A road cooperative warning method and device, electronic equipment and storage medium

Abstract

The application provides a road cooperative warning method and device, electronic equipment and storage medium. The method comprises the following steps: determining a signal state of a target traffic signal lamp, the target traffic signal lamp being a signal lamp arranged at a target intersection and used for guiding traffic operation of a first mobile object in a first passing direction; determining a first motion state of the first mobile object under the signal state; determining a second motion state of a second mobile object under the signal state, the second mobile object being a mobile object on a driving road in a second passing direction at the target intersection, and traffic operation indications of the traffic signal lamps in the first passing direction and the second passing direction being opposite; and based on the first motion state of the first mobile object and the second motion state of the second mobile object under the signal state, determining and executing corresponding warning measures to cooperatively warn traffic accidents by using information of vehicles, pedestrians and traffic signal lamps on the road.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic safety, in particular to a road cooperative warning method and device, an electronic device and a storage medium. BACKGROUND

[0002] The vehicle-road cooperative system is the latest development direction of intelligent transportation, which adopts advanced wireless communication and new generation Internet technology, and implements dynamic real-time information interaction between vehicles and roads in all directions, and carries out vehicle active safety control and road cooperative management on the basis of full-time and space dynamic traffic information collection and fusion, aiming to realize effective cooperation of man, vehicle and road. The existing pedestrian crossing warning method in the vehicle-road cooperative system is mainly based on the traffic signal light state, and the roadside broadcast equipment reminds pedestrians to prohibit passing according to the current traffic light state, and the crossing action is mainly controlled by the subjective consciousness of pedestrians, which cannot be associated with the driving state of vehicles at the intersection, and cannot prevent accidents from happening from the aspects of pedestrians and vehicles. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a road cooperative warning method, device, electronic device and storage medium, which cooperates with the information of vehicles, pedestrians and traffic signal lights on the road to warn the occurrence of traffic accidents.

[0004] In a first aspect, the present application provides a road cooperative warning method, which comprises determining the signal state of a target traffic signal light, the target traffic signal light being a signal light arranged at a target intersection for directing the traffic operation of a first moving object in a first passing direction; determining the first movement state of the first moving object under the signal state; determining the second movement state of a second moving object under the signal state, the second moving object being a moving object on the driving road in a second passing direction at the target intersection, and the traffic operation indication of the traffic signal light in the first passing direction and the second passing direction being opposite; determining and executing corresponding warning measures based on the first movement state of the first moving object and the second movement state of the second moving object under the signal state.

[0005] Preferably, the target intersection is formed by a plurality of driving roads, and before the step of determining the signal state of the target traffic signal, the method further comprises: acquiring monitoring data collected by all target road monitoring devices, each target road monitoring device being arranged on a driving road forming the target intersection to collect monitoring data within a preset range on the driving road; for each monitoring data, identifying a pedestrian or a vehicle moving in a first passing direction on the driving road corresponding to the monitoring data; for each identified pedestrian or vehicle, determining a distance value between the pedestrian or vehicle and a base point of the target intersection based on scanning data collected by the target millimeter wave radar; for each identified pedestrian or vehicle, when the distance value between the pedestrian or vehicle and the base point of the target intersection is less than or equal to a standard distance value, determining the pedestrian or vehicle as the first moving object, and performing the step of determining the signal state of the target traffic signal.

[0006] Preferably, for each monitoring data, the pedestrian moving in the first passing direction on the driving road corresponding to the monitoring data is identified by: based on each frame of monitoring image of the monitoring data, extracting position coordinates of the skeletal joints of each pedestrian in the monitoring image; for each pedestrian, determining changes in the position coordinates of the skeletal joints of the pedestrian in a preset number of continuous monitoring images, determining a movement distance and a movement speed of the pedestrian, and based on the movement distance of the pedestrian, determining a movement direction of the pedestrian, when it is determined that the movement direction of the pedestrian is in the same direction as the first passing direction and the movement speed is greater than zero, it is determined that the pedestrian moving in the first passing direction on the driving road corresponding to the monitoring data is identified.

