Vehicle and pedestrian collision early warning method, device and system and storage medium

Abstract

The invention relates to a vehicle and pedestrian collision early warning method, device and system and a storage medium, and the method comprises the steps: transmitting a snapshot image obtained in real time to a vehicle-mounted control unit, carrying out the recognition of a lower limb region of a target pedestrian in the snapshot image, obtaining a first motion direction of the target pedestrian, and obtaining a second motion direction of the target pedestrian; acquiring relative position information of the target pedestrian and the acquisition device; based on the relative position information, the first motion direction and a second motion direction of the vehicle, predicting whether the target pedestrian will collide with the vehicle; and when the prediction result is that the target pedestrian will collide with the vehicle, generating a collision early warning signal. Through the method and the device, the problem that collision early warning is not timely triggered due to the fact that the ghost probe behavior of the pedestrian cannot be effectively identified is solved, the ghost probe behavior of the pedestrian is effectively identified, and collision early warning is timely triggered.

Description

Technical Field

[0001] The present application relates to the field of traffic safety technology, and in particular to a vehicle-pedestrian collision warning method, device, system and storage medium. Background Art

[0002] In the absence of traffic lights and traffic police control, pedestrians or non-motor vehicles often cross the road. Drivers are affected by roadside vehicles or other obstacles blocking their vision and are unable to predict the sudden appearance of pedestrians or non-motor vehicles from the roadside, which often leads to "ghost jumping" accidents and affects traffic safety.

[0003] In order to solve the above problems, the existing technology usually uses fixed detectors installed at intersections to detect whether pedestrians and vehicles may collide, and sends the detection results to the multimedia terminal of the vehicle driver for warning. However, due to the complex situation of vehicles in the vehicle team, when affected by high-height vehicles or other obstructions, the above method cannot effectively identify the ghost-peek behavior of pedestrians, resulting in the delay in triggering collision warnings.

[0004] There is currently no effective solution to the problem that related technologies cannot effectively identify pedestrians' peeking behavior, resulting in the untimely triggering of collision warnings. Summary of the invention

[0005] In this embodiment, a vehicle-pedestrian collision warning method, device, system and storage medium are provided to solve the problem in the related art that the ghost-peeping behavior of pedestrians cannot be effectively identified, resulting in the untimely triggering of the collision warning.

[0006] In the first aspect, a vehicle-pedestrian collision warning method is provided in this embodiment, which is applicable to a vehicle-pedestrian collision warning system; the system includes multiple acquisition devices and a vehicle-mounted control unit; wherein each acquisition device is arranged at the bottom of the vehicle, and is used to obtain captured images of both sides of the vehicle; the method includes:

[0007] The captured image acquired in real time is sent to the vehicle-mounted control unit, and the lower limb area of ​​the target pedestrian in the captured image is identified to obtain the first movement direction of the target pedestrian and the relative position information between the target pedestrian and the acquisition device;

[0008] Based on the relative position information, the first movement direction, and the second movement direction of the vehicle, predicting whether the target pedestrian will collide with the vehicle;

[0009] When the prediction result is that the target pedestrian will collide with the vehicle, a collision warning signal is generated.

[0010] In some embodiments, predicting whether the target pedestrian will collide with the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle includes:

[0011] Determine whether the first movement direction and the second movement direction have an intersection;

[0012] In the case where there is an intersection between the first movement direction and the second movement direction, determining a first time distance between the target pedestrian and the intersection, and a second time distance between the vehicle and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0013] The first time distance and the second time distance are respectively compared with a first preset threshold, and based on the comparison result, it is predicted whether the target pedestrian will collide with the vehicle.

[0014] In some embodiments, determining a first time distance between the target pedestrian and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle includes:

[0015] Determining a first distance between the target pedestrian and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0016] The first time distance between the target pedestrian and the intersection is determined based on the first distance and a preset movement speed of the target pedestrian.

[0017] In some of the embodiments, determining a second time distance between the vehicle and the intersection based on the relative position information, the first motion direction, and the second motion direction of the vehicle includes:

[0018] determining a second distance between the vehicle and the intersection based on the relative position information, the first movement direction, and a second movement direction of the vehicle;

[0019] According to the driving state of the vehicle, the second distance between the vehicle and the intersection is corrected to obtain a corresponding third distance; the driving state of the vehicle includes the vehicle moving forward and the vehicle reversing;

[0020] The second time distance between the vehicle and the intersection is determined based on the third distance and the current moving speed of the vehicle.

[0021] In some embodiments, when the prediction result is that the target pedestrian will collide with the vehicle, generating a collision warning signal includes:

[0022] When the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, it is determined that the prediction result is that the target pedestrian will collide with the vehicle, and the collision warning signal is generated.

[0023] In some embodiments, after comparing the first time distance and the second time distance with a first preset threshold respectively, the method further includes:

[0024] When the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, comparing the first time distance and the second time distance with a second preset threshold respectively; the second preset threshold is less than the first preset threshold;

[0025] When the first time distance is smaller than the second preset threshold, and the second time distance is smaller than the second preset threshold, emergency braking is triggered.

[0026] In some embodiments, the acquisition device is disposed at the connection between the vehicle wheel and the vehicle body; the acquisition device includes a distance sensor and a camera; and before the captured image acquired in real time is sent to the vehicle-mounted control unit, the device further includes:

[0027] In response to the distance between the detection direction of the distance sensor and the wheel hub on the vehicle wheel being greater than a preset distance value, the camera is controlled to capture the captured image.

