; 40: perspective image; 50: virtual straight line; D1, D2: distance; S201, S202, S203, S204, S205, S206, S207, S501, S502, S503, S504, S505: step. DETAILED DESCRIPTION

[0023] Figure 1 A schematic diagram of a vehicle warning system 100 according to an embodiment of the present application is shown. The vehicle warning system 100 can include a processor 110, a storage medium 120, and a transceiver 130. In an embodiment, the vehicle warning system 100 can further include a detector 140 or a human-machine interface 150. The vehicle warning system 100 can be disposed in a vehicle (e.g., an automobile).

[0024] The processor 110 is, for example, a central processing unit (CPU), or other programmable general purpose or special purpose micro control unit (MCU), microprocessor, digital signal processor (DSP), programmable controller, application specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (FPGA), or other similar element or combination thereof. The processor 110 can be coupled to the storage medium 120, transceiver 130, detector 140, or human-machine interface 150, and access and execute a plurality of modules and various application programs stored in the storage medium 120.

[0025] The storage medium 120 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid state drive (SSD), or similar element or combination thereof. The storage medium 120 is, for example, a non-volatile computer-readable storage medium, and can be configured to store a plurality of modules or various application programs executable by the processor 110. In the present embodiment, the storage medium 120 can store a plurality of modules including a data acquisition module 11, a main detection area module 12, an additional detection area module 13, a human-machine interface module 14, a control module 15, and a communication module 16, the functions of which will be described later.

[0026] The transceiver 130 transmits or receives a signal in a wireless or wired manner. The transceiver 130 can also perform operations such as low-noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and the like. The communication module 16 can communicate with an external electronic device through the transceiver 130. For example, the communication module 16 can be communicatively connected to a controller area network (CAN) bus of a vehicle or a cloud server through the transceiver 130. In an embodiment, the communication module 16 can obtain vehicle information from the CAN bus of the vehicle through the transceiver 130, where the vehicle information includes, for example, information such as a speed, an acceleration, an engine speed, a fuel or an engine temperature of the vehicle. In an embodiment, the communication module 16 can transmit a control instruction to the CAN bus of the vehicle through the transceiver 130 to control the vehicle. For example, the communication module 16 can control the operation of a brake system or an engine of the vehicle through the control instruction, so that the vehicle performs braking or pre-braking (e.g., pre-deceleration).

[0027] The detector 140 is, for example, an image capturing device, a radar, or a light detection and ranging (LiDAR). The detector 140 can have a detection area. The processor 110 can scan the detection area through the detector 140 to generate a detection result. The detection result can indicate whether an object has intruded into the detection area. The detection area of the detector 140 can be polygonal or arc-shaped, but is not limited thereto.

[0028] The human-machine interface 150 can include an input device (e.g., a touch screen or a key) or an output device (e.g., a touch screen, a display, or a speaker). A user can interact with the human-machine interface module 14 of the vehicle early warning system 100 by operating the human-machine interface 150.

[0029] Figure 2 A flowchart of a method for vehicle warning is shown according to an embodiment of the present application, where the method can be implemented by the vehicle early warning system 100 as shown in Figure 1 In step S201, the data acquisition module 11 can obtain a speed of the vehicle from the CAN bus of the vehicle through the communication module 16.

[0030] On the other hand, the data acquisition module 11 can obtain a detection result from the main detection area module 12. Specifically, the detector 140 can have a main detection range. The main detection area module 12 can scan the main detection range through the detector 140 to obtain the detection result. Figure 3 and Figure 4According to an embodiment of the present application, a top view 30 and a perspective view 40 of the detection area are shown, respectively. The view of the top view 30 can correspond to the top of the vehicle, and the view (or driving view) of the perspective view 40 can correspond to the front of the vehicle. The main detection range 31 of the detector 140 is, for example, a sector or polygonal area centered at the detector 140. The detection result generated by the main detection area module 12 can indicate whether an object has invaded the main detection range 31.

[0031] Returning to Figure 2 In step S202, the data collection module 11 can determine whether the speed is greater than a threshold. If the speed is greater than the threshold, step S203 is performed. If the speed is less than or equal to the threshold, step S206 is performed.

[0032] In step S203, the additional detection area module 13 can activate the additional detection area 32 of the detector 140, as shown in Figure 3 or Figure 4 wherein the additional detection area 32 is different from the main detection area 31.

[0033] The additional detection area 32 is, for example, surrounded outside the main detection area 31. Specifically, assume that a virtual straight line 50 passes through the detector 140, a point 311 of the main detection area 31, and a point 321 of the additional detection area 32. The distance D1 between the point 311 and the detector 140 can be less than the distance D2 between the point 321 and the detector 140. That is, compared to the main detection area 31, the additional detection area 32 is farther away from the detector 140 or the vehicle.

[0034] In an embodiment, the size of the additional detection area 32 can be positively correlated with the speed of the vehicle. When the speed of the vehicle is faster, the size of the additional detection area 32 is larger, or the distance between the point of the additional detection area 32 farthest from the detector 140 and the detector 140 is farther. That is, when the vehicle is in a high-speed driving state, the detection area of the vehicle-mounted early warning system 100 can be expanded to more promptly detect objects approaching the vehicle and perform safety measures.