[0007] Preferably, the first movement state includes a crossing action has occurred and a crossing action has not occurred, and the step of determining the first movement state of the first moving object in the signal state specifically comprises: acquiring a real-time position coordinate of the first moving object, determining whether the current position coordinate of the first moving object is located within a first preset area; when the real-time position coordinate of the first moving object is located within the first preset area, it is determined that the movement state of the first moving object is that the crossing action has occurred; when the real-time position coordinate of the first moving object is located outside the first preset area, it is determined that the movement state of the first moving object is that the crossing action has not occurred.

[0008] Preferably, when the first mobile object is a pedestrian and the second mobile object is a vehicle, the second motion state includes a safe state and a dangerous state, and the second motion state of the vehicle is determined by: obtaining target monitoring data corresponding to a target driving road forming the target intersection, the target driving road being a driving road in the second passing direction; based on the target monitoring data, obtaining real-time position coordinates of all moving vehicles, and determining whether the real-time position coordinates of the vehicle are located within the second preset area; when the real-time position coordinates of at least one vehicle are located within the second preset area, it is determined that the second motion state of the vehicle is a dangerous state; and when no real-time position coordinates of the vehicle are located within the second preset area, it is determined that the second motion state of the vehicle is a safe state.

[0009] Preferably, the signal state includes a no-passing state and a passing state, when the first mobile object is a pedestrian and the second mobile object is a vehicle, the corresponding warning measures are determined and executed by: when it is determined that the pedestrian is in the passing state and the vehicle is in the safe state, no warning measures are executed; when it is determined that the pedestrian is in the passing state and the vehicle is in the dangerous state, if the pedestrian crossing action has occurred, the second warning measure is determined and executed, and if the pedestrian crossing action has not occurred, the first warning measure is determined and executed; when it is determined that the pedestrian is in the no-passing state and the vehicle is in the safe state, if the pedestrian crossing action has not occurred, no warning measures are executed, and if the pedestrian crossing action has occurred, the first warning measure is determined and executed; and when it is determined that the pedestrian is in the no-passing state and the vehicle is in the dangerous state, if the pedestrian crossing action has not occurred, no warning measures are executed, and if the pedestrian crossing action has occurred, the second warning measure is determined and executed.

[0010] Preferably, the first warning measure includes playing warning information through a broadcast set at the target intersection, playing warning information through an induction screen set at the target intersection, and sending warning information to a vehicle terminal in the third preset area; the second warning measure includes playing warning information through a broadcast set at the target intersection, playing warning information through an induction screen set at the target intersection, sending warning information to a vehicle terminal in the third preset area, setting all traffic signal lights on the target intersection to display yellow flashing or red light, and the third preset area is larger than the first preset area and the second preset area.

[0011] In a second aspect, the present application provides a road cooperative warning device, the device comprising:

[0012] a signal determination module for determining the signal state of the target traffic signal light, the target traffic signal light being a signal light set at the target intersection for directing the traffic operation of the first mobile object in the first passing direction;

[0013] a first motion state determination module for determining the first motion state of the first mobile object in the signal state;

[0014] a second motion state determination module configured to determine a second motion state of a second moving object in the signal state, the second moving object being a moving object on a driving road in a second passing direction at the target intersection, the traffic operation indication of the traffic signal lamp in the first passing direction being opposite to that in the second passing direction;

[0015] an execution module configured to determine and execute a corresponding early warning measure based on the first motion state of the first moving object and the second motion state of the second moving object in the signal state.

[0016] In a third aspect, the present application provides an electronic device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the road cooperative early warning method as described above.

[0017] In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, when the computer program is run by a processor, the steps of the road cooperative early warning method as described above are performed.