[0028] In the second aspect, a vehicle-pedestrian collision warning device is provided in this embodiment, which is applicable to a vehicle-pedestrian collision warning system; the system includes a plurality of acquisition devices and a vehicle-mounted control unit; wherein each acquisition device is arranged at the bottom of the vehicle, and is used to obtain snapshot images of both sides of the vehicle; the device includes:

[0029] an identification module, used to send the captured image acquired in real time to the vehicle-mounted control unit, identify the lower limb area of ​​the target pedestrian in the captured image, and obtain the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device;

[0030] A prediction module, configured to predict whether a collision will occur between the target pedestrian and the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0031] The generating module is used to generate a collision warning signal when the prediction result shows that the target pedestrian will collide with the vehicle.

[0032] In a third aspect, a vehicle-pedestrian collision warning system is provided in this embodiment, the system comprising a plurality of collection devices and a vehicle-mounted control unit; wherein each of the collection devices is disposed at the bottom of the vehicle;

[0033] The acquisition device is used to obtain snapshot images of both sides of the vehicle;

[0034] The vehicle-mounted control unit is used to execute the vehicle-pedestrian collision warning method described in the first aspect above.

[0035] In a fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the vehicle-pedestrian collision warning method described in the first aspect is implemented.

[0036] Compared with the related art, the vehicle-pedestrian collision warning method, device, system and storage medium provided in this embodiment, by sending the real-time captured image to the vehicle-mounted control unit, the lower limb area of ​​the target pedestrian in the captured image is identified to obtain the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device; based on the relative position information, the first movement direction and the second movement direction of the vehicle, it is predicted whether the target pedestrian and the vehicle will collide; when the prediction result is that the target pedestrian and the vehicle will collide, a collision warning signal is generated, which solves the problem of not being able to effectively identify the ghost-peek behavior of pedestrians, resulting in untimely triggering of collision warnings, and realizes effective identification of the ghost-peek behavior of pedestrians and timely triggering of collision warnings.

[0037] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 This is a hardware structure block diagram of a terminal device of a vehicle-pedestrian collision warning method provided in an embodiment of the present application;

[0040] Figure 2 is a flow chart of a vehicle-pedestrian collision warning method provided by an embodiment of the present application;

[0041] Figure 3 is a schematic diagram of a vehicle and pedestrian collision warning system provided by an embodiment of the present application;

[0042] Figure 4is a schematic diagram of a time distance calculation method provided by an embodiment of the present application;

[0043] Figure 5 It is a schematic diagram of the installation of a collection device provided in one embodiment of the present application;

[0044] Figure 6 It is a schematic diagram of a capture triggering method of a collection device provided in an embodiment of the present application;

[0045] Figure 7 It is a flow chart of a vehicle-pedestrian collision warning method provided in one embodiment of the present application;

[0046] Figure 8 is a flow chart of a vehicle-pedestrian collision warning method provided by a preferred embodiment of the present application;

[0047] Fig. 9 is a structural block diagram of a vehicle-pedestrian collision warning device provided in one embodiment of the present application;

[0048] Fig.10 It is a structural block diagram of a vehicle and pedestrian collision warning system provided in one embodiment of the present application.

[0049] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 10, identification module; 20, prediction module; 30, generation module; 100, vehicle-mounted control unit; 200, collection device; 300, warning unit; 400, braking system. DETAILED DESCRIPTION

[0050] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0051] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0052] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the vehicle-pedestrian collision warning method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0053] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the vehicle-pedestrian collision warning method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0054] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0055] In this embodiment, a vehicle-pedestrian collision warning method is provided, which is applicable to a vehicle-pedestrian collision warning system. The system includes multiple acquisition devices and a vehicle-mounted control unit. Each acquisition device is arranged at the bottom of the vehicle to obtain captured images of both sides of the vehicle. Figure 2 is a flow chart of the vehicle-pedestrian collision warning method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0056] Step S210, sending the captured image acquired in real time to the vehicle-mounted control unit, identifying the lower limb area of ​​the target pedestrian in the captured image, and obtaining the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device;

[0057] Step S220, predicting whether a target pedestrian will collide with the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0058] Step S230: When the prediction result indicates that the target pedestrian will collide with the vehicle, a collision warning signal is generated.

[0059] Specifically, this embodiment is applied to a vehicle-pedestrian collision warning system, such as Figure 3As shown, the system includes multiple acquisition devices and a vehicle control unit. The vehicle control unit is usually the vehicle's driving computer (Electronic Control Unit, ECU). Multiple ECUs can be deployed at different locations of the vehicle, and each acquisition device is set at the bottom of the vehicle. The acquisition device is connected to the data bus of the vehicle control unit through a vehicle data cable to obtain snapshot images on both sides of the vehicle. The real-time captured snapshot image is sent to the vehicle control unit, and the lower limb area of ​​the target pedestrian in the snapshot image is identified to identify the target pedestrian's legs and feet as the first movement direction of the target pedestrian, and the visual distance between the target pedestrian's legs and feet and the acquisition device is estimated to determine the relative position information of the target pedestrian and the acquisition device.

[0060] The recognition process of the above-mentioned captured image can adopt multi-stage recognition, pre-identify the lower limb area of ​​the target pedestrian in the captured image, and then identify the leg and foot direction of the target pedestrian in the lower limb area, and the visual distance between the leg and foot of the target pedestrian and the acquisition device; or, adopt a single stage recognition to directly identify and obtain the lower limb area of ​​the target pedestrian, the leg and foot direction of the target pedestrian, and the visual distance between the leg and foot of the target pedestrian and the acquisition device. In this embodiment, the recognition of the lower limb area and the leg and foot direction can adopt a region-based target detection algorithm, a full-image-based target detection algorithm, etc., and the visual distance estimation can adopt a depth camera depth of field estimation, a multi-view distance calculation scheme, etc.

