A vehicle-pedestrian collision warning method, device and equipment

Abstract

The application discloses a person-vehicle conflict early warning method, device and equipment, and relates to the technical field of Internet of Vehicles. The method comprises the following steps: identifying a vulnerable road user (VRU) in a region of interest (ROI) of the VRU at an intersection, obtaining an identification result; obtaining a driving intention of a vehicle located in a ROI of the vehicle at the intersection; determining a risk area and a risk level according to the identification result and / or the driving intention; and sending an early warning message according to the risk area and the risk level. In this way, a series of accurate notification strategies are designed based on the collision risk area, and the problems of false positives and false negatives existing in the current early warning based on target detection are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle networking technology, and in particular to a method, device and equipment for early warning of human-vehicle conflicts. Background Technology

[0002] With the continuous development of my country's economy, the number of motor vehicles is increasing year by year, resulting in a large number of traffic accidents and significant economic losses. The demand for intelligent transportation systems is growing stronger, and how to reduce traffic accidents and provide safe travel services for motor vehicle drivers is an urgent problem that intelligent transportation systems must solve.

[0003] Historically, intersections and turns have been the most frequent and serious accident sites in traffic accidents. Pedestrians and cyclists are considered vulnerable users (VRUs) in such incidents. Current traffic warning methods for VRUs involve identifying the VRU target and determining the likelihood of a collision based on the relative position and speed of the vehicle and the VRU target. If a collision is imminent, a collision warning is issued. However, this existing method carries the risk of false alarms or missed alarms due to inaccurate VRU target status identification. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, and equipment for early warning of pedestrian-vehicle conflicts, thereby solving the problem of false alarms or missed alarms in the current early warning methods.

[0005] Firstly, in order to achieve the above objectives, embodiments of this application provide a method for early warning of pedestrian-vehicle conflicts, including:

[0006] Within the Region of Interest (ROI) of Vulnerable Traffic Participants (VRUs) at the intersection, identify the VRUs and obtain the identification results.

[0007] Obtain the driving intention of vehicles within the vehicle ROI located at the intersection;

[0008] Based on the identification results and / or the driving intention, the risk area and risk level are determined;

[0009] A warning message is sent based on the risk area and the risk level.

[0010] Optionally, obtaining the driving intentions of vehicles within the vehicle ROI located at the intersection includes:

[0011] Based on the lane information where the vehicle is located, determine the vehicle's driving intention; or,

[0012] Based on the acquired Basic Safety Message (BSM) of the vehicle, the driving intention of the vehicle is determined.

[0013] Optionally, based on the identification results and / or the driving intention, the risk area and risk level are determined, including:

[0014] Based on the identification results, the VRU ROI of the identified VRU is determined to be a risk area, and the risk level is a potential risk level.

[0015] Optionally, determining the risk area and risk level based on the identification result and / or the driving intention further includes:

[0016] Based on the driving intention, identify the area-associated vehicle that is about to enter the risk area of ​​the potential risk level.

[0017] Based on the driving information of the vehicles associated with the region and the driving information of the VRU, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

[0018] Optionally, based on the driving information of the vehicle associated with the region and the driving information of the VRU, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0019] Based on the driving intention and the obtained driving speed of the area-associated vehicle, the first moment when the area-associated vehicle enters the risk area of ​​the potential risk level is obtained; and / or, based on the identification result, the second moment when the VRU leaves the risk area of ​​the potential risk level is obtained;

[0020] Based on at least one of the first time point, the second time point, and the driving speed, determine whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

[0021] Optionally, based on at least one of the first time point, the second time point, and the driving speed, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0022] The post-intrusion time PET is determined based on the difference between the first time point and the second time point;

[0023] When the PET value is less than a first value and the driving speed is between a first speed and a second speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is first level; wherein the first speed is less than the second speed;

[0024] When the PET value is between the first and second values, and the driving speed is between the first and second speeds, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is the second level; wherein the first value is less than the second value;

[0025] When the PET value is less than the second value and the driving speed is less than the first speed, the risk area of ​​the potential risk level is determined to be a collision risk area, and the risk level is the third level.

[0026] Optionally, based on at least one of the first time point, the second time point, and the driving speed, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0027] The collision time TTC is determined based on the difference between the first time point and the current time point.

[0028] When the TTC is less than a first value and the driving speed is between a first speed and a second speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is first level, wherein the first speed is less than the second speed;

[0029] When the TTC is between the first value and the second value, and the driving speed is between the first speed and the second speed, the risk area of ​​the potential risk level is determined to be a collision risk area, and the risk level is the second level, wherein the first value is less than the second value;

[0030] When the TTC is less than the second value and the driving speed is less than the first speed, the risk area of ​​the potential risk level is determined to be a collision risk area, and the risk level is the third level.

[0031] Optionally, based on at least one of the first time point, the second time point, and the driving speed, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0032] When the driving speed is greater than the second speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is the second level;

[0033] When the driving speed is greater than the third speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is the first level, wherein the third speed is greater than the second speed.

[0034] Optionally, based on the risk area and the risk level, an early warning message may be sent, including at least one of the following:

[0035] Send a first warning message to the roadside vehicle alert device corresponding to the risk area. The first warning message is used to instruct the roadside vehicle alert device to output a first warning message related to the risk level of the risk area.

[0036] A second warning message is sent to the roadside VRU alert device associated with the risk area, the second warning message instructing the roadside VRU alert device to output a second warning message related to the risk level of the risk area;

[0037] A third warning message is sent to the roadside unit (RSU), which instructs the RSU to send a third warning message related to the risk level of the risk area to the human-machine interface (HMI) device of the area-associated vehicle, and / or instructs the RSU to send a safety warning message to the HMI device of the collision-risk-associated vehicle; wherein the area-associated vehicle is a vehicle about to enter the risk area, and the collision-risk-associated vehicle is a vehicle directly associated with the collision event.