[0035] In an embodiment, the detection region (e.g., the primary detection region 31 or the additional detection region 32) of the detector 140 can be customized by a user. The human-machine interface module 14 can receive a user operation through the human-machine interface 150 and configure the detection region according to the user operation. Specifically, the data acquisition module 11 can obtain a perspective image (e.g., the perspective image 40) through the detector 140. Then, the processor 110 can perform inverse perspective mapping (IPM) on the perspective image to generate an overhead view (e.g., the overhead view 30). The human-machine interface module 14 can output the overhead view through the human-machine interface 150 for the user to refer. The overhead view can help the user to more clearly understand the actual position of the user-customized detection region relative to the vehicle. The user can operate the human-machine interface 150 based on the overhead view to generate the detection region. The user operation can be stored as a world coordinate. The primary detection region module 12 or the additional detection region module 13 can configure the primary detection region 31 or the additional detection region 32 according to the world coordinate.

[0036] In step S204, the additional detection region module 13 can scan the additional detection region 32 through the detector 140 to update the detection result, wherein the updated detection result can indicate whether an object has intruded into the primary detection region 31 or the additional detection region 32.

[0037] In an embodiment, the processor 110 can obtain the perspective image 40 containing the primary detection region 31 or the additional detection region 32 through the detector 140. The processor 110 can input a portion of the perspective image 40 to a machine learning model to generate or update the detection result corresponding to the primary detection region 31 or the additional detection region 32. The machine learning model is used to detect whether a specific object (e.g., a pedestrian, an obstacle, or a vehicle) is contained in the input image.

[0038] For example, the processor 110 can input the portion of the perspective image 40 marked with the primary detection region 31 to the machine learning model. The machine learning model can determine whether an object has intruded into the primary detection region 31 or a sub-region thereof according to the input information, thereby generating or updating the detection result. For example, the processor 110 can input the portion of the perspective image 40 marked with the additional detection region 32 to the machine learning model. The machine learning model can determine whether an object has intruded into the additional detection region 32 or a sub-region thereof according to the input information, thereby generating or updating the detection result.

[0039] The training data of the machine learning model comprises, for example, one or more perspective images captured by the detector 140, wherein a portion of the perspective images can comprise the specific object and another portion of the perspective images can not comprise the specific object. The processor 110 can train the machine learning model according to the training data based on a supervised machine learning algorithm or an unsupervised machine learning algorithm.

[0040] In step S205, the control module 15 can determine whether the target object intrudes into the main detection area 31 or the additional detection area 32 according to the detection result of the main detection area module 12 or the additional detection area module 13, and control the vehicle according to the determination result. For example, the main detection area 31 can comprise one or more sub-areas. If the processor 110 determines that the target object intrudes into a first sub-area (e.g., a sub-area corresponding to the front of the vehicle) of the main detection area 31 according to the detection result, the control module 15 can control the vehicle to perform emergency braking (e.g., stop the vehicle or lock the accelerator pedal). In addition, the control module 15 can control the vehicle to output warning information or output the warning information (e.g., image, sound or light) through the human-machine interface module 14 and the human-machine interface 150, thereby prompting the driver to pay attention. On the other hand, if the processor 110 determines that the target object intrudes into a second sub-area (e.g., a sub-area corresponding to the oblique front of the vehicle) of the main detection area 31 according to the detection result, the control module 15 can control the vehicle to output warning information or output the warning information through the human-machine interface module 14 and the human-machine interface 150.

[0041] For another example, the additional detection area 32 can comprise one or more sub-areas. If the processor 110 determines that the target object intrudes into a first sub-area (e.g., a sub-area corresponding to the front of the vehicle) of the additional detection area 32 according to the detection result, the control module 15 can control the vehicle to perform pre-braking (i.e., control the vehicle to decelerate). In addition, the control module 15 can control the vehicle to output warning information or output the warning information through the human-machine interface module 14 and the human-machine interface 150, thereby prompting the driver to pay attention. On the other hand, if the processor 110 determines that the target object intrudes into a second sub-area (e.g., a sub-area corresponding to the oblique front of the vehicle) of the additional detection area 32 according to the detection result, the control module 15 can control the vehicle to output warning information or output the warning information through the human-machine interface module 14 and the human-machine interface 150.

[0042] In step S206, the additional detection area module 13 can disable the additional detection area 32. That is, the additional detection area module 13 can stop scanning the additional detection area 32.

[0043] In step S207, the control module 15 can determine whether the target object has intruded into the main detection area 31 based on the detection results of the main detection area module 12, and control the vehicle according to the determination result. For example, the main detection area 31 may contain one or more sub-areas. If the processor 110 determines that the target object has intruded into the first sub-area of ​​the main detection area 31 based on the detection results, the control module 15 can control the vehicle to perform emergency braking. In addition, the control module 15 can control the vehicle to output warning information, or output warning information through the human-machine interface module 14 and the human-machine interface 150. On the other hand, if the processor 110 determines that the target object has intruded into the second sub-area of ​​the main detection area 31 based on the detection results, the control module 15 can control the vehicle to output warning information, or output warning information through the human-machine interface module 14 and the human-machine interface 150.