[0061] Furthermore, according to the angle between the shooting direction of the acquisition device and the preset direction of the vehicle body, the second movement direction of the current vehicle is determined, and it is determined whether there is an intersection between the first movement direction and the second movement direction. In the case that there is an intersection between the first movement direction and the second movement direction, the first time distance between the target pedestrian and the intersection, and the second time distance between the vehicle and the intersection are calculated based on the relative position information, the first movement direction, and the second movement direction of the vehicle, and the first time distance and the second time distance are respectively compared with the first preset threshold. When it is detected that the first time distance is less than the first preset threshold, and the second time distance is less than the first preset threshold, the prediction result is output that the target pedestrian and the vehicle will collide, and a collision warning signal is generated, for example, a corresponding sound and light alarm is issued in the vehicle, a warning information is displayed on the screen in the vehicle, and vibration feedback of the seat or steering wheel is generated, so that the driver can receive the collision warning signal in time and respond.

[0062] Among them, according to the relative position information of the target pedestrian and the collection device, the first movement direction and the second movement direction, the first distance between the target pedestrian and the intersection is calculated, and according to the first distance and the preset movement speed of the target pedestrian, the first time distance between the target pedestrian and the intersection is calculated. At the same time, according to the relative position information of the target pedestrian and the collection device, the first movement direction and the second movement direction, the second distance between the vehicle and the intersection is calculated, and according to the driving state of the vehicle, that is, the vehicle is moving forward or the vehicle is reversing, the second distance between the vehicle and the intersection is corrected to obtain the corresponding third distance, and then according to the third distance and the current movement speed of the vehicle, the second time distance between the vehicle and the intersection is calculated.

[0063] It should be noted that in addition to predicting whether a collision will occur based on the intersection of the motion directions, the relative position vector of the target pedestrian and the vehicle can be determined in advance based on the relative position of the target pedestrian and the collection device, and the relative speed between the preset motion speed of the target pedestrian and the current motion speed of the vehicle can be calculated to determine whether the direction of the relative speed points to the relative position vector. If the direction of the relative speed points to the relative position vector, it indicates that the target pedestrian and the vehicle will collide.

[0064] In the prior art, fixed detectors at intersections are usually used to detect whether pedestrians and vehicles may collide, and the detection results are sent to the multimedia terminal of the vehicle driver for warning. However, due to the complex situation of vehicles in the vehicle team, when affected by high-height vehicles or other obstructions, the above method cannot effectively identify the ghost-peek behavior of pedestrians, resulting in the delay in triggering collision warnings.

[0065] Compared with the prior art, the present application sends the captured image acquired in real time to the vehicle control unit, identifies the lower limb area of ​​the target pedestrian in the captured image, obtains the first movement direction of the target pedestrian, and the relative position information between the target pedestrian and the acquisition device; based on the relative position information, the first movement direction and the second movement direction of the vehicle, predicts whether the target pedestrian and the vehicle will collide; when the prediction result is that the target pedestrian and the vehicle will collide, a collision warning signal is generated. Based on this, by capturing the captured image from the bottom perspective of the vehicle, identifying the lower limb area of ​​the target pedestrian in the captured image, and predicting whether the pedestrian and the vehicle will collide based on the identified information, the ghost-peek behavior of the pedestrian is detected from the bottom perspective of the vehicle, avoiding the influence of obstructions such as tall vehicle bodies, solving the problem of not being able to effectively identify the ghost-peek behavior of the pedestrian, resulting in the untimely triggering of the collision warning, and achieving effective identification of the ghost-peek behavior of the pedestrian and timely triggering of the collision warning.

[0066] In some embodiments, predicting whether a target pedestrian will collide with the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle in step S220 includes the following steps:

[0067] Step S221, determining whether there is an intersection between the first movement direction and the second movement direction;

[0068] Step S222, when there is an intersection between the first movement direction and the second movement direction, determining a first time distance between the target pedestrian and the intersection, and a second time distance between the vehicle and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0069] Step S223, comparing the first time distance and the second time distance with the first preset threshold value respectively, and predicting whether the target pedestrian and the vehicle will collide based on the comparison result.

[0070] Specifically, determine whether there is an intersection between the first movement direction and the second movement direction. If there is no intersection between the first movement direction and the second movement direction, it indicates that the target pedestrian and the vehicle will not collide. If there is an intersection between the first movement direction and the second movement direction, it is predicted whether the two will collide based on the movement information of the pedestrian and the vehicle.

[0071] In the case where there is an intersection between the first movement direction and the second movement direction, the first time distance between the target pedestrian and the intersection, and the second time distance between the vehicle and the intersection are calculated based on the relative position information, the first movement direction, and the second movement direction of the vehicle, and the first time distance and the second time distance are respectively compared with the first preset threshold. When it is detected that the first time distance is less than the first preset threshold, and the second time distance is less than the first preset threshold, the output prediction result is that the target pedestrian and the vehicle will collide, thereby effectively identifying the ghost head behavior of the pedestrian. If other comparison results are output, it indicates that the target pedestrian and the vehicle will not collide.

