Pedestrian collision avoidance method, device, equipment and storage medium

Abstract

The present invention discloses a pedestrian collision avoidance method, device, equipment and storage medium, belonging to the field of vehicle control and traffic safety technology. The method includes: obtaining pedestrian information and road direction sent by roadside equipment; determining whether there is a target pedestrian in the target area according to vehicle information, the pedestrian information and the road direction; if there is, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first duration, then determining the expected acceleration of the vehicle; when the distance between the vehicle and the target pedestrian reaches a safe distance, controlling the vehicle to decelerate according to the expected acceleration of the vehicle to avoid colliding with the pedestrian. Through the above technical solution, in sections where pedestrian collision accidents are frequent or complex driving sections with more obstructions, and when the vehicle has a blind spot, active braking can be performed to decelerate, thereby reducing the incidence of pedestrian collision accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control and traffic safety, and in particular to a pedestrian collision avoidance method, device, equipment and storage medium. Background Art

[0002] As a vulnerable group in road traffic, people have become victims of a large number of traffic accidents. Although intelligent driving technology can now assist drivers in effectively avoiding collisions with pedestrians, such as the widely used automatic emergency braking system (AEB), forward collision warning system (FCW) and other advanced driving assistance systems, the existing related products have limited perception capabilities due to the use of sensors such as millimeter-wave radars and cameras on the vehicle, which are mainly reflected in the narrow range and low accuracy. They can only deal with simple pedestrian collision danger scenarios, such as pedestrians walking and walking forward without interference around. In fact, the road environment is complex and changeable, and people, vehicles and objects are mixed. Existing pedestrian collision avoidance products cannot cope with most dangerous scenarios, such as the most common "ghost head" scenario, that is, the scene where the pedestrian is blocked or blind in the vehicle's field of view. The pedestrian suddenly appears from the vehicle's blind spot, resulting in the system's failure to identify the pedestrian in time, triggering a warning or emergency braking delay, and ultimately leading to a pedestrian collision accident. Summary of the invention

[0003] The present invention provides a pedestrian collision avoidance method, device, equipment and storage medium to reduce the incidence of pedestrian collisions.

[0004] According to a first aspect of the present invention, a pedestrian collision avoidance method is provided, which is applied to a vehicle-mounted device, and the method comprises:

[0005] Obtain pedestrian information and road direction sent by roadside equipment;

[0006] Determining whether there is a target pedestrian in the target area according to the vehicle information, the pedestrian information and the road direction;

[0007] If so, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first duration, determining the expected acceleration of the vehicle;

[0008] When the distance between the vehicle and the target pedestrian reaches a safe distance, the vehicle is controlled to decelerate according to the desired acceleration of the vehicle to avoid collision with the pedestrian.

[0009] According to a second aspect of the present invention, a pedestrian collision avoidance method is provided, which is applied to roadside equipment, and the method comprises:

[0010] Obtain pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle;

[0011] Determining whether a pedestrian in the target area is blocked by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information;

[0012] If yes, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with the pedestrian.

[0013] According to a third aspect of the present invention, a pedestrian collision avoidance system is provided, the system comprising a vehicle-mounted device and a roadside device; wherein:

[0014] The vehicle-mounted device is used to execute the pedestrian collision avoidance method as described in the first aspect;

[0015] The roadside equipment is used to execute the pedestrian collision avoidance method as described in the second aspect.

[0016] According to a fourth aspect of the present invention, there is provided a pedestrian collision avoidance device, which is configured in a vehicle-mounted device, and comprises:

[0017] An information acquisition module is used to obtain pedestrian information and road direction sent by roadside equipment;

[0018] A target pedestrian determination module, used to determine whether there is a target pedestrian in the target area according to the vehicle information, the pedestrian information and the road direction;

[0019] an expected acceleration determination module, configured to determine an expected acceleration of the vehicle if the target pedestrian exists and the encounter time between the target pedestrian and the vehicle is less than or equal to a first duration;

[0020] The vehicle speed control module is used to control the vehicle to decelerate according to the expected acceleration of the vehicle when the distance between the vehicle and the target pedestrian reaches a safe distance, so as to avoid collision with the pedestrian.

[0021] According to a fifth aspect of the present invention, there is provided a pedestrian collision avoidance device, which is configured in a roadside device, and comprises:

[0022] An information acquisition module is used to acquire pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle;

[0023] A pedestrian occlusion determination module, used to determine whether a pedestrian in the target area is occluded by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information;

[0024] The pedestrian information sending module is used to send the road direction and pedestrian information of pedestrians blocked by obstacles to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with pedestrians.

[0025] According to a sixth aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0026] at least one processor; and

[0027] a memory communicatively connected to the at least one processor; wherein,

[0028] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the pedestrian collision avoidance method described in any embodiment of the present invention.

[0029] According to a seventh aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for enabling a processor to implement the pedestrian collision avoidance method described in any embodiment of the present invention when the computer instructions are executed.

[0030] The technical solution of the embodiment of the present invention obtains the pedestrian information and road direction sent by the roadside equipment, and then determines whether there is a target pedestrian in the target area based on the vehicle information, pedestrian information and road direction. If there is, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first time length, the expected acceleration of the vehicle is determined, and then when the distance between the vehicle and the target pedestrian reaches a safe distance, the vehicle is controlled to decelerate according to the expected acceleration of the vehicle to avoid colliding with the pedestrian. The above technical solution can actively brake to decelerate in sections where pedestrian collision accidents are frequent or complex driving sections with more obstructions, and when the vehicle has a blind spot, thereby reducing the incidence of pedestrian collision accidents.

[0031] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 is a flow chart of a pedestrian collision avoidance method provided according to Embodiment 1 of the present invention;

[0034] Figure 2 is a flow chart of a pedestrian collision avoidance method provided according to Embodiment 2 of the present invention;

[0035] Figure 3 is a flow chart of a pedestrian collision avoidance method provided according to Embodiment 3 of the present invention;

[0036] Figure 4 is a flow chart of a pedestrian collision avoidance method provided according to a fourth embodiment of the present invention;

[0037] Figure 5 is an architecture diagram of a pedestrian collision avoidance system provided according to Embodiment 5 of the present invention;

[0038] Figure 6 is a structural schematic diagram of a pedestrian collision avoidance device provided according to Embodiment 6 of the present invention;

[0039] Figure 7 is a schematic structural diagram of a pedestrian collision avoidance device provided according to Embodiment 7 of the present invention;

[0040] Figure 8 It is a schematic diagram of the structure of an electronic device for implementing the pedestrian collision avoidance method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0042] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] Embodiment 1

[0044] Figure 1It is a flow chart of a pedestrian collision avoidance method provided according to the first embodiment of the present invention. This embodiment can be applied to situations of how to perform pedestrian collision avoidance, and is particularly applicable to situations of how to perform pedestrian collision avoidance in "ghosting" scenarios, that is, scenarios in which pedestrians are blocked or in blind spots relative to the vehicle's field of view. Optionally, the pedestrian collision avoidance method of the present invention can be implemented by the cooperation of an on-board device and a roadside device; wherein the on-board device is used to obtain pedestrian information and road direction from the roadside device, and instruct the vehicle to slow down to avoid colliding with pedestrians; the roadside device is used to interact with the vehicle, obtain vehicle information, and remind pedestrians to avoid collisions.