[0038] Optionally, the first warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, and the number of VRUs in the risk area.

[0039] Optionally, the second warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, information of vehicles associated with the risk area, and information of vehicles associated with the collision risk.

[0040] Optionally, the third warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, the center point of the risk area, the outer boundary of the risk area, the number of VRUs in the risk area, information on area-associated vehicles related to the risk area, and information on collision risk-associated vehicles.

[0041] Optionally, the method further includes:

[0042] The pedestrian walkway at the intersection is divided into multiple VRU ROIs, where each VRU ROI is the pedestrian walkway directly opposite the road entering or exiting the intersection.

[0043] Secondly, in order to achieve the above objectives, embodiments of this application provide a pedestrian-vehicle conflict warning device, comprising:

[0044] The identification module is used to identify VRUs within the Region of Interest (ROI) of Vulnerable Traffic Participants (VRUs) at intersections and obtain identification results.

[0045] The acquisition module is used to acquire the driving intentions of vehicles within the vehicle ROI located at the intersection.

[0046] The first determining module is used to determine the risk area and risk level based on the identification result and / or the driving intention.

[0047] Thirdly, in order to achieve the above objectives, this application provides a pedestrian-vehicle conflict early warning device, including a transceiver, a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the pedestrian-vehicle conflict early warning method as described in the first aspect.

[0048] Fourthly, in order to achieve the above objectives, embodiments of this application provide a readable storage medium having a program or instructions stored thereon, wherein the program or instructions, when executed by a processor, implement the human-vehicle conflict early warning method as described in the second aspect.

[0049] The above-mentioned technical solution of this application has at least the following beneficial effects:

[0050] The vehicle-pedestrian conflict early warning method of this application first identifies VRUs within the Region of Interest (ROI) of Vulnerable Traffic Participants (VRUs) at an intersection, obtaining the identification result; secondly, it acquires the driving intention of vehicles located within the vehicle ROI at the intersection; then, based on the identification result and / or the driving intention, it determines the risk area and risk level; finally, it sends an early warning message based on the risk area and the risk level. In this way, it achieves a series of accurate hazard warnings for relevant traffic participants (vehicles, pedestrians, etc.) based on collision risk areas, solving the problem of insufficient accuracy and missed or false alarms in existing hazard warnings based on target states. Attached Figure Description

[0051] Figure 1 This is one of the flowcharts illustrating the pedestrian-vehicle conflict early warning method according to an embodiment of this application;

[0052] Figure 2 A schematic diagram illustrating the architecture of the vehicle-pedestrian conflict early warning method according to embodiments of this application;

[0053] Figure 3 This is a schematic diagram of the VRU ROI regions defined in the embodiments of this application;

[0054] Figure 4 This is a schematic diagram of the vehicle ROI regions defined in the embodiments of this application;

[0055] Figure 5 This is a schematic diagram illustrating regional risk identification in an embodiment of this application.

[0056] Figure 6 This is a schematic diagram illustrating the calculation of PET in an embodiment of this application;

[0057] Figure 7 This is a schematic diagram of the structure of the pedestrian-vehicle conflict early warning device according to an embodiment of this application;

[0058] Figure 8 This is a schematic diagram of the structure of the vehicle-pedestrian conflict early warning device according to an embodiment of this application. Detailed Implementation

[0059] To make the technical problems, technical solutions, and advantages of this application clearer, a detailed description will be provided below in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as particular configurations and components are provided merely to aid in a comprehensive understanding of the embodiments of this application. Therefore, those skilled in the art should understand that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Furthermore, for clarity and brevity, descriptions of known functions and structures have been omitted.

[0060] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0061] In the various embodiments of this application, it should be understood that the sequence number of each process described below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0062] In the embodiments provided in this application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information.

[0063] like Figure 1 As shown in the figure, this application provides a method for early warning of pedestrian-vehicle conflicts, including:

[0064] Step 101: Identify VRUs within the Region of Interest (ROI) of the Vulnerable Traffic Participants (VRUs) at the intersection and obtain the identification results.

[0065] In this step, roadside sensors may collect images of the intersection and analyze them to identify VRUs. The identification results should include the VRU's ROI (Region of Interest) and the number of VRUs within each ROI. Specifically, using... Figure 2 For example, roadside sensing devices include cameras, millimeter-wave radar, and lidar.

[0066] It should be noted that VRU ROI is the result of pre-dividing the geographical location of an intersection, such as dividing the pedestrian crossing of an intersection into multiple VRU ROI areas.

[0067] Step 102: Obtain the driving intentions of vehicles within the vehicle ROI located at the intersection;

[0068] The vehicle's driving intention in this step can specifically be left turn, right turn, straight ahead, or U-turn at the intersection. Among these, [the specific intention is to...]. Figure 5 For example, the ROI of a vehicle is mainly set within x meters of all lanes at the four entrances of the intersection, and is divided into left-turn lanes, right-turn lanes, U-turn lanes, and straight lanes (compound lanes are allowed).

[0069] Step 103: Based on the identification results and / or driving intention, determine the risk area and risk level;

[0070] In this step, we specifically determine whether each VRU ROI is a risk area, and if it is, we determine its risk level.

[0071] Step 104: Send an early warning message based on the risk area and the risk level.

[0072] In this step, a warning message may be sent to the relevant vehicle and / or the relevant VRU.

[0073] In this embodiment, firstly, within the Region of Interest (ROI) of the Vulnerable Traffic Participant (VRU) at the intersection, the VRU is identified, and the identification result is obtained. Secondly, the driving intention of vehicles located within the VRU ROI at the intersection is acquired. Then, based on the identification result and / or the driving intention, the risk area and risk level are determined. Finally, a warning message is sent based on the risk area and the risk level. This achieves a series of accurate hazard warnings for relevant traffic participants (vehicles, pedestrians, etc.) based on collision risk areas, solving the problem of insufficient accuracy and missed or false alarms in existing hazard warnings based on target states.