[0072] Among them, according to the relative position information of the target pedestrian and the collection device, the first movement direction and the second movement direction, the first distance between the target pedestrian and the intersection is calculated, and according to the first distance and the preset movement speed of the target pedestrian, the first time distance between the target pedestrian and the intersection is calculated. At the same time, according to the relative position information of the target pedestrian and the collection device, the first movement direction and the second movement direction, the second distance between the vehicle and the intersection is calculated, and according to the driving state of the vehicle, that is, the vehicle is moving forward or the vehicle is reversing, the second distance between the vehicle and the intersection is corrected to obtain the corresponding third distance, and then according to the third distance and the current movement speed of the vehicle, the second time distance between the vehicle and the intersection is calculated.

[0073] Through this embodiment, it is determined whether there is an intersection between the first movement direction and the second movement direction. When there is an intersection between the first movement direction and the second movement direction, a first time distance between the target pedestrian and the intersection, and a second time distance between the vehicle and the intersection are determined based on the relative position information, the first movement direction and the second movement direction of the vehicle, and the first time distance and the second time distance are respectively compared with a first preset threshold value. According to the comparison result, it is predicted whether a collision will occur between the target pedestrian and the vehicle, so as to accurately calculate the time distance between the pedestrian and the vehicle to reach the intersection, improve the accuracy of predicting collision events, and help to achieve timely collision warning.

[0074] The following is an explanation of the calculation method of the first time distance and the second time distance. Figure 4 .

[0075] In some embodiments, determining the first time distance between the target pedestrian and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle in step S222 includes the following steps:

[0076] Determining a first distance between the target pedestrian and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0077] Based on the first distance and a preset moving speed of the target pedestrian, a first time distance between the target pedestrian and the intersection is determined.

[0078] Specifically, the preset movement speed of the target pedestrian is obtained. The preset movement speed is usually a faster walking speed of the pedestrian under normal walking conditions, such as 5 meters per second, so that the first time distance obtained by subsequent calculation is relatively small, ensuring safety warning.

[0079] Further, according to the relative position information and the first movement direction of the target pedestrian, a first angle formed by the line between the target pedestrian and the collection device and the first movement direction is determined, according to the relative position information and the second movement direction of the vehicle, a second angle formed by the line between the target pedestrian and the collection device and the second movement direction is determined, and the visual distance between the target pedestrian and the collection device is obtained from the relative position information, and according to the first angle, the second angle and the visual distance, the first distance between the target pedestrian and the intersection is calculated. The specific calculation formula is as follows:

[0080]

[0081] In formula (1), L1 represents the first distance between the target pedestrian and the intersection; L represents the visual distance between the target pedestrian and the collection device; A represents the second angle formed by the line between the target pedestrian and the collection device and the second direction of motion; B represents the first angle formed by the line between the target pedestrian and the collection device and the first direction of motion. Then, the first time distance between the target pedestrian and the intersection is calculated based on the first distance and the preset movement speed of the target pedestrian.

[0082] Through this embodiment, the first distance between the target pedestrian and the intersection is determined based on the relative position information, the first movement direction and the second movement direction of the vehicle, and the first time distance between the target pedestrian and the intersection is determined based on the first distance and the preset movement speed of the target pedestrian. The time distance for the target pedestrian to arrive at the intersection is accurately calculated, which helps to improve the accuracy of collision prediction.

[0083] In some embodiments, determining the second time distance between the vehicle and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle in step S222 includes the following steps:

[0084] determining a second distance between the vehicle and the intersection based on the relative position information, the first direction of motion, and a second direction of motion of the vehicle;

[0085] According to the driving state of the vehicle, the second distance between the vehicle and the intersection is corrected to obtain a corresponding third distance; the driving state of the vehicle includes the vehicle moving forward and the vehicle reversing;

[0086] Based on the third distance and the current moving speed of the vehicle, a second time distance between the vehicle and the intersection is determined.

[0087] In this embodiment, the current moving speed of the vehicle is obtained in advance. It can be understood that the vehicle control unit records the moving speed of the vehicle in real time during driving, and the vehicle speed is usually obtained by using a vehicle speed sensor, an inertial measurement unit, etc.

[0088] Further, according to the relative position information and the first movement direction of the target pedestrian, a first angle formed by the line between the target pedestrian and the collection device and the first movement direction is determined, according to the relative position information and the second movement direction of the vehicle, a second angle formed by the line between the target pedestrian and the collection device and the second movement direction is determined, and the visual distance between the target pedestrian and the collection device is obtained from the relative position information, and the second distance between the vehicle and the intersection is calculated according to the first angle, the second angle and the visual distance. The specific calculation formula is as follows:

[0089]

[0090] In formula (2), L2 represents the second distance between the vehicle and the intersection; L represents the visual distance between the target pedestrian and the collection device; A represents the second angle formed by the line between the target pedestrian and the collection device and the second direction of motion; B represents the first angle formed by the line between the target pedestrian and the collection device and the first direction of motion. Then, the first time distance between the target pedestrian and the intersection is calculated based on the first distance and the preset movement speed of the target pedestrian.

[0091] Afterwards, since a collision between a vehicle and a pedestrian usually refers to a collision between the front of the vehicle (i.e., the front end of the vehicle) or the rear of the vehicle (i.e., the rear end of the vehicle) and the pedestrian, and the collection device can be installed at different positions on the bottom of the vehicle, and different collection devices are at a certain distance from the front and rear of the vehicle, this embodiment corrects the second distance between the vehicle and the intersection according to the driving state of the vehicle, obtains the corresponding third distance, and calculates the second time distance between the vehicle and the intersection based on the third distance and the current movement speed of the vehicle.

[0092] Among them, when the vehicle is moving forward, the second distance between the vehicle and the intersection is corrected to a third distance L2`=L2-L3, where L3 represents the distance between the front of the vehicle and the collection device in the horizontal forward direction of the vehicle; when the vehicle is moving backward, the second distance between the vehicle and the intersection is corrected to a third distance L2`=L2-L4, where L4 represents the distance between the rear of the vehicle and the collection device in the horizontal reverse direction of the vehicle.