[0045] The method can be performed by a pedestrian collision avoidance device, which can be implemented in the form of hardware and / or software and can be integrated into an electronic device that carries the pedestrian collision avoidance function, such as a vehicle-mounted terminal, and specifically can be a main controller of the vehicle-mounted terminal. Figure 1 As shown, the pedestrian collision avoidance method of this embodiment may include:

[0046] S110: Obtain pedestrian information and road direction sent by roadside equipment.

[0047] In this embodiment, pedestrian information refers to pedestrian information of pedestrians blocked in the target area, wherein the target area refers to the vehicle blind area on the road section with small curvature and straight line, that is, the blind area of ​​the vehicle in the area that can be detected by the roadside equipment. Optionally, the pedestrian information may include but is not limited to the pedestrian position, pedestrian moving direction and pedestrian moving speed.

[0048] The so-called road direction refers to the direction of the road, which can be expressed in the form of an angle in a geodetic coordinate system.

[0049] Specifically, after obtaining the pedestrian information of the obscured pedestrian, the roadside equipment sends the pedestrian information and road direction to the vehicle terminal through the V2X communication module; correspondingly, the main controller in the vehicle terminal can obtain the pedestrian information and road direction based on the V2X communication module.

[0050] It should be noted that the V2X communication module can be integrated into both the vehicle-mounted terminal and the roadside equipment, and then the vehicle-mounted terminal and the roadside equipment can exchange information based on the V2X communication module.

[0051] S120: Determine whether there is a target pedestrian in the target area according to the vehicle information, the pedestrian information and the road direction.

[0052] In this embodiment, the vehicle information may include but is not limited to vehicle speed, longitudinal acceleration, yaw angular velocity, vehicle position, vehicle width and vehicle driving direction. The so-called target pedestrian is the most dangerous pedestrian in the vehicle blind spot, that is, the pedestrian most likely to be hit.

[0053] Specifically, based on the target pedestrian detection model, it can be determined whether there is a target pedestrian in the target area according to vehicle information, pedestrian information and road direction. The target pedestrian detection model can be pre-trained based on a machine learning algorithm.

[0054] S130: If yes, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first duration, determine the expected acceleration of the vehicle.

[0055] Specifically, if there is a target pedestrian in the target area, the encounter time between the target pedestrian and the vehicle can be calculated based on the kinematic algorithm, and if the encounter time is less than or equal to the first time length, the expected acceleration of the vehicle is determined. The first time length can be set by those skilled in the art according to actual needs, for example, 5 seconds.

[0056] Exemplarily, determining the expected acceleration of the vehicle may be, based on a correspondence between a preset encounter time, a vehicle speed, and an acceleration, determining the vehicle speed at this moment and the expected acceleration of the vehicle corresponding to the encounter time between the target pedestrian and the vehicle at this moment.

[0057] S140: When the distance between the vehicle and the target pedestrian reaches a safe distance, control the vehicle to decelerate according to the desired acceleration of the vehicle to avoid collision with the pedestrian.

[0058] Specifically, the distance between the vehicle and the target pedestrian can be calculated based on a kinematic algorithm. Then, when the distance reaches a safe distance, the vehicle's desired acceleration is used to control the vehicle to decelerate to avoid colliding with the pedestrian. For example, an active braking command can be sent to a body stability control system, wherein the active braking command is used to instruct the body stability control system to control the vehicle to decelerate, and the active braking command may include the vehicle's desired acceleration.

[0059] The technical solution of the embodiment of the present invention obtains the pedestrian information and road direction sent by the roadside equipment, and then determines whether there is a target pedestrian in the target area based on the vehicle information, pedestrian information and road direction. If there is, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first time length, the expected acceleration of the vehicle is determined, and then when the distance between the vehicle and the target pedestrian reaches a safe distance, the vehicle is controlled to decelerate according to the expected acceleration of the vehicle to avoid colliding with the pedestrian. The above technical solution can actively brake to decelerate in sections where pedestrian collision accidents are frequent or complex driving sections with more obstructions, and when the vehicle has a blind spot, thereby reducing the incidence of pedestrian collision accidents.

[0060] On the basis of the above embodiment, as an optional manner of the embodiment of the present invention, a warning message may be sent to the instrument when the encounter time is less than or equal to a second duration; wherein the second duration is less than the first duration.

[0061] The warning information is used to warn the driver, and may be in the form of voice or visual animation, etc. The second duration may be set by those skilled in the art according to actual needs, for example, 3s.

[0062] Specifically, when the encounter duration is less than or equal to the second duration, a warning message may be sent to the instrument. For example, a visual warning may be provided to the driver in a preset form in the instrument, and an audible warning may be provided to the driver in combination with voice.

[0063] It is understandable that by displaying warning information to the driver in various forms such as voice and vision, warning information can be provided to the driver in a timely manner, so that the driver can slow down and avoid colliding with pedestrians; at the same time, it also improves the driver's driving experience.

[0064] Embodiment 2

[0065] Figure 2 is a flowchart of a pedestrian collision avoidance method provided according to the second embodiment of the present invention; based on the above embodiment, this embodiment further optimizes "determining whether there is a target pedestrian in the target area according to vehicle information, pedestrian information and road direction" and provides an optional implementation scheme. Figure 2 As shown, the pedestrian collision avoidance method of this embodiment may include:

[0066] S210: Obtain pedestrian information and road direction sent by roadside equipment.

[0067] S220: Determine the driving radius of the vehicle according to the vehicle speed and the yaw angular velocity.

[0068] Specifically, the quotient of the vehicle speed and the yaw rate may be calculated to obtain the driving radius of the vehicle.

[0069] S230. When the driving radius is greater than a set threshold, determine whether there is a risk of collision between pedestrians and vehicles in the target area based on the vehicle position, pedestrian position, vehicle driving direction, road direction, pedestrian moving speed, pedestrian moving direction, vehicle speed and vehicle width.

[0070] In an optional manner, when the driving radius is greater than a set threshold, that is, when the vehicle is currently in a small curvature or straight section, for each pedestrian in the target area, the vehicle position, vehicle driving direction, road direction, vehicle speed, vehicle width, pedestrian position, pedestrian moving speed and pedestrian moving direction of the pedestrian can be input into the collision assessment model, and after model processing, it is determined whether there is a collision risk between the pedestrian and the vehicle. Among them, the collision assessment model can be obtained based on a machine learning algorithm. The threshold can be set by those skilled in the art according to actual needs, for example, 125m.

[0071] Another optional method is to determine the first vector of the vehicle pointing to each pedestrian in the target area according to the vehicle position and the pedestrian position when the driving radius is greater than the set threshold. Specifically, for each pedestrian in the target area, the first vector of the vehicle pointing to the pedestrian is determined according to the Gaussian coordinates of the vehicle position and the Gaussian coordinates of the pedestrian position. For example, it can be (x pt -x c ,y pt -y c ), where (x pt ,y pt ) is the Gaussian coordinate of the pedestrian’s position, (x c ,y c ) is the Gaussian coordinate of the vehicle position.

[0072] After determining the first vector, the absolute value of the angle between the first vector and the road direction can be determined according to the first vector and the road direction. Specifically, the absolute value of the angle between the first vector and the road direction can be determined according to the following formula:

[0073]

[0074] Among them, θ r Indicates the road direction, β cptr Indicates the absolute value of the angle.