[0018] The road cooperative early warning method, device, electronic device and storage medium provided by the present application can determine the signal state of the target traffic signal lamp, the target traffic signal lamp being a signal lamp arranged at the target intersection for guiding the traffic operation of the first moving object in the first passing direction, determine the first motion state of the first moving object in the signal state, determine the second motion state of the second moving object in the signal state, the second moving object being a moving object on a driving road in a second passing direction at the target intersection, the traffic operation indication of the traffic signal lamp in the first passing direction being opposite to that in the second passing direction, determine and execute a corresponding early warning measure based on the first motion state of the first moving object and the second motion state of the second moving object in the signal state, and can cooperate the information of the vehicles, pedestrians and traffic signal lamps on the road, early warning the occurrence of traffic accidents, so as to avoid the occurrence of traffic accidents and protect the safety of pedestrians and vehicles.

[0019] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 A flow chart of a road cooperative warning method provided by the embodiments of the present application;

[0022] Figure 2 A working principle diagram of a vehicle-road cooperative system provided by the embodiments of the present application;

[0023] Figure 3 A flow chart of a triggering step provided by the embodiments of the present application;

[0024] Figure 4 A flow chart of a pedestrian recognition step provided by the embodiments of the present application;

[0025] Figure 5 A flow chart of a step of determining a first motion state of a first mobile object provided by the embodiments of the present application;

[0026] Figure 6 A flow chart of a step of determining a second motion state of a second mobile object provided by the embodiments of the present application;

[0027] Figure 7 A flow chart of a warning of a vehicle-road cooperative system provided by the embodiments of the present application;

[0028] Figure 8 A structural schematic diagram of a road cooperative warning device provided by the embodiments of the present application;

[0029] Figure 9 A structural schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0030] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application and are not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without creative work belongs to the scope of protection of the present application.

[0031] Firstly, the application scenarios applicable to the present application are introduced. The present application can be applied to a vehicle-road cooperative system.

[0032] In recent years, the informationization construction in China has made great progress, especially in the field of intelligent transportation, a series of new applications and new technologies are emerging. Among them, vehicle-road cooperation is the latest development direction of intelligent transportation system, which uses advanced wireless communication and new generation Internet technology, and implements vehicle-vehicle and vehicle-road dynamic real-time information interaction in all directions, and carries out vehicle active safety control and road cooperative management on the basis of full-time and space dynamic traffic information collection and fusion, aiming to realize the effective cooperation of man, vehicle and road.

[0033] In real road scenes, the position relationship between people and vehicles is complex and diverse, which needs to be quickly analyzed and calculated according to real-time local information and the results need to be fed back to pedestrians and surrounding vehicles, such as dangerous road condition avoidance and traffic accident warning. Some scenes need to collect global information and unified analysis to effectively avoid traffic accidents.

[0034] At present, the traditional pedestrian crossing warning method is mainly based on the state of traffic signal lights, and the roadside broadcast equipment reminds pedestrians to prohibit passing according to the current traffic light state, and the crossing action mainly relies on the subjective consciousness control of pedestrians, which cannot be associated with the driving state of vehicles at the intersection, and cannot prevent accidents from happening from the aspects of pedestrians and vehicles.

[0035] Based on this, the embodiments of the present application provide a vehicle-road cooperative system, which includes roadside camera monitoring, millimeter wave radar, traffic signal light, roadside broadcast, induction screen and other devices.

[0036] Please refer to Figure 1 and Figure 2 , Figure 1 a flowchart of a road cooperative warning method provided by the embodiments of the present application, Figure 2 a working principle diagram of a vehicle-road cooperative system provided by the embodiments of the present application. For example Figure 1As shown in the embodiments of this application, the road cooperative early warning method is applicable to vehicle-road cooperative systems and includes:

[0037] S101. Determine the signal status of the target traffic light. The target traffic light is a signal light installed at the target intersection to direct the traffic flow of the first moving object in the first direction of travel.

[0038] The first direction of travel here refers to the direction of movement of the moving object. This first moving object can be a pedestrian or a vehicle; we will use a pedestrian as an example here.

[0039] Specifically, when the target traffic light is yellow or red, it is determined to be a prohibited state; when the target traffic light is green, it is determined to be a permitted state.