[0093] Through this embodiment, the second distance between the vehicle and the intersection is determined based on the relative position information, the first movement direction and the second movement direction of the vehicle. According to the driving state of the vehicle, the second distance between the vehicle and the intersection is corrected to obtain the corresponding third distance. Based on the third distance and the current movement speed of the vehicle, the second time distance between the vehicle and the intersection is determined, thereby accurately calculating the time distance for the vehicle to reach the intersection, which helps to improve the accuracy of collision prediction.

[0094] In some embodiments, when the prediction result is that the target pedestrian and the vehicle will collide, generating a collision warning signal in step S230 includes the following steps:

[0095] When the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, it is determined that the prediction result is that the target pedestrian and the vehicle will collide, and a collision warning signal is generated.

[0096] Specifically, the first time distance and the second time distance are compared with the first preset threshold value respectively. When it is detected that the first time distance is less than the first preset threshold value, and the second time distance is less than the first preset threshold value, the output prediction result is that the target pedestrian and the vehicle will collide. If other comparison results are output, it indicates that the target pedestrian and the vehicle will not collide. It should be noted that the first preset threshold value can be set by comprehensively considering factors such as the braking reaction time and braking time of general drivers to ensure the effectiveness of the collision warning signal.

[0097] Exemplarily, when the first preset threshold is 3 seconds, the actually detected first time distance is 2.5 seconds, and the second time distance is 2.8 seconds. At this time, both the first time distance and the second time distance are less than the first preset threshold, indicating that the target pedestrian will collide with the vehicle, triggering a collision warning signal.

[0098] Through this embodiment, when the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, it is determined that the prediction result is that the target pedestrian and the vehicle will collide, and a collision warning signal is generated to trigger the collision warning in time.

[0099] In some of the embodiments, after comparing the first time distance and the second time distance with the first preset threshold respectively, the vehicle-pedestrian collision warning method further includes the following steps:

[0100] When the first time distance is less than the first preset threshold, and the second time distance is less than the first preset threshold, the first time distance and the second time distance are respectively compared with the second preset threshold; the second preset threshold is less than the first preset threshold;

[0101] When the first time distance is less than the second preset threshold and the second time distance is less than the second preset threshold, emergency braking is triggered.

[0102] Specifically, when both the first time distance and the second time distance are less than the first preset threshold, the first time distance and the second time distance are respectively compared with the second preset threshold, and the second preset threshold is less than the first preset threshold. If it is detected that the first time distance is less than the second preset threshold, and the second time distance is less than the second preset threshold, an emergency braking signal is generated and transmitted to the braking system of the vehicle to instruct the braking system to perform automatic emergency braking.

[0103] For example, when the second preset threshold is 1 second, the actually detected first time distance is 0.6 seconds and the second time distance is 0.8 seconds. At this time, both the first time distance and the second time distance are less than the second preset threshold, indicating that even if a collision warning signal is issued, the driver cannot avoid the pedestrian's peeking behavior and needs to trigger an emergency braking signal.

[0104] Through this embodiment, when the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, the first time distance and the second time distance are compared with the second preset threshold respectively, wherein the second preset threshold is less than the first preset threshold, and when the first time distance is less than the second preset threshold and the second time distance is less than the second preset threshold, emergency braking is triggered, thereby improving driving safety through automatic emergency braking when the time distance between pedestrians and vehicles reaching the collision intersection is too short.

[0105] In some of the embodiments, the acquisition device is disposed at the connection between the vehicle wheel and the vehicle body; the acquisition device includes a distance sensor and a camera; and before the real-time captured image is sent to the vehicle control unit, the following steps are also included:

[0106] In response to the distance between the detection direction of the distance sensor and the wheel hub on the vehicle wheel being greater than a preset distance value, the camera is controlled to capture a captured image.

[0107] In this embodiment, the acquisition device is installed at the connection between the vehicle wheel and the body, close to the wheel hub position, such as the lower control arm, the lower swing arm, etc., to ensure that the acquisition device is not unable to effectively capture due to the relative position offset of the wheel and the components, and to prevent the camera from being damaged by dragging on the ground due to the up and down floating of the suspension when it is directly installed on the chassis; secondly, the installation height of the acquisition device is below the height of the wheel drive shaft, so that the acquisition device is located at the bottom of the vehicle, and can fully capture the bottom space of the vehicle, and the camera in the acquisition device is illuminated in the direction of the outer side of the wheel, which is used to collect captured images on both sides of the vehicle.

[0108] For example, Figure 5 As shown, the components near the vehicle wheels include shock absorbers, coil springs, anti-roll bar connecting rods, subframes and lower control arms. The acquisition device is installed on the lower control arm between the subframe and the wheel to ensure that high-quality snapshot images are captured from the perspective of the bottom of the vehicle.

[0109] Specifically, according to the above setting method, a collection device is installed near one or more wheels, and each collection device includes a distance sensor and a camera. The distance sensor includes a laser distance sensor, an infrared distance sensor, etc. Since the collection device is close to the wheel hub, the collection device will be blocked by the wheel hub during part of the driving process. The distance sensor senses the distance to the wheel hub. When the sensed distance is less than the preset distance value, a shutdown signal is triggered to control the camera to shut down. When the sensed distance is greater than the preset distance value, a start signal is triggered to control the camera to capture the captured image. Figure 6 As shown, the wheel hub rotates during driving. When the relative position of the wheel hub and the distance sensor is at point A, a closing signal is triggered; when the relative position of the wheel hub and the distance sensor is at point B, an opening signal is triggered.