[0075] After determining the absolute value of the angle, if the relative relationship between the vehicle and the pedestrian is determined to be the vehicle approaching the pedestrian based on the vehicle's driving direction, the road direction, and the absolute value of the angle, then the direction of movement of the pedestrian relative to the vehicle is determined based on the vehicle's position, the road direction, and the pedestrian's position. Specifically, if the absolute value of the difference between the vehicle's driving direction and the road direction is within a preset range, and the absolute value of the angle is less than or equal to a set value, then the relative relationship between the vehicle and the pedestrian is determined to be the vehicle approaching the pedestrian. For example, if the vehicle's driving direction is in the same direction as the road direction, that is, |θ c -θ r |≤45deg or |θ c -θ r |≥315deg, and β cptr ≤45deg, the relative relationship between the vehicle and the pedestrian is that the vehicle is driving towards the pedestrian; if the vehicle is driving in the opposite direction of the road, that is, 135deg≤|θ c -θ r |≤225deg, and β cptr ≥135deg, the relative relationship between the vehicle and the pedestrian is that the vehicle is heading towards the pedestrian.

[0076] Then, the direction of movement of the pedestrian relative to the vehicle is determined based on the vehicle position, the road direction, the pedestrian position, and the pedestrian movement direction. Specifically, the direction angle θ of the vector pointing from the vehicle to the pedestrian is determined based on the vehicle position and the pedestrian position. cpt , for example, can be determined by the following formula:

[0077]

[0078] Afterwards, based on the direction angle and the road direction, it is determined whether the pedestrian is located on the left or right side of the road in the direction of vehicle travel, and combined with the pedestrian's moving direction, the pedestrian's moving direction relative to the vehicle is determined.

[0079] After determining the direction of movement of the pedestrian relative to the vehicle, if the pedestrian is determined to be crossing the road based on the direction of movement, determine whether there is a risk of collision between the pedestrian and the vehicle based on the vehicle position, speed, width, absolute value of the angle, the pedestrian's position, pedestrian movement speed and pedestrian movement direction.

[0080] Specifically, the following steps can be used to determine whether there is a collision risk between the pedestrian and the vehicle based on the vehicle position, speed, width, absolute value of the angle, the pedestrian position, pedestrian moving speed and pedestrian moving direction:

[0081] In the first step, a first person-vehicle distance along the road direction and a second person-vehicle distance perpendicular to the road direction are determined according to the vehicle position, the absolute value of the angle and the pedestrian position of the pedestrian.

[0082] The first distance between pedestrians and vehicles refers to the distance between pedestrians and vehicles along the road, and the second distance between pedestrians and vehicles refers to the distance between pedestrians and vehicles in a direction perpendicular to the road.

[0083] Specifically, the first person-vehicle distance and the second person-vehicle distance can be determined by the following formula:

[0084]

[0085]

[0086] Among them, D rlon Indicates the distance between the first person and the car; D rlat Indicates the distance between the second person and the vehicle.

[0087] The second step is to determine the horizontal moving speed of the pedestrian along the road direction and the vertical moving speed of the pedestrian along the direction perpendicular to the road according to the road direction, the pedestrian's moving speed and the pedestrian's moving direction. Specifically, the horizontal moving speed and the vertical moving speed can be determined by the following formula:

[0088] v x =vpt cos(θ pt -θ r )

[0089] v y =v pt sin(θ pt -θ r )

[0090] Among them, v x Indicates the horizontal moving speed, v y represents the vertical moving speed, θ pt Indicates the direction of pedestrian movement, v pt Indicates the pedestrian moving speed.

[0091] The third step is to determine the time it takes for the vehicle to meet the pedestrian based on the first person-vehicle distance, vehicle speed, and horizontal moving speed. Specifically, the time it takes for the vehicle to meet the pedestrian can be determined using the following formula:

[0092] t cpt =D rlon / (v c -v x )

[0093] Among them, t cpt Indicates the time it takes to meet, v c Indicates vehicle speed.

[0094] The fourth step is to determine the vertical distance between the pedestrian and the road based on the encounter time and the vertical moving speed. Specifically, the vertical distance between the vehicle and the pedestrian can be determined by the following formula:

[0095] d ptlat =v y ×t cpt

[0096] Among them, d ptlat Indicates the vertical distance.

[0097] The fifth step is to determine whether there is a risk of collision between the pedestrian and the vehicle based on the vertical distance, the distance between the second person and the vehicle and the width of the vehicle.

[0098] Specifically, the collision range can be determined based on the second pedestrian-vehicle distance and the vehicle width. For example, the result obtained by subtracting a set multiple of the vehicle width from the second pedestrian-vehicle distance can be used as the minimum value of the collision range, and the result obtained by adding a set multiple of the vehicle width to the second pedestrian-vehicle distance can be used as the maximum value of the collision range. Then, based on the vertical distance and the collision range, it is determined whether there is a collision risk between the pedestrian and the vehicle. If the vertical distance is within the collision range, that is, the vertical distance is equal to or greater than the minimum value and less than or equal to the maximum value, it is determined that there is a collision risk between the pedestrian and the vehicle.

[0099] It can be understood that, through the above method, it is possible to accurately determine whether there is a collision risk between pedestrians and vehicles in the target area.

[0100] S240: Pedestrians in the target area who are at risk of colliding with the vehicle are selected as candidate pedestrians.

[0101] Specifically, pedestrians in the target area who are at risk of colliding with the vehicle may be selected as candidate pedestrians.

[0102] S250: Select a target pedestrian from the candidate pedestrians according to the encounter time between the candidate pedestrians and the vehicle.

[0103] Specifically, from the candidate pedestrians, the pedestrian whose encounter time with the vehicle is the shortest is selected as the target pedestrian.

[0104] S260: If the target pedestrian exists and the encounter time between the target pedestrian and the vehicle is less than or equal to the first duration, determine the expected acceleration of the vehicle.

[0105] Exemplarily, the expected acceleration of the vehicle may be determined according to the vehicle speed, the distance between the first person and the vehicle, the vertical distance, and the horizontal moving speed. For example, it may be determined by the following formula:

[0106]

[0107] Among them, a cd represents the expected acceleration of the vehicle, d safe Indicates a safety distance, which can be set by technicians in this field according to actual conditions.

[0108] S270: When the distance between the vehicle and the target pedestrian reaches a safe distance, control the vehicle to decelerate according to the desired acceleration of the vehicle to avoid collision with the pedestrian.

[0109] The technical solution of the embodiment of the present invention obtains the pedestrian information and road direction sent by the roadside equipment, and then determines the driving radius of the vehicle according to the vehicle speed and yaw rate. When the driving radius is greater than the set threshold, it determines whether there is a collision risk between the pedestrian and the vehicle in the target area according to the vehicle position, pedestrian position, vehicle driving direction, road direction, pedestrian moving speed, pedestrian moving direction, vehicle speed and vehicle width, and then takes the pedestrians in the target area who have a collision risk with the vehicle as candidate pedestrians, and selects the target pedestrian from the candidate pedestrians according to the time it takes for the candidate pedestrians to meet the vehicle. If the target pedestrian exists and the time it takes for the target pedestrian to meet the vehicle is less than or equal to the first time, the expected acceleration of the vehicle is determined, and finally, when the distance between the vehicle and the target pedestrian reaches the safe distance, the vehicle is controlled to decelerate according to the expected acceleration of the vehicle to avoid colliding with the pedestrian. The above technical solution can actively brake to decelerate in sections where pedestrian collision accidents are frequent or complex driving sections with more obstructions, and when the vehicle has a blind spot, thereby reducing the incidence of pedestrian collision accidents.