[0040] like Figure 3 As shown, Figure 3 A flowchart illustrating a triggering step provided in an embodiment of this application. Prior to step S101, the method further includes:

[0041] S201. Obtain monitoring data collected by all target road monitoring devices. Each target road monitoring device is set on a driving road that forms the target intersection to collect monitoring data within a preset range on that driving road.

[0042] In one embodiment of this application, the vehicle-road cooperative system can acquire data collected in real time from roadside terminals at the target intersection. This data includes monitoring videos of each roadway entrance captured by intersection monitoring equipment (or road monitoring equipment), scanning data from millimeter-wave radar, and the signal status of each traffic light at the target intersection, including at least yellow, red, and green lights.

[0043] Each road is equipped with at least one millimeter-wave radar and at least one road monitoring device.

[0044] S202. For each monitoring data, identify the pedestrians or vehicles moving along the first traffic direction on the road corresponding to that monitoring data.

[0045] like Figure 4 The diagram shown is a flowchart of a pedestrian recognition step provided in an embodiment of this application. Specifically, for each piece of monitoring data, the pedestrian moving along the first traffic direction on the road corresponding to that monitoring data is identified in the following way:

[0046] S301. Based on each frame of the monitoring image, extract the position coordinates of the skeletal joints of each pedestrian in the monitoring image.

[0047] S302, for each pedestrian, determine the change of position coordinates of the skeleton joints of the pedestrian in a preset number of continuous monitoring images, determine the motion distance and motion speed of the pedestrian, and determine the motion direction of the pedestrian based on the motion distance of the pedestrian, and when it is determined that the motion direction of the pedestrian is in the same direction as the first passing direction and the motion speed is greater than zero, it is determined that a pedestrian moving in the first passing direction on the driving road corresponding to the monitoring data is recognized.

[0048] In one case, all pedestrians moving in the first passing direction can be recognized based on the monitoring video collected by the road monitoring device. Specifically, the means of skeleton posture recognition can be used to recognize all pedestrians with motion trend.

[0049] S203, for each recognized pedestrian or vehicle, based on the scanning data collected by the target millimeter wave radar, determine the distance value between the pedestrian or vehicle and the base point of the target intersection.

[0050] S204, for each recognized pedestrian or vehicle, when the distance value between the pedestrian or vehicle and the base point of the target intersection is less than or equal to the standard distance value, the pedestrian or vehicle is determined as the first moving object, and the step of determining the signal state of the target traffic signal is executed.

[0051] The base point of the target intersection here can be the center point of the target intersection. When the pedestrian moves to a position 20 meters away from the base point, step S101 is triggered. The standard distance value here needs to be determined according to the size of each intersection, and the standard distance value of pedestrians and vehicles can be different. Since pedestrians move slowly and vehicles move quickly, in order to ensure the effectiveness of the early warning, the standard distance value of vehicles can be greater than that of pedestrians, for example, the standard distance value of vehicles is 30 meters, and the standard distance value of pedestrians is 15 meters.

[0052] In another case, considering the working properties of the monitoring device and the millimeter wave radar, the way of recognizing pedestrians or vehicles can be determined according to the time period or weather information. For example, in sunny daytime, recognition can be based on monitoring video, while in dark or rainy and snowy weather, recognition of pedestrians or vehicles can be based on the scanning results of the millimeter wave radar.

[0053] S102, determine the first motion state of the first moving object under the signal state.

[0054] As shown in the flow chart of the step of determining the first motion state of the first moving object provided by the embodiment of the present application. Figure 5

[0055] ​S1020: Obtain the real-time position coordinates of the first moving object, and determine whether the current position coordinates of the first moving object are within the first preset area;

[0056] S1022. When the real-time position coordinates of the first moving object are within the first preset area, the motion state of the first moving object is determined to be that the traversing action has occurred.

[0057] S1024. When the real-time position coordinates of the first moving object are outside the first preset area, the motion state of the first moving object is determined to be that the through motion has not occurred.