[0044] Figure 5 A schematic diagram of a vehicle warning method according to an embodiment of the present invention is shown, wherein the vehicle warning method may be composed of, for example, Figure 1 The vehicle warning system 100 shown is implemented. In step S501, a first detection area is scanned by a detector to generate a detection result. In step S502, a rate is obtained from the vehicle's controller area network bus. In step S503, it is determined whether the rate is greater than a threshold. In step S504, in response to the rate being greater than the threshold, a second detection area is scanned by a detector to update the detection result, wherein the second detection area is different from the first detection area. In step S505, the vehicle is controlled based on the detection result.

[0045] In summary, the vehicle warning system of this invention continuously scans the main detection area to detect whether a target is approaching the vehicle. As the vehicle's speed increases, the vehicle warning system can generate an additional detection area and scan this additional detection area. This additional detection area can surround the main detection area. When a target intrudes into the additional detection area, the vehicle warning system can detect the target and take preventative measures such as pre-braking or issuing a warning to avoid a collision. When the vehicle is traveling at low speed, the vehicle warning system can disable the additional detection area to avoid false alarms.

[0046] The above description is only a preferred embodiment of the present invention, but it is not intended to limit the scope of the present invention. Any person skilled in the art can make further improvements and changes on this basis without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the claims of this application.

Claims

1. A vehicle-mounted early warning system, suitable for vehicles, characterized in that, include: A transceiver, communicatively connected to the controller area network bus of the vehicle; The detector scans the first detection area to generate a detection result; as well as A processor, coupled to the transceiver and the detector, wherein the processor is configured to perform: The vehicle's speed is obtained from the controller area network bus; Determine whether the rate is greater than a threshold; In response to the rate being greater than the threshold, the detector scans a second detection region to update the detection result, wherein the second detection region is different from the first detection region; as well as The vehicle is controlled based on the detection results.

2. The vehicle-mounted early warning system according to claim 1, wherein, The processor is configured to further perform: Determine whether the rate is less than or equal to the threshold; and In response to the rate being less than or equal to the threshold, scanning of the second detection area is stopped.

3. The vehicle-mounted early warning system according to claim 1, further comprising: A human-machine interface coupled to the processor, wherein the processor receives user operations through the human-machine interface and configures the second detection area according to the user operations.

4. The vehicle-mounted early warning system according to claim 3, wherein, The detector includes an image capturing device, wherein the processor is configured to further perform: The detector acquires a perspective image; and Perform inverse perspective projection on the perspective image to generate a top view, and output the top view through the human-machine interface.

5. The vehicle-mounted warning system of claim 4, wherein the processor is configured to further perform: In response to outputting the top view, the user operation for the top view is received through the human-machine interface.

6. The vehicle-mounted early warning system of claim 1, wherein the detector includes an image capturing device, and wherein the processor is configured to further perform: The detector acquires a perspective image; and A portion of the perspective image is input into a machine learning model to generate or update the detection results, wherein the portion corresponds to the first detection region or the second detection region.

7. The vehicle-mounted early warning system according to claim 1, wherein the size of the second detection area is positively correlated with the rate.

8. The vehicle-mounted warning system according to claim 1, wherein the first detection area comprises a first sub-region and a second sub-region, wherein the processor is configured to further execute: Based on the detection results, it is determined whether the target object has intruded into the first sub-region or the second sub-region; In response to determining that the target object has intruded into the first sub-region, the vehicle is controlled to perform emergency braking and output a warning message; and In response to determining that the target object has intruded into the second sub-region, the vehicle is controlled to output the warning information.

9. The vehicle-mounted warning system according to claim 1, wherein the second detection area includes a first sub-region and a second sub-region, wherein the processor is configured to further perform: Based on the detection results, it is determined whether the target object has intruded into the first sub-region or the second sub-region; In response to determining that the target object has intruded into the first sub-region, the vehicle is controlled to perform pre-braking and output a warning message; and In response to determining that the target object has intruded into the second sub-region, the vehicle is controlled to output the warning information.

10. The vehicle-mounted early warning system according to claim 1, wherein... The virtual straight line passes through the detector, a first point in the first detection area, and a second point in the second detection area, wherein the first distance between the first point and the detector is less than the second distance between the second point and the detector.

11. A vehicle-mounted early warning method, applicable to vehicles, characterized in that, include: The detector scans the first detection area to generate a detection result; The vehicle's speed is obtained from the vehicle's controller area network bus; Determine whether the rate is greater than a threshold; In response to the rate being greater than the threshold, the detector scans a second detection region to update the detection result, wherein the second detection region is different from the first detection region; as well as The vehicle is controlled based on the detection results.

Images