[0110] Embodiment 3

[0111] Figure 3 This is a flow chart of a pedestrian collision avoidance method provided according to Embodiment 3 of the present invention. This embodiment can be applied to situations where pedestrians are subject to collision avoidance, and is particularly applicable to situations where pedestrians are subject to collision avoidance in a "ghosting" scenario, i.e., a scenario where pedestrians are blocked or have blind spots relative to the vehicle's field of view. Optionally, the pedestrian collision avoidance method of the present invention can be implemented by the cooperation of an on-board device and a roadside device.

[0112] The method can be performed by a pedestrian collision avoidance device, which can be implemented in the form of hardware and / or software and can be integrated into an electronic device that carries a pedestrian collision avoidance function, such as a roadside device. Figure 3 As shown, the pedestrian collision avoidance method of this embodiment may include:

[0113] S310: Obtain pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle.

[0114] In this embodiment, vehicle information may include but is not limited to vehicle speed, longitudinal acceleration, vehicle position and vehicle travel direction; pedestrian information may include but is not limited to pedestrian position, pedestrian movement direction and pedestrian movement speed. Obstacle information may include but is not limited to obstacle position, size and movement direction.

[0115] Specifically, the road test equipment can identify pedestrians and stationary obstacles in the target area through the fusion perception module, and obtain pedestrian information of pedestrians in the target area and obstacle information of stationary obstacles; at the same time, it can also obtain vehicle information sent by the target vehicle through the V2X communication module.

[0116] S320: Determine whether the pedestrian in the target area is blocked by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information.

[0117] Specifically, the obstacle position in the obstacle information can be used as the center, including the four-point coordinates of the matrix outline of the obstacle, and the pedestrian position, to determine whether the pedestrian is blocked by the obstacle in the forward and reverse directions of the road. For example, if the pedestrian is blocked in the forward direction of the road, the mark state is 1, if the pedestrian is blocked in the reverse direction of the road, the mark state is 2, and if there is no blockage in both directions, the mark state is 0.

[0118] S330: If yes, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with the pedestrian.

[0119] In this embodiment, the target vehicle refers to a vehicle that is about to enter the target area.

[0120] Specifically, if the flag state is 1, it is determined that the pedestrian is blocked by an obstacle, and the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle. Correspondingly, the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with the pedestrian.

[0121] The technical solution of the embodiment of the present invention obtains pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle, and then determines whether the pedestrian in the target area is blocked by obstacles based on the obstacle information and the pedestrian position in the pedestrian information. If so, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid colliding with the pedestrian. The above technical solution can provide information to the vehicle in a timely manner by sending the pedestrian information of the blocked pedestrian to the target vehicle, thereby avoiding the occurrence of collision accidents.

[0122] Embodiment 4

[0123] Figure 4 1 is a flowchart of a pedestrian collision avoidance method provided according to Embodiment 4 of the present invention. This embodiment is further optimized on the basis of the above embodiment to provide an optional implementation scheme. Figure 4 As shown, the pedestrian collision avoidance method of this embodiment may include:

[0124] S410: Obtain pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle.

[0125] S420: Determine whether the pedestrian in the target area is blocked by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information.

[0126] S430: If yes, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with the pedestrian.

[0127] S440: For each target vehicle in the target area, determine the encounter time between the target vehicle and the pedestrian according to the road direction, vehicle information and pedestrian information.

[0128] Exemplarily, for each pedestrian in the target area, a first vector pointing from the target vehicle to the pedestrian is determined based on the vehicle position of the target vehicle and the pedestrian position of the pedestrian. Specifically, for each pedestrian in the target area, a first vector pointing from the vehicle to the pedestrian is determined based on the Gaussian coordinates of the vehicle position of the target vehicle and the Gaussian coordinates of the pedestrian position. For example, it can be (x pt -x c ,y pt -y c ), where (x pt ,y pt ) is the Gaussian coordinate of the pedestrian’s position, (x c ,y c ) is the Gaussian coordinate of the vehicle position.

[0129] After determining the first vector, the absolute value of the angle between the first vector and the road direction can be determined according to the first vector and the road direction. Specifically, the absolute value of the angle between the first vector and the road direction can be determined according to the following formula:

[0130]

[0131] Among them, θ r Indicates the road direction, β cptr Indicates the absolute value of the angle.

[0132] After determining the absolute value of the angle, if the relative relationship between the vehicle and the pedestrian is determined to be the vehicle heading toward the pedestrian based on the vehicle's driving direction, the road direction, and the absolute value of the angle, then the direction of motion of the pedestrian relative to the target vehicle is determined based on the vehicle's position, the road direction, and the pedestrian's position. Specifically, if the absolute value of the difference between the road direction and the target vehicle's driving direction is within a preset range, and the absolute value of the angle is less than or equal to a set value, then the relative relationship between the target vehicle and the pedestrian is determined to be the vehicle heading toward the pedestrian. For example, if the vehicle's driving direction is in the same direction as the road direction, that is, |θ c -θ r |≤45deg or |θ c -θ r |≥315deg, and β cptr≤45deg, the relative relationship between the vehicle and the pedestrian is that the vehicle is driving towards the pedestrian; if the vehicle is driving in the opposite direction of the road, that is, 135deg≤|θ c -θ r |≤225deg, and β cptr ≥135deg, the relative relationship between the vehicle and the pedestrian is that the vehicle is heading towards the pedestrian.

[0133] Then, the direction of movement of the pedestrian relative to the vehicle is determined based on the vehicle position, the road direction, the pedestrian position, and the pedestrian movement direction. Specifically, the direction angle θ of the vector pointing from the vehicle to the pedestrian is determined based on the vehicle position and the pedestrian position. cpt , for example, can be determined by the following formula:

[0134]

[0135] Afterwards, based on the direction angle and the road direction, it is determined whether the pedestrian is located on the left or right side of the road in the direction of vehicle travel, and combined with the pedestrian's moving direction, the pedestrian's moving direction relative to the vehicle is determined.

[0136] After determining the direction of movement of the pedestrian relative to the vehicle, if the pedestrian is determined to be crossing the road based on the direction of movement, the time it takes for the pedestrian to encounter the target vehicle is determined based on the absolute value of the angle, the vehicle position, speed and width of the target vehicle, and the pedestrian position, pedestrian moving speed and pedestrian moving direction.

[0137] Specifically, the encounter time between the pedestrian and the target vehicle can be determined through the following steps based on the absolute value of the angle, the vehicle position, speed and width of the target vehicle, and the pedestrian position, pedestrian moving speed and pedestrian moving direction:

[0138] In the first step, a first person-vehicle distance along the road direction and a second person-vehicle distance perpendicular to the road direction are determined according to the absolute value of the angle, the vehicle position and the pedestrian position of the pedestrian.

[0139] The first distance between pedestrians and vehicles refers to the distance between pedestrians and vehicles along the road, and the second distance between pedestrians and vehicles refers to the distance between pedestrians and vehicles in a direction perpendicular to the road.