[0058] Here, when the first moving object is a pedestrian, the first preset area corresponding to the pedestrian is the closed area enclosed by the extension lines of the first and last lines of each zebra crossing segment set at the target intersection. When the first moving object is a vehicle, the first preset area corresponding to the vehicle is the closed area enclosed by the extension lines of all stop lines at the target intersection. This first preset area can also be a scaled-up version of the aforementioned closed area.

[0059] S103. Determine the second motion state of the second moving object under the signal condition. The second moving object is a moving object located on the road in the second direction of travel at the target intersection. The traffic operation indications of the traffic lights in the first direction of travel and the second direction of travel are opposite.

[0060] like Figure 6 The diagram shows a flowchart of a step for determining the second motion state of a second moving object according to an embodiment of this application. In this step, when the first moving object is a pedestrian, the second moving object is a vehicle, and the second motion state includes a safe state and a dangerous state. The second motion state of the vehicle is determined in the following manner:

[0061] S1030. Obtain target monitoring data corresponding to the target driving road that forms the target intersection. The target driving road is the driving road located in the second direction of traffic.

[0062] S1032. Based on the target monitoring data, obtain the real-time position coordinates of all moving vehicles, and determine whether the real-time position coordinates of the vehicles are located within the second preset area.

[0063] S1034. When the real-time position coordinates of at least one vehicle are located within the second preset area, the second motion state of the vehicle is determined to be a dangerous state.

[0064] S1036. When no vehicle's real-time location coordinates are within the second preset area, the second motion state of the vehicle is determined to be a safe state.

[0065] The second preset area corresponding to the vehicle here is the closed area enclosed by the extensions of all stop lines at the target intersection. This second preset area can also be a proportionally enlarged version of the aforementioned closed area, and it can be equal to the first preset area.

[0066] S104. Based on the first motion state of the first moving object and the second motion state of the second moving object under the signal state, determine and execute the corresponding early warning measures.

[0067] like Figure 7 As shown, Figure 7 This is a flowchart illustrating an early warning system for a vehicle-road cooperative system provided in this application embodiment. As shown in the figure, the signal status includes a prohibited state and a permitted state. When the first moving object is a pedestrian and the second moving object is a vehicle, the corresponding early warning measures are determined and executed in the following manner:

[0068] If it is determined that pedestrians are crossing the road and vehicles are in a safe condition, then no warning measures will be implemented.

[0069] When it is determined that a pedestrian is crossing the road and the vehicle is in a dangerous state, if the pedestrian crossing has already occurred, then the second warning measure is determined and implemented; if the pedestrian crossing has not occurred, then the first warning measure is determined and implemented.

[0070] When it is determined that pedestrians are in a prohibited state and vehicles are in a safe state, if pedestrian crossing has not occurred, no warning measures will be implemented; if pedestrian crossing has occurred, the first warning measure will be determined and implemented.

[0071] When it is determined that a pedestrian is in a prohibited state and the vehicle is in a dangerous state, if the pedestrian crossing has not occurred, no warning measures will be implemented; if the pedestrian crossing has occurred, a second warning measure will be determined and implemented.

[0072] like Figure 7 As shown, when the first moving object is a vehicle, the process is similar to that when the first moving object is a pedestrian, so it will not be described again here.

[0073] Specifically, the first early warning measures include broadcasting early warning information through a public address system at the target intersection, displaying early warning information through a guidance screen at the target intersection, and sending early warning information to the vehicle-mounted terminals of vehicles within the third preset area; the second early warning measures include broadcasting early warning information through a public address system at the target intersection, displaying early warning information through a guidance screen at the target intersection, sending early warning information to the vehicle-mounted terminals of vehicles within the third preset area, and setting all traffic lights at the target intersection to flashing yellow or red. The third preset area is larger than the first and second preset areas.

[0074] Further, all vehicle license plates in the third preset area can be recognized based on the monitoring video, and warning information can be sent to the vehicle terminal corresponding to the license plate according to the pre-registered vehicle information.