[0110] It should be noted that this embodiment does not limit the specific installation position of the collection device. The collection device can be set at a suitable position at the bottom of the vehicle according to different vehicle condition information, such as the ground clearance of the vehicle, and the captured image can be collected from the perspective of the bottom of the vehicle.

[0111] Through this embodiment, when the acquisition device is set at the connection between the vehicle wheel and the vehicle body, in response to the distance between the detection direction of the distance sensor and the wheel hub on the vehicle wheel being greater than a preset distance value, the camera is controlled to acquire the captured image, thereby avoiding the camera from acquiring the captured image when it is blocked, improving the quality of the captured image, and at the same time improving the installation stability of the acquisition device.

[0112] The present embodiment is described and illustrated by means of specific examples below.

[0113] Figure 7 is a flow chart of the vehicle-pedestrian collision warning method of the preferred embodiment, such as Figure 7 As shown, the vehicle-pedestrian collision warning method specifically includes the following steps:

[0114] During driving, the acquisition device is triggered to take snapshots S710, and the captured images are transmitted to the vehicle control unit, and the lower limb area of ​​the target pedestrian in the captured images is identified to obtain the target pedestrian's leg and foot movement direction, and the relative position information of the target pedestrian and the acquisition device S720. It is determined whether there is an intersection between the target pedestrian's leg and foot movement direction and the vehicle's movement direction S730. If there is no intersection, the detection process based on the current captured image is terminated. If there is an intersection, the first time distance of the target pedestrian arriving at the intersection and the second time distance of the vehicle arriving at the intersection are calculated, and it is determined whether the first time distance and the second time distance are both within the m-second distance S740.

[0115] When the first time distance and the second time distance are both within the m-second distance, a collision warning signal is triggered S750; otherwise, the detection process based on the current captured image is terminated. In the case of triggering a collision warning signal, it is further determined that the first time distance and the second time distance are both within the n-second distance (n is less than m) seconds S760. If the first time distance and the second time distance are both within the n-second distance, an emergency braking signal is triggered, and the braking system implements automatic emergency braking S770; otherwise, the detection process based on the current captured image is terminated.

[0116] The present embodiment is described and illustrated below through preferred embodiments.

[0117] Figure 8 is a flow chart of the vehicle-pedestrian collision warning method of the preferred embodiment, such as Figure 8 As shown, the vehicle-pedestrian collision warning method includes the following steps:

[0118] Step S810, sending the captured image acquired in real time to the vehicle-mounted control unit, identifying the lower limb area of ​​the target pedestrian in the captured image, and obtaining the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device;

[0119] Step S820, when there is an intersection between the first moving direction and the second moving direction of the vehicle, determining a first time distance between the target pedestrian and the intersection, and a second time distance between the vehicle and the intersection based on the relative position information, the first moving direction, and the second moving direction;

[0120] Step S830, comparing the first time distance and the second time distance with a first preset threshold value respectively, and predicting whether a collision will occur between the target pedestrian and the vehicle according to the comparison result;

[0121] Step S840, when the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, determining that the prediction result is that the target pedestrian and the vehicle will collide, and generating a collision warning signal;

[0122] Step S850, comparing the first time distance and the second time distance with the second preset threshold respectively, the second preset threshold is less than the first preset threshold, and when the first time distance is less than the second preset threshold and the second time distance is less than the second preset threshold, emergency braking is triggered.

[0123] Through this embodiment, the captured image acquired in real time is sent to the vehicle control unit, the lower limb area of ​​the target pedestrian in the captured image is identified, and the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device are obtained. In the case where there is an intersection between the first movement direction and the second movement direction of the vehicle, the first time distance between the target pedestrian and the intersection and the second time distance between the vehicle and the intersection are determined based on the relative position information, the first movement direction and the second movement direction, and the first time distance and the second time distance are respectively compared with the first preset threshold value, and according to the comparison result, it is predicted whether the target pedestrian and the vehicle will collide. Among them, when the first time distance is less than the first preset threshold value, and the second time distance is less than the first preset threshold value, it is determined that the prediction result is that the target pedestrian and the vehicle will collide, and a collision warning signal is generated, which solves the problem that the ghost head behavior of the pedestrian cannot be effectively identified, resulting in the untimely triggering of the collision warning, and realizes the effective identification of the ghost head behavior of the pedestrian and the timely triggering of the collision warning.

[0124] Furthermore, the first time distance and the second time distance are respectively compared with a second preset threshold value, and the second preset threshold value is less than the first preset threshold value. When the first time distance is less than the second preset threshold value and the second time distance is less than the second preset threshold value, emergency braking is triggered, thereby improving driving safety through automatic emergency braking when the time distance between the pedestrian and the vehicle reaching the collision intersection is too short.

[0125] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0126] In this embodiment, a vehicle-pedestrian collision warning device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0127] Fig. 9 : is a structural block diagram of the vehicle and pedestrian collision warning device of this embodiment, such as Fig. 9 As shown, the device comprises:

[0128] The recognition module 10 is used to send the captured image acquired in real time to the vehicle-mounted control unit, recognize the lower limb area of ​​the target pedestrian in the captured image, and obtain the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device;

[0129] A prediction module 20, for predicting whether a target pedestrian will collide with the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0130] The generating module 30 is used to generate a collision warning signal when the prediction result shows that the target pedestrian will collide with the vehicle.