[0074] It should be noted that the subject executing the vehicle-pedestrian conflict warning method in this application embodiment can be a roadside computing device, such as a roadside edge computing device (MEC) or an artificial intelligence (AI) camera.

[0075] As an optional implementation, step 102 involves obtaining the driving intentions of vehicles within the vehicle ROI located at the intersection, including:

[0076] Based on the lane information where the vehicle is located, determine the vehicle's driving intention; or,

[0077] Based on the acquired Basic Safety Message (BSM) of the vehicle, the driving intention of the vehicle is determined.

[0078] In other words, when a vehicle has Vehicle to Everything (V2X) functionality, its driving intention can be determined based on the V2X messages it sends. When a vehicle does not have V2X functionality, its driving intention can be determined based on the detected lane it is in. Specifically, when a vehicle has V2X functionality, the vehicle sends a BSM (Browser Message Signal) to a roadside device (such as a C-V2X RSU), and the C-V2X RSU sends the vehicle's driving intention to the execution entity (such as the aforementioned roadside computing device) that implements the method of this application embodiment based on the received BSM.

[0079] As an optional implementation, step 103, based on the identification results and / or driving intention, determines the risk area and risk level, including:

[0080] Based on the identification results, the VRU ROI of the identified VRU is determined to be a risk area, and the risk level is a potential risk level.

[0081] In other words, when a VRU is identified in any VRU ROI, the VRU ROI is determined to be a potential risk area, meaning that there may be a collision risk within the VRU ROI.

[0082] Furthermore, as an optional implementation, step 103, determining the risk area and risk level based on the identification results and / or driving intention, also includes:

[0083] Based on driving intent, identify area-associated vehicles related to risk areas of potential risk levels; these area-associated vehicles are those vehicles about to enter the risk area of ​​that potential risk level. Figure 5For example, assuming that the pedestrian crossing marked "2" is a risk area with a potential risk level, the vehicles associated with the risk area with this potential risk level include straight-through vehicles in "Entrance 3" of the intersection (vehicles near the pedestrian crossing marked "5"), right-turning vehicles in "Entrance 2" of the intersection (vehicles near the pedestrian crossing marked "3"), etc.

[0084] Based on the driving information of the associated vehicles and the VRU, this step determines whether a potential risk area is a collision risk area, and the risk level if the potential risk area is indeed a collision risk area. Specifically, the driving information includes driving speed; that is, based on the vehicle's and the VRU's driving information, it is determined whether the two vehicles will meet in the potential risk area. If they do meet, a collision will occur, and the potential risk area will be considered a collision risk area.

[0085] As a specific implementation method, based on the driving information of the region-associated vehicles and the driving information of the VRU, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0086] (1) Based on the driving intention and the driving speed of the vehicle associated with the region, obtain the first moment when the vehicle associated with the region enters the risk area of ​​the potential risk level; and / or, based on the identification result, obtain the second moment when the VRU leaves the risk area of ​​the potential risk level.

[0087] In this step, the first moment can be determined based on the distance between the vehicle's position and the position where it enters the risk area of ​​the potential risk level, and the driving speed; the second moment refers to the moment when all VRUs in the potential collision risk area leave the potential collision risk area, which can be determined based on the VRU's driving information (which may be a pre-set empirical value) and the distance between the VRU's current position and the position where the VRU leaves the potential collision risk area.

[0088] (2) Based on at least one of the first moment, the second moment and the driving speed, determine whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

[0089] In this step, it is specifically determined whether a collision will occur between the associated vehicle and the identified VRU in the area and the degree of collision based on at least one of the first moment, the second moment and the form speed, thereby determining whether the risk area of ​​the potential risk level is a collision risk area and the risk level of the collision risk area.

[0090] As a specific implementation, based on at least one of the first moment, the second moment, and the driving speed, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0091] (1) Determine the post-encroachment time (PET) based on the difference between the first moment and the second moment;

[0092] PET refers to the time difference between two vehicles arriving at a specified cross-section; for example... Figure 6 As shown, PET is the difference between the time when vech1 enters the collision zone (last-entrance-time) and the time when vech2 leaves the collision zone (first-exit-time). In this step, PET refers to the time difference between the associated vehicle and the identified VRU arriving at a specified section in this area; that is, PET is the difference between the first time and the second time.

[0093] (2) When PET is less than the first value and the driving speed is between the first speed and the second speed, the risk area with potential risk level is determined as the collision risk area and the risk level is the first level; wherein the first speed is less than the second speed;

[0094] (3) When PET is between the first value and the second value, and the driving speed is between the first speed and the second speed, the risk area of ​​the potential risk level is determined as the collision risk area, and the risk level is the second level; wherein the first value is less than the second value;

[0095] (4) When PET is less than the second value and the driving speed is less than the first speed, the risk area with potential risk level is determined as the collision risk area and the risk level is the third level.

[0096] It should be noted that the first level is lower than the second level, and the second level is lower than the third level.

[0097] As another specific implementation, based on at least one of the first moment, the second moment, and the driving speed, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0098] (1) Determine the time to collision (TTC) based on the difference between the first moment and the current moment; in this step, TTC refers to the time when this vehicle will collide with the vehicle in front.

[0099] It should be noted that when it is impossible to predict when the identified VRU will leave the risk area of ​​the potential risk level, assuming that the VRU is always in the risk area of ​​the potential risk level, then the risk of collision begins after the area-associated vehicle enters the risk area of ​​the potential risk level.

[0100] (2) When the TTC is less than the first value and the driving speed is between the first speed and the second speed, the risk area of ​​the potential risk level is determined as the collision risk area, and the risk level is the first level, where the first speed is less than the second speed;

[0101] (3) When the TTC is between the first value and the second value, and the driving speed is between the first speed and the second speed, the risk area of ​​the potential risk level is determined as the collision risk area, and the risk level is the second level, where the first value is less than the second value.