[0075] The road cooperative warning method provided in the embodiments of the present application can comprehensively judge the road information and the state of the vehicle based on the vehicle-road cooperative system, the road monitoring equipment, the roadside sensing equipment such as the millimeter wave radar, the AI skeleton recognition, the motion posture judgment, the position detection, the AI license plate recognition, the motion state detection position detection from both sides of the pedestrian and the vehicle, the state of the intersection signal, the warning and the alert for the pedestrian and the vehicle in different roles.

[0076] The road cooperative warning method provided in the embodiments of the present application can comprehensively judge the road information and the state of the vehicle based on the vehicle-road cooperative system, the road monitoring equipment, the roadside sensing equipment such as the millimeter wave radar, the AI skeleton recognition, the motion posture judgment, the position detection, the AI license plate recognition, the motion state detection position detection from both sides of the pedestrian and the vehicle, the state of the intersection signal, the warning and the alert for the pedestrian and the vehicle in different roles.

[0077] Meanwhile, the driving state and the speed of the motor vehicle at the intersection are estimated according to the intersection camera monitoring and the real-time monitoring of the vehicle terminal, the event simulation is performed in combination with the state of the pedestrian crossing, the warning information is sent to the vehicle terminal to warn the driver to pay attention to the pedestrian crossing or to stop the vehicle in time, the traffic signal can be temporarily changed to the yellow flashing state or the red light warning when necessary, and the vehicle information and the driver information are put into the induction screen for public warning.

[0078] Compared with the traditional pedestrian crossing warning method, the present application effectively combines the vehicle-road cooperative system and the roadside sensing equipment to comprehensively calculate from multiple aspects, and actively takes measures from both sides of the pedestrian and the motor vehicle to effectively avoid the occurrence of the pedestrian crossing or the motor vehicle crossing accident.

[0079] Based on the same inventive concept, the embodiments of the present application also provide a road cooperative warning device corresponding to the road cooperative warning method. Since the principle of solving problems of the device in the embodiments of the present application is similar to the road cooperative warning method described above, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0080] Please refer to Figure 8 , Figure 8 The structure of a road cooperative warning device provided in the embodiments of the present application is shown in FIG. 8. Figure 8 As shown in FIG. 8, the road cooperative warning device 800 includes:

[0081] A signal determination module 810 is configured to determine the signal state of a target traffic signal lamp, the target traffic signal lamp being a signal lamp arranged at a target intersection and used to guide the traffic running of a first mobile object in a first passing direction.

[0082] The first motion state determining module 820 is configured to determine a first motion state of the first moving object in the signal state.

[0083] The second motion state determining module 830 is configured to determine a second motion state of a second moving object in the signal state, the second moving object being a moving object on a driving road in a second driving direction at the target intersection, the traffic operation indication of the traffic signal lamp in the first driving direction being opposite to that in the second driving direction.

[0084] The executing module 840 is configured to determine and execute a corresponding early warning measure based on the first motion state of the first moving object and the second motion state of the second moving object in the signal state.

[0085] In a preferred embodiment, the target intersection is formed by a plurality of driving roads intersecting, and further comprises a triggering module configured to: acquire monitoring data collected by all target road monitoring devices, each target road monitoring device being arranged on a driving road forming the target intersection to collect monitoring data within a preset range on the driving road; for each monitoring data, identify a pedestrian or a vehicle moving in the first driving direction on the driving road corresponding to the monitoring data; for each identified pedestrian or vehicle, determine a distance value between the pedestrian or vehicle and a base point of the target intersection based on scanning data collected by the target millimeter wave radar; and for each identified pedestrian or vehicle, when the distance value between the pedestrian or vehicle and the base point of the target intersection is less than or equal to a standard distance value, determine the pedestrian or vehicle as the first moving object, and execute the step of determining the signal state of the target traffic signal lamp.