[0131] Through the device provided in this embodiment, the captured image acquired in real time is sent to the vehicle-mounted control unit, the lower limb area of ​​the target pedestrian in the captured image is identified, and the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device are obtained; based on the relative position information, the first movement direction and the second movement direction of the vehicle, it is predicted whether the target pedestrian and the vehicle will collide; when the prediction result is that the target pedestrian and the vehicle will collide, a collision warning signal is generated, which solves the problem of inability to effectively identify the ghost-peek behavior of pedestrians, resulting in untimely triggering of collision warnings, and realizes effective identification of the ghost-peek behavior of pedestrians and timely triggering of collision warnings.

[0132] In some of the embodiments, the prediction module 20 is also used to determine whether there is an intersection between the first movement direction and the second movement direction; when there is an intersection between the first movement direction and the second movement direction, determine the first time distance between the target pedestrian and the intersection, and the second time distance between the vehicle and the intersection based on the relative position information, the first movement direction and the second movement direction of the vehicle; compare the first time distance and the second time distance with the first preset threshold value respectively, and predict whether the target pedestrian and the vehicle will collide based on the comparison result.

[0133] In some of the embodiments, the prediction module 20 is also used to determine a first distance between the target pedestrian and the intersection based on the relative position information, the first movement direction and the second movement direction of the vehicle; and to determine a first time distance between the target pedestrian and the intersection based on the first distance and a preset movement speed of the target pedestrian.

[0134] In some of the embodiments, the prediction module 20 is further used to determine a second distance between the vehicle and the intersection based on the relative position information, the first movement direction and the second movement direction of the vehicle; correct the second distance between the vehicle and the intersection according to the driving state of the vehicle to obtain a corresponding third distance; the driving state of the vehicle includes the vehicle moving forward and the vehicle reversing; and determine the second time distance between the vehicle and the intersection based on the third distance and the current movement speed of the vehicle.

[0135] In some of the embodiments, the generation module 30 is further used to determine that the prediction result is that the target pedestrian and the vehicle will collide when the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, and generate a collision warning signal.

[0136] In some of the embodiments, the prediction module 20 is also used to compare the first time distance and the second time distance with the second preset threshold respectively when the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold; the second preset threshold is less than the first preset threshold; and trigger emergency braking when the first time distance is less than the second preset threshold and the second time distance is less than the second preset threshold.

[0137] In some of these embodiments, Fig. 9 On the basis of, the device also includes a collection module, which is used to control the camera to collect the captured image in response to the distance between the detection direction of the distance sensor and the wheel hub on the vehicle wheel being greater than a preset distance value.

[0138] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0139] In this embodiment, a vehicle-pedestrian collision warning system is also provided. Fig.10 is a structural block diagram of the vehicle and pedestrian collision warning system of this embodiment, such as Fig.10 As shown, the system includes a plurality of collection devices 200 and a vehicle-mounted control unit 100; wherein each collection device 200 is disposed at the bottom of the vehicle;

[0140] The acquisition device 200 is used to obtain snapshot images of both sides of the vehicle;

[0141] The vehicle-mounted control unit 100 is used to execute the steps in any of the above method embodiments.

[0142] Specifically, the vehicle control unit 100 is the vehicle's driving computer, the acquisition device 200 is connected to the data bus of the vehicle control unit 100 via a vehicle data cable, and each acquisition device 200 is arranged at the bottom of the vehicle to obtain snapshot images of both sides of the vehicle. The collision warning system in this embodiment also includes a warning unit 300, which is used to issue a collision warning between the vehicle and the pedestrian.

[0143] It should be noted that the collection device 200 can be installed at the connection between the vehicle wheel and the body, close to the wheel hub, to prevent the camera from being damaged by dragging on the ground due to the up and down floating of the suspension when it is directly installed on the chassis, such as the lower control arm, lower swing arm, etc., to ensure that the collection device 200 will not be unable to effectively capture due to the relative position offset of the wheel and the components; secondly, the installation height of the collection device 200 is below the height of the wheel drive shaft, so that the collection device 200 is located at the bottom of the vehicle, and can fully capture the bottom space of the vehicle, and the camera in the collection device 200 is illuminated in the direction of the outer side of the wheel, which is used to collect snapshot images on both sides of the vehicle.

[0144] The captured image acquired in real time is sent to the vehicle control unit, the lower limb area of ​​the target pedestrian in the captured image is identified, the first movement direction of the target pedestrian and the relative position information between the target pedestrian and the acquisition device 200 are obtained, and the first time distance between the target pedestrian and the intersection and the second time distance between the vehicle and the intersection are determined based on the relative position information, the first movement direction and the second movement direction of the vehicle. The first time distance and the second time distance are respectively compared with the first preset threshold value, and according to the comparison result, it is predicted whether the target pedestrian and the vehicle will collide, and when the prediction result is that the target pedestrian and the vehicle will collide, a collision warning signal is generated to control the warning unit 300 to issue a collision warning between the vehicle and the pedestrian, prompting the driver that there is a current collision risk.

[0145] When the collision warning signal is triggered, it is further determined that the first time distance and the second time distance are both less than the second preset threshold. If the first time distance and the second time distance are both less than the second preset threshold, an emergency braking signal is generated and transmitted to the braking system 400, and automatic emergency braking is implemented by the braking system 400.

[0146] Through this embodiment, captured images are collected from the perspective of the bottom of the vehicle, the lower limb area of ​​the target pedestrian in the captured image is identified, and the identified information is used to predict whether a collision will occur between the pedestrian and the vehicle. The peeking behavior of pedestrians is detected from the perspective of the bottom of the vehicle to avoid being affected by obstructions such as tall vehicle bodies. This solves the problem of being unable to effectively identify the peeking behavior of pedestrians, resulting in untimely triggering of collision warnings, and achieves effective identification of the peeking behavior of pedestrians and timely triggering of collision warnings.