[0140] Specifically, the first person-vehicle distance and the second person-vehicle distance can be determined by the following formula:

[0141]

[0142]

[0143] Among them, D rlon Indicates the distance between the first person and the car; D rlatIndicates the distance between the second person and the vehicle.

[0144] The second step is to determine the horizontal moving speed of the pedestrian along the road direction and the vertical moving speed of the pedestrian along the direction perpendicular to the road according to the road direction, the pedestrian's moving speed and the pedestrian's moving direction. Specifically, the horizontal moving speed and the vertical moving speed can be determined by the following formula:

[0145] v x =v pt cos(θ pt -θ r )

[0146] v y =v pt sin(θ pt -θ r )

[0147] Among them, v x Indicates the horizontal moving speed, v y represents the vertical moving speed, θ pt Indicates the direction of pedestrian movement, v pt Indicates the pedestrian moving speed.

[0148] The third step is to determine the time it takes for the target vehicle to meet the pedestrian based on the first person-vehicle distance, vehicle speed, and horizontal moving speed. Specifically, the time it takes for the vehicle to meet the pedestrian can be determined by the following formula:

[0149] t cpt =D rlon / (v c -v x )

[0150] Among them, t cpt Indicates the time it takes to meet, v c Indicates vehicle speed.

[0151] S450: If the encounter time is less than the set time, a warning message is generated and displayed.

[0152] In this embodiment, the warning information is used to warn pedestrians and may be text content or language content.

[0153] Specifically, if the encounter time is less than the set time, a warning message is generated and displayed. The set time can be set by a person skilled in the art according to actual conditions, such as 10 seconds. For example, the problem reminder content can be displayed in a flashing manner or on a display screen in the roadside equipment, such as "Attention! Oncoming vehicle on the right / left side".

[0154] The technical solution of the embodiment of the present invention determines whether the pedestrians in the target area are blocked by obstacles through the obtained obstacle information and pedestrian positions in the pedestrian information. If so, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and road direction to avoid collision with the pedestrian. After that, for each target vehicle in the target area, the time it takes for the target vehicle to meet the pedestrian is determined according to the road direction, vehicle information and pedestrian information. If the meeting time is less than the set time, a warning message is generated and displayed. The above technical solution outputs warning information to pedestrians at the roadside end to remind pedestrians to avoid collisions, thereby reducing the incidence of collision accidents.

[0155] Embodiment 5

[0156] Figure 5 1 is a diagram of a pedestrian collision avoidance system architecture provided according to Embodiment 5 of the present invention. Figure 5 , the entire pedestrian collision avoidance system is introduced.

[0157] like Figure 5 As shown, the pedestrian collision avoidance system may include vehicle-mounted equipment and roadside equipment; wherein the vehicle-mounted equipment includes a vehicle bus, a main controller, a high-precision positioning module, a V2X communication module, an early warning module, a human-computer interaction module, and an active braking execution module. Exemplarily, the high-precision positioning module is used to locate the vehicle, obtain the vehicle position, and send the vehicle position to the main controller. The vehicle bus sends vehicle information such as the vehicle speed, yaw rate, and vehicle width to the main controller. The main controller is used to obtain the vehicle position from the high-precision positioning module; interact with the V2X communication module to obtain the road direction and pedestrian information of the target area sent by the roadside equipment, and send the vehicle information of the vehicle to the roadside equipment; and determine whether there is a target pedestrian in the target area based on the vehicle information, pedestrian information and road direction. If there is, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first time duration, determine the expected acceleration of the vehicle, and when the distance between the vehicle and the target pedestrian reaches a safe distance, send a deceleration command to the active braking execution module to make the active braking module decelerate according to the expected acceleration of the vehicle; at the same time, it can also send warning information to the warning module and the human-computer interaction module, provide a sound warning to the driver through the warning module, and provide a visual warning to the driver through the human-computer interaction module.

[0158] It should be noted that the driver can also control the opening and closing of the vehicle-side pedestrian collision avoidance system through the human-computer interaction module.

[0159] The roadside equipment includes a main controller, a high-precision positioning module, a fusion perception module, a V2X communication module, a high-precision map database, an early warning module, and a lighting module. Among them, the high-precision positioning module is used to obtain the location information and time information of the roadside equipment, and send the time information and the location information of the roadside equipment to the main controller. The fusion perception module uses high-definition cameras and millimeter-wave radars to monitor the target area, achieve complementary advantages, and obtain obstacle information and pedestrian information such as the location, shape, and movement status of static and moving obstacles in the target area in real time, and send the obstacle information and pedestrian information to the main controller.

[0160] The main controller of the roadside equipment receives the obstacle information and pedestrian information sent by the fusion perception module, receives the vehicle information output by the V2X communication module, and retrieves the map data of the high-precision map database; according to the obstacle information and the pedestrian position in the pedestrian information, it is determined whether the pedestrians in the target area are blocked by obstacles. If so, the road direction and the pedestrian information of the pedestrians blocked by obstacles are sent to the target vehicle through the V2X communication module. Furthermore, for each target vehicle in the target area, the time it takes for the target vehicle to meet the pedestrian is determined based on the road direction, vehicle information and pedestrian information; if the meeting time is less than the set time, an early warning message is generated and displayed through the early warning module, for example, the early warning module provides an acoustic and visual warning to pedestrians in the target area, reminding pedestrians of the countdown of the upcoming vehicle. Furthermore, according to the time information of the high-precision positioning module, the target area can be illuminated at night through the lighting module to improve the accuracy of night perception and recognition.

[0161] The present invention is aimed at pedestrian scenarios in blind spots, especially "ghost peeking" scenarios where pedestrians cross the road and are blocked, to achieve two-way synergy for drivers and roadside pedestrians, and to achieve collision avoidance by assisting both parties (on-board equipment and roadside equipment). Based on two-way reminders based on information interaction, it takes into account early warning and braking assistance for both drivers and pedestrians.

[0162] Embodiment 6

[0163] Figure 6 It is a structural schematic diagram of a pedestrian collision avoidance device provided according to the sixth embodiment of the present invention. This embodiment can be applied to situations of how to avoid pedestrian collisions, and is particularly applicable to situations of how to avoid pedestrian collisions in "ghosting" scenarios, that is, scenarios in which pedestrians are blocked or in blind spots relative to the vehicle's field of view. Optionally, the pedestrian collision avoidance method of the present invention can be implemented by the cooperation of an on-board device and a roadside device; wherein the on-board device is used to obtain pedestrian information and road direction from the roadside device, and instruct the vehicle to slow down to avoid colliding with pedestrians; the roadside device is used to interact with the vehicle, obtain vehicle information, and remind pedestrians to avoid collisions.

[0164] The device can be implemented in the form of hardware and / or software, and can be integrated into an electronic device carrying a pedestrian collision avoidance function, such as an on-board device. Figure 6 As shown, the pedestrian collision avoidance device of this embodiment may include:

[0165] The information acquisition module 610 is used to acquire pedestrian information and road direction sent by the roadside equipment;

[0166] A target pedestrian determination module 620, for determining whether there is a target pedestrian in the target area according to vehicle information, pedestrian information and road direction;

[0167] An expected acceleration determination module 630, configured to determine an expected acceleration of the vehicle if the target pedestrian exists and the encounter time between the target pedestrian and the vehicle is less than or equal to a first duration;

[0168] The vehicle speed control module 640 is used to control the vehicle to decelerate according to the expected acceleration of the vehicle when the distance between the vehicle and the target pedestrian reaches a safe distance, so as to avoid collision with the pedestrian.