[0086] In a preferred embodiment, further comprising a first identifying module configured to, for each monitoring data, identify a pedestrian moving in the first driving direction on the driving road corresponding to the monitoring data by: based on each monitoring image of the monitoring data, extracting position coordinates of the skeletal joints of each pedestrian in the monitoring image; for each pedestrian, determining changes in the position coordinates of the skeletal joints of the pedestrian in a preset number of continuous monitoring images, determining a motion distance and a motion speed of the pedestrian, and based on the motion distance of the pedestrian, determining a motion direction of the pedestrian, and when it is determined that the motion direction of the pedestrian is in the same direction as the first driving direction and the motion speed is greater than zero, identifying the pedestrian moving in the first driving direction on the driving road corresponding to the monitoring data.

[0087] In a preferred embodiment, the first motion state includes a crossing action occurrence and a crossing action non-occurrence, and the first motion state determination module 820 is specifically configured to acquire a real-time position coordinate of the first mobile object, and determine whether the current position coordinate of the first mobile object is located within a first preset region; when the real-time position coordinate of the first mobile object is located within the first preset region, it is determined that the motion state of the first mobile object is a crossing action occurrence; when the real-time position coordinate of the first mobile object is located outside the first preset region, it is determined that the motion state of the first mobile object is a crossing action non-occurrence.

[0088] In a preferred embodiment, when the first mobile object is a pedestrian and the second mobile object is a vehicle, the second motion state includes a safe state and a dangerous state, and further includes a second identification module configured to determine the second motion state of the vehicle by: acquiring target monitoring data corresponding to a target driving road forming a target intersection, the target driving road being a driving road in a second passing direction; based on the target monitoring data, acquiring real-time position coordinates of all moving vehicles, and determining whether the real-time position coordinates of the vehicles are located within a second preset region; when the real-time position coordinates of at least one vehicle are located within the second preset region, it is determined that the second motion state of the vehicle is a dangerous state; when the real-time position coordinates of no vehicle are located within the second preset region, it is determined that the second motion state of the vehicle is a safe state.

[0089] In a preferred embodiment, the signal state includes a no-passing state and a passing state, when the first mobile object is a pedestrian and the second mobile object is a vehicle, the execution module 840 determines and executes corresponding warning measures by: when it is determined that the pedestrian is in the passing state and the vehicle is in the safe state, no warning measure is executed; when it is determined that the pedestrian is in the passing state and the vehicle is in the dangerous state, if the crossing action of the pedestrian has occurred, a second warning measure is determined and executed, and if the crossing action of the pedestrian has not occurred, a first warning measure is determined and executed; when it is determined that the pedestrian is in the no-passing state and the vehicle is in the safe state, if the crossing action of the pedestrian has not occurred, no warning measure is executed, and if the crossing action of the pedestrian has occurred, a first warning measure is determined and executed; when it is determined that the pedestrian is in the no-passing state and the vehicle is in the dangerous state, if the crossing action of the pedestrian has not occurred, no warning measure is executed, and if the crossing action of the pedestrian has occurred, a second warning measure is determined and executed.

[0090] In a preferred embodiment, the first early warning measure comprises playing early warning information through a broadcast arranged at the target intersection, playing early warning information through an induction screen arranged at the target intersection, and sending early warning information to a vehicle terminal of a vehicle in the third preset area; the second early warning measure comprises playing early warning information through a broadcast arranged at the target intersection, playing early warning information through an induction screen arranged at the target intersection, sending early warning information to a vehicle terminal of a vehicle in the third preset area, and setting all traffic lights at the target intersection to display yellow flashing or red light, and the third preset area is larger than the first preset area and the second preset area.

[0091] Please refer to Figure 9 , Figure 9 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 9. As shown in FIG. 9, the electronic device 900 includes a processor 910, a memory 920, and a bus 930. Figure 9

[0092] The memory 920 stores machine readable instructions executable by the processor 910. When the electronic device 900 is running, the processor 910 communicates with the memory 920 through the bus 930. The machine readable instructions, when executed by the processor 910, can perform the steps of the road cooperative early warning method in the above method embodiments. For details, refer to the method embodiments, which will not be described here again.