[0102] (4) When the TTC is less than the second value and the driving speed is less than the first speed, the risk area of ​​the potential risk level is determined as the collision risk area and the risk level is the third level.

[0103] It should be noted that the first level is lower than the second level, and the second level is lower than the third level.

[0104] As another specific implementation, based on at least one of the first moment, the second moment, and the driving speed, it is determined whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including:

[0105] When the driving speed is greater than the second speed, the risk area with the potential risk level is determined as the collision risk area, and the risk level is the second level.

[0106] When the driving speed is greater than the third speed, the risk area with potential risk level is determined as the collision risk area, and the risk level is the first level, where the third speed is greater than the second speed.

[0107] It should be noted that the first level is lower than the second level.

[0108] The following table illustrates the relationship between PET, TTC, driving speed, and risk level in the above specific implementation methods:

[0109] Table 1: Determination of Collision Risk Zones and Risk Levels

[0110]

[0111] In Table 1, the first value is 5 seconds, the second value is 3 seconds, the first speed is 10 km / h, the second speed is the maximum speed limit * 1.1, the third speed is the maximum speed limit * 1.5, the first level is general, the second level is emergency, and the third level is lethal.

[0112] In other words, this application determines a potential risk area as a collision risk area based on the boundary of the potential risk area (rather than the VRU target) and the collision risk of its associated vehicles, if the conditions shown in Table 1 above are met.

[0113] As an optional implementation, step 103 involves sending an early warning message based on the risk area and risk level, including at least one of the following:

[0114] (1) Send a first warning message to the roadside vehicle warning device corresponding to the risk area, the first warning message being used to instruct the roadside vehicle warning device to output a first warning message related to the risk level of the risk area;

[0115] It should be noted here that roadside vehicle warning devices are typically installed on the side of the entrance lanes at intersections, with one device deployed at each of the four entrances, such as... Figure 5 The vehicle warning devices shown are 1 to 4. These devices typically take the form of LED information boards, and can be supplemented with light strips or other auxiliary warning devices. Warning methods include text, color, and flashing, corresponding to the risk level of the area.

[0116] like Figure 5 As shown, assuming the pedestrian crossing marked "1" is a risk area, the roadside vehicle warning device corresponding to this risk area is... Figure 5 The "Vehicle Warning Device 1" in the diagram; assuming the pedestrian crossing marked "2" is a risk area, then the roadside vehicle warning device corresponding to this risk area is... Figure 5 The "Vehicle Warning Device 2" and "Vehicle Warning Device 3" are mentioned.

[0117] (2) Send a second warning message to the roadside VRU alert device related to the risk area, the second warning message being used to instruct the roadside VRU alert device to output a second warning message related to the risk level of the risk area;

[0118] It should be noted that roadside VRU alert devices are typically installed on both sides of pedestrian crossings at intersections, with two devices deployed at each crosswalk. Figure 5 The VRU early warning devices 1-4 are shown. The device forms include audible and visual alarms, LED / LCD screens, and light strips as auxiliary reminders. The reminder methods include text, color, flashing, voice / prompt sounds, and corresponding risk levels for the area.

[0119] like Figure 5As shown, assuming the pedestrian crossing marked "1" is a risk area, the roadside vehicle warning device corresponding to this risk area is... Figure 5 The "VRU warning device 1" in the text; assuming the pedestrian crossing marked "2" is a risk area, then the roadside vehicle warning device corresponding to this risk area is... Figure 5 "VRU early warning device 2" in the middle.

[0120] (3) Send a third warning message to the roadside unit (RSU), which is used to instruct the RSU to send a third warning message related to the risk level of the risk area to the human machine interface (HMI) device of the area-associated vehicle, and / or instruct the RSU to send a safety warning message to the HMI device of the collision risk-associated vehicle; wherein the area-associated vehicle is the vehicle that is about to enter the risk area, and the collision risk-associated vehicle is the vehicle that is directly associated with the collision event.

[0121] It should be noted that the RSU and HMI can communicate via the PC5 interface; the HMI device for connected vehicles includes pre-installed / aftermarket human-machine interaction devices or combinations of devices that support connected communication functions. One device is deployed in each connected vehicle. The device forms include screens and speakers, and the reminder methods include text, video, animation, voice / prompt sounds, etc.

[0122] like Figure 5 As shown, assuming the pedestrian walkway marked "1" is a risk zone, the associated vehicles in that zone are... Figure 5 Two vehicles in the lane marked "Import 1"; assuming the pedestrian crossing marked "2" is a risk area, the associated vehicles in that area are... Figure 5 Vehicles in the lane marked "Import 2" and vehicles in the lane marked "Import 3"

[0123] As a specific implementation, the first warning message includes at least one of the following: the area code of the risk area, the risk level of the risk area, and the number of VRUs in the risk area. That is, for roadside vehicle alert devices, the necessary fields for data interaction with roadside computing devices include, but are not limited to: risk area, area risk level (potential, general, urgent, fatal), and number of at-risk pedestrians.

[0124] As another specific implementation, the second warning message includes at least one of the following: the area code of the risk area, the risk level of the risk area, information on vehicles associated with the risk area, and information on vehicles associated with collision risk. That is, for roadside VRU alert devices, the necessary fields for data interaction with roadside computing devices include, but are not limited to: risk area, area risk level (potential, general, urgent, lethal), vehicles associated with the area (whether connected, vehicle type, location, speed, orientation, etc.), and vehicles associated with collision risk (whether connected, vehicle type, location, speed, orientation, etc.).

[0125] As another specific implementation method, the third early warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, the center point of the risk area, the outer boundary of the risk area, the number of VRUs in the risk area, information on vehicles associated with the risk area, and information on vehicles associated with collision risk. That is, for connected vehicle HMI devices, the necessary fields for data interaction via PC5 messages include, but are not limited to: MAP message: risk area number, risk area level (potential / general / severe / fatal), area center point, area outer boundary, number of VRUs, vehicles associated with the area (whether connected, vehicle type, location, speed, orientation, etc.), vehicles associated with collision risk (whether connected, license plate, vehicle type, location, speed, orientation, collision risk level, TTC / PET to the risk area), etc., and the sending scope is vehicles that are about to pass through this area (i.e., vehicles associated with the area).