[0169] The technical solution of the embodiment of the present invention obtains the pedestrian information and road direction sent by the roadside equipment, and then determines whether there is a target pedestrian in the target area based on the vehicle information, pedestrian information and road direction. If there is, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first time length, the expected acceleration of the vehicle is determined, and then when the distance between the vehicle and the target pedestrian reaches a safe distance, the vehicle is controlled to decelerate according to the expected acceleration of the vehicle to avoid colliding with the pedestrian. The above technical solution can actively brake to decelerate in sections where pedestrian collision accidents are frequent or complex driving sections with more obstructions, and when the vehicle has a blind spot, thereby reducing the incidence of pedestrian collision accidents.

[0170] Optionally, the vehicle information includes vehicle speed, longitudinal acceleration, yaw angular velocity, vehicle position, vehicle width and vehicle driving direction; the pedestrian information includes pedestrian position, pedestrian moving direction and pedestrian moving speed; accordingly, the target pedestrian determination module 620 includes:

[0171] A driving radius determination unit, used to determine the driving radius of the vehicle according to the vehicle speed and the yaw rate;

[0172] a collision risk determination unit, for determining whether there is a collision risk between a pedestrian and a vehicle in a target area according to the vehicle position, the pedestrian position, the vehicle driving direction, the road direction, the pedestrian moving speed, the pedestrian moving direction, the vehicle speed and the vehicle width when the driving radius is greater than a set threshold;

[0173] A candidate pedestrian determination unit, used to determine pedestrians in the target area who have a risk of collision with the vehicle as candidate pedestrians;

[0174] The target pedestrian determination unit is used to select a target pedestrian from the candidate pedestrians according to the encounter time between the candidate pedestrians and the vehicle.

[0175] Optionally, the collision risk determination unit includes:

[0176] A first vector determination subunit is used to determine, for each pedestrian in the target area, a first vector pointing from the vehicle to the pedestrian according to the vehicle position and the pedestrian position of the pedestrian;

[0177] An angle absolute value determination subunit, used to determine the absolute value of the angle between the first vector and the road direction according to the first vector and the road direction;

[0178] a motion direction determination subunit, for determining the motion direction of the pedestrian relative to the vehicle based on the vehicle position, the road direction, the pedestrian position and the pedestrian moving direction, if the relative relationship between the vehicle and the pedestrian is determined to be that the vehicle is driving towards the pedestrian based on the vehicle position, the road direction and the pedestrian position and the pedestrian moving direction;

[0179] The collision risk determination subunit is used to determine whether there is a collision risk between the pedestrian and the vehicle based on the vehicle position, speed, width, absolute value of the angle, the pedestrian position, pedestrian movement speed and pedestrian movement direction if the pedestrian is determined to be crossing the road based on the movement direction.

[0180] Optionally, the collision risk determination subunit is specifically used for:

[0181] Determine a first vehicle-person distance along the road direction and a second vehicle-person distance perpendicular to the road direction according to the vehicle position, the absolute value of the angle and the pedestrian position of the pedestrian;

[0182] Determine the horizontal moving speed of the pedestrian along the road direction and the vertical moving speed of the pedestrian in a direction perpendicular to the road according to the road direction, the pedestrian moving speed and the pedestrian moving direction;

[0183] Determine the time it takes for the vehicle and the pedestrian to meet based on the distance between the first person and the vehicle, the vehicle speed and the horizontal moving speed;

[0184] Determine the vertical distance between the pedestrian and the road based on the encounter time and vertical moving speed;

[0185] Based on the vertical distance, the distance between the second person and the vehicle, and the width of the vehicle, determine whether there is a risk of collision between the pedestrian and the vehicle.

[0186] Optionally, the expected acceleration determination module 630 is specifically used for:

[0187] The expected acceleration of the vehicle is determined based on the vehicle speed, the distance between the first person and the vehicle, the vertical distance and the horizontal moving speed.

[0188] Optionally, the device further comprises:

[0189] The warning information sending module is used to send warning information to the instrument when the encounter time is less than or equal to the second time length; wherein the second time length is less than the first time length.

[0190] The pedestrian collision avoidance device provided in the embodiment of the present invention can execute the pedestrian collision avoidance method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0191] Embodiment 7

[0192] Figure 7 1 is a schematic diagram of the structure of a pedestrian collision avoidance device provided according to Embodiment 7 of the present invention. This embodiment can be applied to situations where pedestrians are subject to collision avoidance, and is particularly applicable to situations where pedestrians are subject to collision avoidance in a "ghosting" scenario, i.e., a scenario where pedestrians are blocked or have blind spots relative to the vehicle's field of view. Optionally, the pedestrian collision avoidance method of the present invention can be implemented by the cooperation of a vehicle-mounted device and a roadside device.

[0193] The device can be implemented in the form of hardware and / or software, and can be integrated into an electronic device that carries a pedestrian collision avoidance function, such as a roadside device. Figure 7 As shown, the pedestrian collision avoidance device of this embodiment may include:

[0194] The information acquisition module 710 is used to acquire pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle;

[0195] A pedestrian occlusion determination module 720, for determining whether a pedestrian in a target area is occluded by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information;

[0196] The pedestrian information sending module 730 is used to send the road direction and pedestrian information of pedestrians blocked by obstacles to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and road direction to avoid collision with pedestrians.

[0197] The technical solution of the embodiment of the present invention obtains pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle, and then determines whether the pedestrian in the target area is blocked by obstacles based on the obstacle information and the pedestrian position in the pedestrian information. If so, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid colliding with the pedestrian. The above technical solution can provide information to the vehicle in a timely manner by sending the pedestrian information of the blocked pedestrian to the target vehicle, thereby avoiding the occurrence of collision accidents.

[0198] Optionally, the device further comprises:

[0199] An encounter time determination module is used to determine, for each target vehicle in the target area, an encounter time between the target vehicle and the pedestrian according to the road direction, vehicle information and pedestrian information;

[0200] The warning information display module is used to generate and display a warning message if the encounter time is less than the set time.

[0201] Optionally, the vehicle information includes vehicle speed, longitudinal acceleration, vehicle position and vehicle travel direction; the pedestrian information includes pedestrian position, pedestrian moving direction and pedestrian moving speed; accordingly, the encounter time determination module includes:

[0202] A first vector determination unit is used to determine, for each pedestrian in the target area, a first vector of the target vehicle pointing to the pedestrian according to the vehicle position of the target vehicle and the pedestrian position of the pedestrian;

[0203] An angle absolute value determining unit, used to determine the absolute value of the angle between the first vector and the road direction according to the first vector and the road direction;

[0204] a movement direction determining unit, for determining the movement direction of the pedestrian relative to the target vehicle according to the road direction, the vehicle position of the target vehicle and the pedestrian position of the pedestrian, if the relative relationship between the target vehicle and the pedestrian is determined to be the vehicle driving towards the pedestrian according to the road direction, the absolute value of the angle and the vehicle driving direction of the target vehicle;

[0205] The meeting time determination unit is used to determine the meeting time between the pedestrian and the target vehicle based on the absolute value of the angle, the vehicle position and speed of the target vehicle, and the pedestrian position, pedestrian movement speed and pedestrian movement direction if the pedestrian is determined to be crossing the road based on the movement direction.