[0147] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0148] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0149] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0150] S1, sending the captured image acquired in real time to the vehicle control unit, identifying the lower limb area of ​​the target pedestrian in the captured image, and obtaining the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device;

[0151] S2, predicting whether a target pedestrian will collide with the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle;

[0152] S3: When the prediction result shows that the target pedestrian will collide with the vehicle, a collision warning signal is generated.

[0153] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0154] In addition, in combination with the vehicle-pedestrian collision warning method provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by the processor, any vehicle-pedestrian collision warning method in the above embodiments is implemented.

[0155] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0156] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0157] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0158] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A vehicle-pedestrian collision warning method, characterized in that: Applicable to a vehicle-pedestrian collision warning system; the system includes multiple acquisition devices and a vehicle-mounted control unit; wherein each acquisition device is arranged at the bottom of the vehicle, and is used to obtain snapshot images of both sides of the vehicle; the method includes: The captured image acquired in real time is sent to the vehicle-mounted control unit, and the lower limb area of ​​the target pedestrian in the captured image is identified to obtain the first movement direction of the target pedestrian and the relative position information between the target pedestrian and the acquisition device; Based on the relative position information, the first movement direction, and the second movement direction of the vehicle, predicting whether the target pedestrian will collide with the vehicle; When the prediction result is that the target pedestrian will collide with the vehicle, a collision warning signal is generated.

2. The vehicle-pedestrian collision warning method according to claim 1, characterized in that: The predicting whether the target pedestrian will collide with the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle includes: Determine whether the first movement direction and the second movement direction have an intersection; In the case where there is an intersection between the first movement direction and the second movement direction, determining a first time distance between the target pedestrian and the intersection, and a second time distance between the vehicle and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle; The first time distance and the second time distance are respectively compared with a first preset threshold, and based on the comparison result, it is predicted whether the target pedestrian will collide with the vehicle.

3. The vehicle-pedestrian collision warning method according to claim 2, characterized in that: The determining, based on the relative position information, the first movement direction, and the second movement direction of the vehicle, a first time distance between the target pedestrian and the intersection includes: Determining a first distance between the target pedestrian and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle; The first time distance between the target pedestrian and the intersection is determined based on the first distance and a preset movement speed of the target pedestrian.

4. The vehicle-pedestrian collision warning method according to claim 2, characterized in that: Determining a second time distance between the vehicle and the intersection based on the relative position information, the first movement direction, and the second movement direction of the vehicle includes: determining a second distance between the vehicle and the intersection based on the relative position information, the first movement direction, and a second movement direction of the vehicle; According to the driving state of the vehicle, the second distance between the vehicle and the intersection is corrected to obtain a corresponding third distance; the driving state of the vehicle includes the vehicle moving forward and the vehicle reversing; The second time distance between the vehicle and the intersection is determined based on the third distance and the current moving speed of the vehicle.

5. The vehicle-pedestrian collision warning method according to claim 2, characterized in that: When the prediction result indicates that the target pedestrian will collide with the vehicle, generating a collision warning signal includes: When the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, it is determined that the prediction result is that the target pedestrian will collide with the vehicle, and the collision warning signal is generated.

6. The vehicle-pedestrian collision warning method according to claim 2, characterized in that: After comparing the first time distance and the second time distance with a first preset threshold respectively, the method further includes: When the first time distance is less than the first preset threshold and the second time distance is less than the first preset threshold, comparing the first time distance and the second time distance with a second preset threshold respectively; the second preset threshold is less than the first preset threshold; When the first time distance is smaller than the second preset threshold, and the second time distance is smaller than the second preset threshold, emergency braking is triggered.

7. The vehicle-pedestrian collision warning method according to claim 1, characterized in that: The acquisition device is arranged at the connection between the vehicle wheel and the vehicle body; the acquisition device comprises a distance sensor and a camera; Before sending the captured image acquired in real time to the vehicle-mounted control unit, the method further includes: In response to the distance between the detection direction of the distance sensor and the wheel hub on the vehicle wheel being greater than a preset distance value, the camera is controlled to capture the captured image.

8. A vehicle-pedestrian collision warning device, characterized in that: Applicable to a vehicle-pedestrian collision warning system; the system includes multiple acquisition devices and a vehicle-mounted control unit; wherein each acquisition device is arranged at the bottom of the vehicle, and is used to obtain snapshot images of both sides of the vehicle; the device includes: an identification module, used to send the captured image acquired in real time to the vehicle-mounted control unit, identify the lower limb area of ​​the target pedestrian in the captured image, and obtain the first movement direction of the target pedestrian and the relative position information of the target pedestrian and the acquisition device; A prediction module, configured to predict whether a collision will occur between the target pedestrian and the vehicle based on the relative position information, the first movement direction, and the second movement direction of the vehicle; The generating module is used to generate a collision warning signal when the prediction result shows that the target pedestrian will collide with the vehicle.

9. A vehicle-pedestrian collision warning system, characterized in that: The system includes a plurality of collection devices and a vehicle-mounted control unit; wherein each of the collection devices is arranged at the bottom of the vehicle; The acquisition device is used to obtain snapshot images of both sides of the vehicle; The vehicle-mounted control unit is used to execute the vehicle-pedestrian collision warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle-pedestrian collision warning method described in any one of claims 1 to 7 are implemented.

Images