[0126] Furthermore, as an optional implementation, the method also includes:

[0127] The pedestrian walkway at the intersection is divided into multiple VRU ROIs, where each VRU ROI is the pedestrian walkway directly opposite the road entering or exiting the intersection.

[0128] by Figure 3 For example, the pedestrian crossing at the intersection is divided into eight VRU ROIs (Vehicle-Round Entities). Figure 3 In this embodiment of the application, when a VRU is identified, it is determined which VRU ROI the identified VRU is located in.

[0129] This application proposes to construct a series of facilities along the roadside to address the early warning problem of pedestrian-vehicle conflicts at intersections. The overall technical architecture is as follows: Figure 2As shown. From an equipment perspective, it includes roadside sensing devices, roadside computing devices, C-V2X RSUs, vehicle warning devices, and VRU warning devices. Key technologies in the architecture include: VRU target perception, vehicle target perception, risk event identification, and precise notification strategies. In this embodiment, the execution entity is a roadside computing device, which includes: a VRU target perception module, a vehicle target perception module, an area risk identification module, and a precise notification strategy module. Specifically, the VRU target perception module is used for: VRU ROI area setting, VRU target detection and tracking, and VRU area resolution; the vehicle target perception module is used for: vehicle ROI area setting, vehicle target detection and tracking, and vehicle driving intention identification; the area risk identification module is used for: potential risk area identification, collision risk area identification and classification; and the precise notification strategy module is used for: area risk event generation, roadside vehicle warning device notification strategy, connected vehicle HMI device notification strategy, and roadside VRU warning device notification strategy. Furthermore, the roadside computing device also interacts with roadside sensing devices, roadside C-V2X RSUs, roadside vehicle warning devices, and roadside VRU warning devices; the roadside C-V2X... The RSU also interacts with the HMI device of the connected vehicle via the PC5 interface; among which, roadside sensing devices include cameras, millimeter-wave radar, lidar, etc.; the roadside C-V2X RSU is used for PC5 air interface message encapsulation, the connected vehicle HMI device is used for PC5 message reception and parsing, as well as sound, light, and text alerts; the roadside vehicle warning device is used for sound, light, and text alerts; and the roadside VRU warning device is used for sound, light, and text alerts.

[0130] Below, with Figure 2 Based on the architecture, specific examples of the pedestrian-vehicle conflict early warning method in this application embodiment are described below:

[0131] 1) The roadside sensing equipment senses the VRUs at the intersection and sends the sensing results to the VRU target sensing (module) of the roadside computing equipment;

[0132] 2) VRU target perception

[0133] The main functions of VRU target perception include VRU ROI region setting, VRU target detection and tracking, and VRU region resolution. The core of VRU target perception is the regional division of the VRU's perception area. This is achieved through ROI division within the target perception module, specifically as follows: Figure 3 As shown, the pedestrian crossing at the intersection is divided as follows: Figure 3 The diagram shows eight regions, numbered 1 to 8. The result of VRU target perception is the identification of all regions to which the VRU belongs, and the region number is sent to the region risk identification (module).

[0134] 3) Vehicle target perception

[0135] The main functions of vehicle target perception include vehicle ROI region setting, vehicle target detection and tracking, and vehicle trajectory prediction. Among these, for example... Figure 4 and 5 As shown, the vehicle ROI area is mainly set within x meters of all lanes at the four entrances of the intersection, and divided into left-turn lanes, right-turn lanes, U-turn lanes, and straight-ahead lanes (combined lanes are allowed). Based on vehicle target detection and tracking, the vehicle's driving intention is inferred from its ROI area. For intelligent connected vehicles, the driving intention can be sent to the C-V2X RSU via the onboard unit (OBU). Finally, the vehicle target perception module sends the vehicle targets and intentions within the ROI to the area risk identification module.

[0136] 4) Regional risk identification

[0137] 4.1) Identification of potential risk areas. For VRU ROI areas d i ∈[d1,d2,...,d8], if there is a decision region d i If there is a VRU target, then set region d. i This is a potential risk area.

[0138] 4.2) Identification of vehicles associated with potential risk areas. Determine all vehicles that will enter area d. i The area's roads and driveways. For example... Figure 5 As shown, VRU ROI regions 1, 3, 5, and 7 are related to imports 1, 2, 3, and 4, respectively, while VRU ROI regions 2, 4, 6, and 8 are related to all imports. Then, the driving intentions of all vehicles at the relevant imports are analyzed to determine which vehicle will be entering port d. i The vehicle as d i Vehicles associated with a specific region are denoted as D = V(d i )={v1,..,v n Taking VRU ROI regions 1 and 2 as examples where pedestrian traffic exists, the vehicle filtering for region association is shown in the table below:

[0139] Table 2: Potential Risk Areas and Associated Vehicles

[0140]

[0141]

[0142] 4.3) Collision risk event detection. For all current potential risk areas d i The post-PET, TTC, and driving speed will be used as the basis for determining risk events. Specifically, when area d... iWhen a VRU target enters, predict the second time t when all VRUs leave. ped-exit PET+ driving speed is used as the basis for judging risk events. If the departure time of the VRU cannot be predicted, then area d can be used. i The area is considered as occupied, and TTC is used as the basis for judging risk events.

[0143] 4.3.1) For region d i The set of vehicles associated with a region is D = V(d i )={v1,..,v n Using the vehicle's bounding box as its outer border, calculate the entry area d for all vehicles. i The moment t vech-entrance .

[0144] 4.3.2) When the time of pedestrian departure can be predicted, PET = t vech-entrance -t ped-exit When the VRU exit event cannot be predicted, TTC = t vech-entrance .