[0206] Optionally, the encounter time determination unit is specifically used for:

[0207] Then, according to the absolute value of the angle, the vehicle position and the pedestrian position of the pedestrian, a first person-vehicle distance along the road direction and a second person-vehicle distance perpendicular to the road direction are determined;

[0208] Determine the horizontal moving speed of the pedestrian along the road direction and the vertical moving speed of the pedestrian in a direction perpendicular to the road according to the road direction, the pedestrian moving speed and the pedestrian moving direction;

[0209] The encounter time between the target vehicle and the pedestrian is determined based on the first person-vehicle distance, vehicle speed and horizontal moving speed.

[0210] The pedestrian collision avoidance device provided in the embodiment of the present invention can execute the pedestrian collision avoidance method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0211] In the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of data such as vehicle information, road direction and pedestrian information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0212] Embodiment 8

[0213] Figure 8 is a schematic diagram of the structure of an electronic device for implementing the pedestrian collision avoidance method according to an embodiment of the present invention, Figure 8 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0214] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0215] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0216] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a pedestrian collision avoidance method.

[0217] In some embodiments, the pedestrian collision avoidance method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the pedestrian collision avoidance method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the pedestrian collision avoidance method in any other appropriate manner (e.g., by means of firmware).

[0218] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0219] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0220] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0221] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0222] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0223] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0224] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0225] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A pedestrian collision avoidance method, applied to a vehicle-mounted device, characterized in that: include: Obtain pedestrian information and road direction sent by roadside equipment; Determining whether there is a target pedestrian in the target area according to the vehicle information, the pedestrian information and the road direction; If so, and the encounter time between the target pedestrian and the vehicle is less than or equal to the first duration, determining the expected acceleration of the vehicle; When the distance between the vehicle and the target pedestrian reaches a safe distance, controlling the vehicle to decelerate according to the expected acceleration of the vehicle to avoid collision with the pedestrian; The vehicle information includes vehicle speed, longitudinal acceleration, yaw angular velocity, vehicle position, vehicle width and vehicle travel direction; the pedestrian information includes pedestrian position, pedestrian moving direction and pedestrian moving speed; and determining whether there is a target pedestrian in the target area according to the vehicle information, the pedestrian information and the road direction includes: determining a travel radius of the vehicle according to the vehicle speed and the yaw angular velocity; When the driving radius is greater than a set threshold, determining whether there is a collision risk between the pedestrian and the vehicle in the target area according to the vehicle position, the pedestrian position, the vehicle driving direction, the road direction, the pedestrian moving speed, the pedestrian moving direction, the vehicle speed and the vehicle width; Taking pedestrians in the target area who have a collision risk with the vehicle as candidate pedestrians; Selecting a target pedestrian from the candidate pedestrians according to the encounter time between the candidate pedestrians and the vehicle; The determining, based on the vehicle position, the pedestrian position, the vehicle driving direction, the road direction, the pedestrian moving speed, the pedestrian moving direction, the vehicle speed and the vehicle width, whether there is a collision risk between the pedestrian and the vehicle in the target area comprises: For each pedestrian in the target area, determining a first vector of the vehicle pointing to the pedestrian according to the vehicle position and the pedestrian position of the pedestrian; Determine an absolute value of an angle between the first vector and the road direction according to the first vector and the road direction; If the relative relationship between the vehicle and the pedestrian is determined to be that the vehicle is heading toward the pedestrian based on the vehicle's driving direction, the road direction, and the absolute value of the angle, then the direction of movement of the pedestrian relative to the vehicle is determined based on the vehicle's position, the road direction, the pedestrian's position, and the pedestrian's moving direction; If the pedestrian is determined to be crossing the road according to the movement direction, then determining whether there is a risk of collision between the pedestrian and the vehicle according to the vehicle position, the vehicle speed, the vehicle width, the absolute value of the angle, the pedestrian position, the pedestrian moving speed and the pedestrian moving direction; Wherein, determining, based on the vehicle's driving direction, the road direction and the absolute value of the angle, that the relative relationship between the vehicle and the pedestrian is that the vehicle is driving towards the pedestrian comprises: If the absolute value of the difference between the vehicle's driving direction and the road direction is within a preset range, and the absolute value of the angle is less than or equal to a set value, then the relative relationship between the vehicle and the pedestrian is determined to be that the vehicle is driving towards the pedestrian.

2. The method according to claim 1, characterized in that The determining whether there is a collision risk between the pedestrian and the vehicle according to the vehicle position, the vehicle speed, the vehicle width, the absolute value of the angle, the pedestrian position, the pedestrian moving speed and the pedestrian moving direction includes: Determine a first person-vehicle distance along the road direction and a second person-vehicle distance perpendicular to the road direction according to the vehicle position, the absolute value of the angle and the pedestrian position of the pedestrian; Determining the horizontal moving speed of the pedestrian along the road direction and the vertical moving speed of the pedestrian in a direction perpendicular to the road according to the road direction, the pedestrian moving speed and the pedestrian moving direction; Determining the encounter time between the vehicle and the pedestrian according to the first vehicle-person distance, the vehicle speed and the horizontal moving speed; Determining a vertical distance between the pedestrian and the road according to the encounter time and the vertical moving speed; Determine whether there is a collision risk between the pedestrian and the vehicle according to the vertical distance, the second person-vehicle distance and the vehicle width.

3. The method according to claim 2, characterized in that The determining of the expected acceleration of the vehicle includes: The expected acceleration of the vehicle is determined according to the vehicle speed, the first vehicle-person distance, the vertical distance and the horizontal moving speed.

4. The method according to claim 1, characterized in that Also includes: When the encounter time is less than or equal to a second time length, a warning message is sent to the instrument; wherein the second time length is less than the first time length.

5. A pedestrian collision avoidance method, applied to roadside equipment, characterized in that: include: Obtain pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle; Determining whether a pedestrian in the target area is blocked by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information; If yes, the road direction and pedestrian information of the pedestrian blocked by the obstacle are sent to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with the pedestrian; The method further comprises: For each target vehicle in the target area, determining an encounter time between the target vehicle and the pedestrian according to the road direction, the vehicle information and the pedestrian information; If the encounter time is less than the set time, a warning message will be generated and displayed; The vehicle information includes vehicle speed, longitudinal acceleration, vehicle position and vehicle travel direction; the pedestrian information includes pedestrian position, pedestrian moving direction and pedestrian moving speed; and determining the encounter time between the target vehicle and the pedestrian based on the road direction, the vehicle information and the pedestrian information includes: For each pedestrian in the target area, determining a first vector of the target vehicle pointing to the pedestrian according to the vehicle position of the target vehicle and the pedestrian position of the pedestrian; Determine an absolute value of an angle between the first vector and the road direction according to the first vector and the road direction; If the relative relationship between the target vehicle and the pedestrian is determined to be that the vehicle is traveling toward the pedestrian based on the road direction, the absolute value of the angle, and the driving direction of the target vehicle, then the moving direction of the pedestrian relative to the target vehicle is determined based on the road direction, the vehicle position of the target vehicle, and the pedestrian position of the pedestrian; If the pedestrian is determined to be crossing the road according to the moving direction, then the time taken for the pedestrian to meet the target vehicle is determined according to the absolute value of the angle, the vehicle position and speed of the target vehicle, and the pedestrian position, pedestrian moving speed and pedestrian moving direction; Wherein, determining, based on the road direction, the absolute value of the angle and the driving direction of the target vehicle, that the relative relationship between the target vehicle and the pedestrian is that the vehicle is driving towards the pedestrian comprises: If the absolute value of the difference between the road direction and the vehicle driving direction of the target vehicle is within a preset range, and the absolute value of the angle is less than or equal to a set value, then the relative relationship between the target vehicle and the pedestrian is determined to be that the vehicle is driving towards the pedestrian.