[0145] 4.3.3) For potential risk area d i Any associated vehicle v j If PET / TTC and driving speed meet the conditions, then the collision area d i The area is upgraded to a collision risk zone, and collision warning events and corresponding levels are generated as shown in Table 1 above.

[0146] 5) Send warning messages

[0147] This invention can use various means to notify the risk level of a region using different early warning devices. As mentioned above, the early warning devices include roadside vehicle alert devices, roadside VRU alert devices, and connected vehicle HMI devices.

[0148] In other words, based on potential risk areas and collision risk areas, precise notifications are sent to associated vehicles and VRUs. There are three notification methods: HMI notification for connected vehicles, notification from roadside vehicle warning devices, and notification from roadside VRU warning devices. For connected vehicle HMI devices, messages about potential risk areas need to notify the set of associated vehicles in the area, D = V(d i )={v1,..,v n}; Collision risk area message notification directly triggers collision risk for the vehicle v j The notification will be sent to other associated vehicles in other areas via message. Taking VRU areas 1 and 2 as examples, the notification strategy is based on Table 3 below.

[0149] Table 3: Precise Notification Strategy

[0150]

[0151]

[0152] Among them, the necessary fields for data interaction between roadside vehicle warning devices and roadside computing devices include, but are not limited to: risk area, area risk level (potential, general, urgent, fatal), and number of at-risk pedestrians.

[0153] The necessary fields for data interaction between roadside VRU alert devices and roadside computing devices include, but are not limited to: risk area, area risk level (potential, general, emergency, fatal), risk-associated vehicles (whether connected, vehicle type, location, speed, orientation, etc.), and collision risk-associated vehicles (whether connected, vehicle type, location, speed, orientation, etc.).

[0154] For HMI devices in connected vehicles, the necessary fields for data interaction via PC5 messages include, but are not limited to: MAP messages: risk area number, risk area level (potential / general / critical / fatal), area center point, area outer boundary, VRU personnel, area-related vehicles (whether connected, vehicle type, location, speed, orientation, etc.), collision risk-related vehicles (whether connected, license plate, vehicle type, location, speed, orientation, collision risk level, TTC / PET to the risk area), etc., with the sending scope being vehicles about to pass through this area. Additionally, safety warning information can be sent to vehicles that directly pose a collision risk.

[0155] In the vehicle-pedestrian conflict warning method of this application embodiment, the intersection is divided into multiple VRU identification areas, which can identify whether there are VRU targets in the area and determine whether it is a potential risk area. On this basis, by identifying the relationship between vehicles and these VRU areas, the collision risk between vehicles and VRUs is identified, and the area is set as a collision risk area of ​​a certain level. Based on the collision risk areas, a series of precise notification strategies are designed to provide relevant notifications based on roadside vehicle reminder devices, roadside VRU reminder devices, and intelligent connected HMI devices. In this process, for the direct communication between C-V2X RSU and intelligent connected vehicles, the message sent must include the following information: the potential risk area with VRU activity, specifically including the area number, area risk level (potential), area center point, area outer boundary, number of VRUs, etc., and the sending range is vehicles that are about to pass through this area (hereinafter referred to as area-related vehicles). When this potential risk area detects a collision risk, it is also necessary to send information such as the area risk level (general / serious / fatal), directly related vehicles, etc., the sending range includes area-related vehicles, and send safety warning information to the vehicle that directly causes the collision risk. This regional VRU identification and notification granularity can reduce false alarms and missed alarms caused by target-level conflict detection (pedestrian identification and prediction are difficult and have a limited scope of applicability). It summarizes the reminders of risk targets into early warnings of risk areas, thereby improving the effectiveness and practicality of safety early warnings.

[0156] like Figure 7 As shown in the figure, this application embodiment also provides a pedestrian-vehicle conflict warning device, including:

[0157] The identification module 701 is used to identify VRUs within the Region of Interest (ROI) of Vulnerable Traffic Participants (VRUs) at an intersection and obtain identification results.

[0158] The acquisition module 702 is used to acquire the driving intention of vehicles within the vehicle ROI located at the intersection;

[0159] The first determining module 703 is used to determine the risk area and risk level based on the identification result and / or the driving intention;

[0160] The sending module 704 is used to send a warning message based on the risk area and the risk level.

[0161] Optionally, the acquisition module 702 is specifically used for:

[0162] Based on the lane information where the vehicle is located, determine the vehicle's driving intention; or,

[0163] Based on the acquired Basic Safety Message (BSM) of the vehicle, the driving intention of the vehicle is determined.

[0164] Optionally, the first determining module 703 is specifically used for:

[0165] Based on the identification results, the VRU ROI of the identified VRU is determined to be a risk area, and the risk level is a potential risk level.

[0166] Optionally, the device further includes:

[0167] The second determining module is used to determine, based on the driving intention, a region-associated vehicle related to a risk area of ​​a potential risk level, wherein the region-associated vehicle is a vehicle that is about to enter the risk area of ​​the potential risk level.

[0168] The third determining module is used to determine whether the risk area of ​​the potential risk level is a collision risk area based on the driving information of the vehicle associated with the region and the driving information of the VRU, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

[0169] Optionally, the third determining module includes:

[0170] The acquisition submodule is used to obtain, based on the driving intention and the obtained driving speed of the area-associated vehicle, the first moment when the area-associated vehicle enters the risk area of ​​the potential risk level; and / or, based on the identification result, the second moment when the VRU leaves the risk area of ​​the potential risk level.

[0171] The determination submodule is used to determine whether the risk area of ​​the potential risk level is a collision risk area based on at least one of the first time, the second time, and the driving speed, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

[0172] Optionally, the determining submodule includes:

[0173] The first determining unit is used to determine the post-intrusion time PET based on the difference between the first time and the second time.

[0174] The second determining unit is configured to determine the risk area of ​​the potential risk level as a collision risk area and the risk level as the first level when the PET is less than a first value and the driving speed is between a first speed and a second speed; wherein the first speed is less than the second speed.