6. The method according to claim 5, characterized in that Determining the encounter time between the pedestrian and the target vehicle according to the absolute value of the angle, the vehicle position and speed of the target vehicle, and the pedestrian position, pedestrian moving speed and pedestrian moving direction, comprises: determining a first person-vehicle distance along the road direction and a second person-vehicle distance perpendicular to the road direction according to the absolute value of the angle, the vehicle position and the pedestrian position of the pedestrian; Determine the horizontal moving speed of the pedestrian along the road direction and the vertical moving speed of the pedestrian perpendicular to the road direction according to the road direction, the pedestrian moving speed and the pedestrian moving direction; The encounter time between the target vehicle and the pedestrian is determined according to the first vehicle-person distance, the vehicle speed and the horizontal moving speed.

7. A pedestrian collision avoidance device, configured on a vehicle-mounted device, characterized in that: include: An information acquisition module is used to obtain pedestrian information and road direction sent by roadside equipment; A target pedestrian determination module, used to determine whether there is a target pedestrian in the target area according to the vehicle information, the pedestrian information and the road direction; an expected acceleration determination module, configured to determine an expected acceleration of the vehicle if the target pedestrian exists and the encounter time between the target pedestrian and the vehicle is less than or equal to a first duration; A vehicle speed control module, configured to control the vehicle to decelerate according to the expected acceleration of the vehicle when the distance between the vehicle and the target pedestrian reaches a safe distance, so as to avoid collision with the pedestrian; The vehicle information includes vehicle speed, longitudinal acceleration, yaw rate, vehicle position, vehicle width and vehicle travel direction; The pedestrian information includes the pedestrian's position, pedestrian's moving direction and pedestrian's moving speed; The target pedestrian determination module includes: a driving radius determining unit, configured to determine a driving radius of the vehicle according to the vehicle speed and the yaw rate; a collision risk determination unit, configured to determine whether there is a collision risk between the pedestrian in the target area and the vehicle according to the vehicle position, the pedestrian position, the vehicle driving direction, the road direction, the pedestrian moving speed, the pedestrian moving direction, the vehicle speed and the vehicle width when the driving radius is greater than a set threshold; a candidate pedestrian determination unit, configured to determine pedestrians in the target area who are at risk of collision with the vehicle as candidate pedestrians; a target pedestrian determination unit, configured to select a target pedestrian from the candidate pedestrians according to an encounter time between the candidate pedestrians and the vehicle; The collision risk determination unit comprises: A first vector determination subunit is used to determine, for each pedestrian in the target area, a first vector pointing from the vehicle to the pedestrian according to the vehicle position and the pedestrian position of the pedestrian; an angle absolute value determining subunit, configured to determine an absolute value of an angle between the first vector and the road direction according to the first vector and the road direction; a motion direction determination subunit, configured to determine the motion direction of the pedestrian relative to the vehicle according to the vehicle position, the road direction, the pedestrian position and the pedestrian moving direction, if the relative relationship between the vehicle and the pedestrian is determined to be that the vehicle is driving towards the pedestrian according to the vehicle driving direction, the road direction and the absolute value of the angle; a collision risk determination subunit, for determining whether there is a collision risk between the pedestrian and the vehicle based on the vehicle position, the vehicle speed, the vehicle width, the absolute value of the angle, the pedestrian position, the pedestrian moving speed and the pedestrian moving direction, if the pedestrian is determined to be crossing the road based on the moving direction; The movement direction determination subunit is specifically used to determine that the relative relationship between the vehicle and the pedestrian is that the vehicle is driving towards the pedestrian if the absolute value of the difference between the vehicle's driving direction and the road direction is within a preset range and the absolute value of the angle is less than or equal to a set value.

8. A pedestrian collision avoidance device, arranged on a roadside device, characterized in that: include: An information acquisition module is used to acquire pedestrian information and obstacle information in the target area, as well as vehicle information sent by the target vehicle; A pedestrian occlusion determination module, used to determine whether a pedestrian in the target area is occluded by an obstacle according to the obstacle information and the pedestrian position in the pedestrian information; A pedestrian information sending module, for sending the road direction and pedestrian information of pedestrians blocked by obstacles to the target vehicle, so that the target vehicle controls the vehicle to slow down according to the pedestrian information and the road direction to avoid collision with pedestrians; The device further comprises: an encounter time determination module, configured to determine, for each target vehicle in the target area, an encounter time between the target vehicle and the pedestrian according to the road direction, the vehicle information and the pedestrian information; The warning information display module is used to generate and display a warning message if the encounter time is less than the set time; The vehicle information includes vehicle speed, longitudinal acceleration, vehicle position and vehicle travel direction; the pedestrian information includes pedestrian position, pedestrian moving direction and pedestrian moving speed; the encounter time determination module includes: A first vector determination unit is used to determine, for each pedestrian in the target area, a first vector of the target vehicle pointing to the pedestrian according to the vehicle position of the target vehicle and the pedestrian position of the pedestrian; an angle absolute value determining unit, configured to determine an absolute value of an angle between the first vector and the road direction according to the first vector and the road direction; a movement direction determining unit, configured to determine the movement direction of the pedestrian relative to the target vehicle according to the road direction, the vehicle position of the target vehicle and the pedestrian position of the pedestrian, if the relative relationship between the target vehicle and the pedestrian is determined to be the vehicle driving towards the pedestrian according to the road direction, the absolute value of the angle and the vehicle driving direction of the target vehicle; an encounter time determination unit, for determining an encounter time between the pedestrian and the target vehicle based on the absolute value of the angle, the vehicle position and speed of the target vehicle, and the pedestrian position, pedestrian moving speed and pedestrian moving direction, if the pedestrian is determined to be crossing the road based on the moving direction; The movement direction determination unit is specifically used to determine that the relative relationship between the target vehicle and the pedestrian is that the vehicle is driving towards the pedestrian if the absolute value of the difference between the road direction and the vehicle driving direction of the target vehicle is within a preset range and the absolute value of the angle is less than or equal to a set value.

9. A pedestrian collision avoidance system, characterized in that: The system includes vehicle equipment and roadside equipment; wherein, The vehicle-mounted device is used to perform the pedestrian collision avoidance method according to any one of claims 1 to 4; The roadside equipment is used to execute the pedestrian collision avoidance method as described in any one of claims 5-6.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the pedestrian collision avoidance method described in any one of claims 1 to 4, or the pedestrian collision avoidance method described in any one of claims 5 to 6.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the pedestrian collision avoidance method described in any one of claims 1 to 4, or the pedestrian collision avoidance method described in any one of claims 5 to 6 when executed.

Images