[0175] The third determining unit is configured to determine the risk area of ​​the potential risk level as a collision risk area and the risk level as a second level when the PET is between the first value and the second value, and the driving speed is between the first speed and the second speed; wherein the first value is less than the second value.

[0176] The fourth determining unit is used to determine the risk area of ​​the potential risk level as a collision risk area and the risk level as the third level when the PET is less than the second value and the driving speed is less than the first speed.

[0177] Optionally, the determining submodule includes:

[0178] The fifth determining unit is used to determine the collision time TTC based on the difference between the first time and the current time.

[0179] The sixth determining unit is used to determine the risk area of ​​the potential risk level as a collision risk area and the risk level as the first level when the TTC is less than the first value and the driving speed is between the first speed and the second speed;

[0180] The seventh determining unit is configured to determine the risk area of ​​the potential risk level as a collision risk area and the risk level as a second level when the TTC is between the first value and the second value, and the driving speed is between the first speed and the second speed; wherein the first value is less than the second value.

[0181] The eighth determining unit is used to determine the risk area of ​​the potential risk level as a collision risk area and the risk level as the third level when the TTC is less than the second value and the driving speed is less than the first speed.

[0182] Optionally, the determining submodule includes:

[0183] The ninth determining unit is used to determine, when the driving speed is greater than the second speed, the risk area of ​​the potential risk level is a collision risk area and the risk level is the second level;

[0184] The tenth determining unit is used to determine, when the driving speed is greater than the third speed, the risk area of ​​the potential risk level is a collision risk area and the risk level is the first level, wherein the third speed is greater than the second speed.

[0185] Optionally, the sending module 704 is specifically configured to perform at least one of the following:

[0186] Send a first warning message to the roadside vehicle alert device corresponding to the risk area. The first warning message is used to instruct the roadside vehicle alert device to output a first warning message related to the risk level of the risk area.

[0187] A second warning message is sent to the roadside VRU alert device associated with the risk area, the second warning message instructing the roadside VRU alert device to output a second warning message related to the risk level of the risk area;

[0188] A third warning message is sent to the roadside unit (RSU), which instructs the RSU to send a third warning message related to the risk level of the risk area to the human-machine interface (HMI) device of the area-associated vehicle, and / or instructs the RSU to send a safety warning message to the HMI device of the collision-risk-associated vehicle; wherein the area-associated vehicle is a vehicle about to enter the risk area, and the collision-risk-associated vehicle is a vehicle directly associated with the collision event.

[0189] Optionally, the first warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, and the number of VRUs in the risk area.

[0190] Optionally, the second warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, information of vehicles associated with the risk area, and information of vehicles associated with the collision risk.

[0191] Optionally, the third warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, the center point of the risk area, the outer boundary of the risk area, the number of VRUs in the risk area, information on area-associated vehicles related to the risk area, and information on collision risk-associated vehicles.

[0192] Furthermore, the device also includes:

[0193] A partitioning module is used to divide the pedestrian walkway of the intersection into multiple VRU ROIs, wherein each VRU ROI is the pedestrian walkway directly opposite the road entering or exiting the intersection.

[0194] It should be noted that the above-mentioned pedestrian-vehicle conflict warning device provided in this application embodiment can realize all the method steps implemented in the above-mentioned pedestrian-vehicle conflict warning method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0195] like Figure 8 As shown, this application embodiment also provides a pedestrian-vehicle conflict early warning device, including a transceiver 810, a processor 800, a memory 820, and a program or instructions stored in the memory 820 and executable on the processor 800; when the processor 800 executes the program or instructions, it implements the above-mentioned pedestrian-vehicle conflict early warning method.

[0196] The transceiver 810 is used to receive and send data under the control of the processor 800.

[0197] Among them, Figure 8 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 800) and memory (memory 820). The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 810 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 can store data used by the processor 800 during operation.

[0198] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a computer program instructing the relevant hardware to implement them. The computer program includes instructions to perform some or all of the steps of the above methods; and the computer program can be stored in a readable storage medium, which can be any form of storage medium.

[0199] In addition, this application embodiment also provides a computer-readable storage medium storing a program. When executed by a processor, this program implements the various processes of the pedestrian-vehicle conflict warning method embodiment described above and achieves the same technical effect. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0200] Furthermore, it should be noted that in the apparatus and method of this application, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of this application. Moreover, the steps performing the above series of processes can naturally be executed in the order described or in chronological order, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of this application can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of this application.

[0201] Therefore, the object of this application can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of this application can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes this application, and a storage medium storing such a program product also constitutes this application. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future.

[0202] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0203] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles described in this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for early warning of pedestrian-vehicle conflicts, characterized in that, include: Within the Region of Interest (ROI) of Vulnerable Traffic Participants (VRUs) at the intersection, VRUs are identified, and identification results are obtained. The identification results include the VRU ROI regions where the identified VRUs are located, and the number of VRUs within each VRU ROI region. Obtain the driving intention of vehicles within the vehicle ROI located at the intersection; Based on the identification results and / or the driving intention, determine the risk area and risk level; including: based on the identification results, determine that the VRU ROI where the VRU is identified is a risk area, and the risk level is a potential risk level; based on the driving intention, determine the area-associated vehicle related to the risk area of ​​the potential risk level, the area-associated vehicle being a vehicle about to enter the risk area of ​​the potential risk level; based on the driving information of the area-associated vehicle and the driving information of the VRU, determine whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area; wherein, the risk level is the risk level of the risk area; Based on the risk area and the risk level, send an early warning message, including at least one of the following: A first warning message is sent to the roadside vehicle alert device corresponding to the risk area. The first warning message is used to instruct the roadside vehicle alert device to output first warning information related to the risk level of the risk area. The first warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, and the number of VRUs in the risk area. A second warning message is sent to a roadside VRU alert device associated with the risk area. The second warning message instructs the roadside VRU alert device to output a second warning message related to the risk level of the risk area. The second warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, information of vehicles associated with the risk area, and information of vehicles associated with the collision risk. A third warning message is sent to the Roadside Unit (RSU), which instructs the RSU to send a third warning message related to the risk level of the risk area to the human-machine interface (HMI) device of the area-associated vehicle, and / or instructs the RSU to send a safety warning message to the HMI device of the collision-risk-associated vehicle; wherein the area-associated vehicle is a vehicle about to enter the risk area, and the collision-risk-associated vehicle is a vehicle directly associated with a collision event; wherein the third warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, the center point of the risk area, the outer boundary of the risk area, the number of VRUs in the risk area, the information of the area-associated vehicle related to the risk area, and the information of the collision-risk-associated vehicle.

2. The method according to claim 1, characterized in that, Obtaining the driving intentions of vehicles within the vehicle ROI located at the intersection includes: Based on the lane information where the vehicle is located, determine the vehicle's driving intention; or, Based on the acquired Basic Safety Message (BSM) of the vehicle, the driving intention of the vehicle is determined.

3. The method according to claim 1, characterized in that, Based on the driving information of the vehicles associated with the region and the driving information of the VRU, determine whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, including: Based on the driving intention and the obtained driving speed of the area-associated vehicle, the first moment when the area-associated vehicle enters the risk area of ​​the potential risk level is obtained; and / or, based on the identification result, the second moment when the VRU leaves the risk area of ​​the potential risk level is obtained; Based on at least one of the first time point, the second time point, and the driving speed, determine whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

4. The method according to claim 3, characterized in that, Determining whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, based on at least one of the first time point, the second time point, and the driving speed, includes: The post-intrusion time PET is determined based on the difference between the first time point and the second time point; When the PET value is less than a first value and the driving speed is between a first speed and a second speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is first level; wherein the first speed is less than the second speed; When the PET value is between the first and second values, and the driving speed is between the first and second speeds, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is the second level; wherein the first value is less than the second value; When the PET value is less than the second value and the driving speed is less than the first speed, the risk area of ​​the potential risk level is determined to be a collision risk area, and the risk level is the third level.

5. The method according to claim 3, characterized in that, Determining whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, based on at least one of the first time point, the second time point, and the driving speed, includes: The collision time TTC is determined based on the difference between the first time point and the current time point. When the TTC is less than a first value and the driving speed is between a first speed and a second speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is first level, wherein the first speed is less than the second speed; When the TTC is between the first value and the second value, and the driving speed is between the first speed and the second speed, the risk area of ​​the potential risk level is determined to be a collision risk area, and the risk level is the second level, wherein the first value is less than the second value; When the TTC is less than the second value and the driving speed is less than the first speed, the risk area of ​​the potential risk level is determined to be a collision risk area, and the risk level is the third level.

6. The method according to claim 3, characterized in that, Determining whether the risk area of ​​the potential risk level is a collision risk area, and the risk level when the risk area of ​​the potential risk level is a collision risk area, based on at least one of the first time point, the second time point, and the driving speed, includes: When the driving speed is greater than the second speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is the second level; When the driving speed is greater than the third speed, the risk area of ​​the potential risk level is determined as a collision risk area, and the risk level is the first level, wherein the third speed is greater than the second speed.

7. A pedestrian-vehicle conflict early warning device, characterized in that, include: The identification module is used to identify VRUs within the Region of Interest (ROI) of VRUs at an intersection and obtain identification results; wherein, the identification results include the VRU ROI region where the identified VRU is located, and the number of VRUs in each VRU ROI region; The acquisition module is used to acquire the driving intentions of vehicles within the vehicle ROI located at the intersection. The first determining module is used to determine a risk area and a risk level based on the identification result and / or the driving intention; wherein the risk level is the risk level of the risk area; A sending module is configured to send a warning message based on the risk area and the risk level; wherein, the sending module is specifically configured to perform at least one of the following: A first warning message is sent to the roadside vehicle alert device corresponding to the risk area. The first warning message is used to instruct the roadside vehicle alert device to output first warning information related to the risk level of the risk area. The first warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, and the number of VRUs in the risk area. A second warning message is sent to a roadside VRU alert device associated with the risk area. The second warning message instructs the roadside VRU alert device to output a second warning message related to the risk level of the risk area. The second warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, information of vehicles associated with the risk area, and information of vehicles associated with the collision risk. A third warning message is sent to the Roadside Unit (RSU), which instructs the RSU to send a third warning message related to the risk level of the risk area to the human-machine interface (HMI) device of the area-associated vehicle, and / or instructs the RSU to send a safety warning message to the HMI device of the collision-risk-associated vehicle; wherein the area-associated vehicle is a vehicle about to enter the risk area, and the collision-risk-associated vehicle is a vehicle directly associated with a collision event; wherein the third warning message includes at least one of the following: the area number of the risk area, the risk level of the risk area, the center point of the risk area, the outer boundary of the risk area, the number of VRUs in the risk area, the information of the area-associated vehicle related to the risk area, and the information of the collision-risk-associated vehicle; Specifically, the first determining module is used to: determine, based on the identification result, that the VRU ROI to which the VRU was identified is a risk area and that the risk level is a potential risk level; The device further includes: The second determining module is used to determine, based on the driving intention, a region-associated vehicle related to a risk area of ​​a potential risk level, wherein the region-associated vehicle is a vehicle that is about to enter the risk area of ​​the potential risk level. The third determining module is used to determine whether the risk area of ​​the potential risk level is a collision risk area based on the driving information of the vehicle associated with the region and the driving information of the VRU, and the risk level when the risk area of ​​the potential risk level is a collision risk area.

8. A pedestrian-vehicle conflict early warning device, comprising a transceiver, a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the human-vehicle conflict early warning method as described in any one of claims 1 to 6.

9. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the human-vehicle conflict early warning method as described in any one of claims 1 to 6.

Images