[0093] An embodiment of the present application further provides a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the road cooperative early warning method in the above method embodiments can be performed. For details, refer to the method embodiments, which will not be described here again.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here again.

[0095] In several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented by other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices, or units, and can be electrical, mechanical, or other forms.

[0096] ​The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0097] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0098] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, and various program code storage media.

[0099] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, used to illustrate the technical solutions of the present application, and not to limit them, the protection scope of the present application is not limited thereto, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand: any skilled person familiar with the technical field can modify or easily think of changes to the technical solutions recorded in the foregoing embodiments within the technical range disclosed by the present application, or make equivalent replacement to part of the technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and all should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A road cooperative early warning method, characterized in that, The method includes: Determine the signal status of the target traffic light, which is a traffic light installed at the target intersection to direct the traffic flow of the first moving object in the first direction of travel. Determine the first motion state of the first moving object under the signal state; Determine the second motion state of the second moving object under the signal condition. The second moving object is a moving object located on the road in the second direction of travel at the target intersection. The traffic operation indications of the traffic lights in the first direction of travel and the second direction of travel are opposite. Based on the first motion state of the first moving object and the second motion state of the second moving object under the signal state, the corresponding early warning measures are determined and executed. The target intersection is formed by the convergence of multiple driving roads. Before the step of determining the signal status of the target traffic light, the method further includes: Acquire monitoring data collected by all target road monitoring devices. Each target road monitoring device is set up on a driving road that forms the target intersection to collect monitoring data within a preset range on that driving road. For each monitoring data, identify the pedestrians or vehicles moving along the first direction of travel on the road corresponding to that monitoring data; For each identified pedestrian or vehicle, the distance between the pedestrian or vehicle and the base point of the target intersection is determined based on the scanning data collected by the target millimeter-wave radar. For each identified pedestrian or vehicle, if the distance between the pedestrian or vehicle and the base point of the target intersection is less than or equal to the standard distance, the pedestrian or vehicle is identified as the first moving object, and the step of determining the signal status of the target traffic light is executed. For each monitoring data point, pedestrians moving along the first traffic direction on the corresponding road are identified using the following method: Based on each frame of the surveillance image, the position coordinates of the skeletal joints of each pedestrian in the surveillance image are extracted; For each pedestrian, the changes in the position coordinates of the skeletal joints of the pedestrian in a preset number of consecutive monitoring images are determined, the pedestrian's movement distance and speed are determined, and the pedestrian's movement direction is determined based on the pedestrian's movement distance. When it is determined that the pedestrian's movement direction is in the same direction as the first traffic direction and the movement speed is greater than zero, then the pedestrian moving along the first traffic direction on the road corresponding to the monitoring data is identified.

2. The road cooperative early warning method according to claim 1, characterized in that, The first motion state includes whether the crossing action has occurred or not. The step of determining the first motion state of the first moving object under the signal state specifically includes: Obtain the real-time position coordinates of the first moving object and determine whether the current position coordinates of the first moving object are within the first preset area; When the real-time position coordinates of the first moving object are within the first preset area, the motion state of the first moving object is determined to be that the traversing action has occurred; When the real-time position coordinates of the first moving object are outside the first preset area, the motion state of the first moving object is determined to be that the traversing action has not occurred.

3. The road cooperative early warning method according to claim 2, characterized in that, When the first moving object is a pedestrian, the second moving object is a vehicle. The second motion state includes a safe state and a dangerous state. The second motion state of the vehicle is determined by the following method: Acquire target monitoring data corresponding to the target driving road that forms the target intersection, wherein the target driving road is a driving road located in the second direction of traffic; Based on the target monitoring data, the real-time position coordinates of all moving vehicles are obtained, and it is determined whether the real-time position coordinates of the vehicles are within the second preset area. When the real-time position coordinates of at least one vehicle are within the second preset area, the second motion state of the vehicle is determined to be a dangerous state. When no vehicle's real-time location coordinates are within the second preset area, the vehicle's second motion state is determined to be a safe state.

4. The road cooperative early warning method according to claim 3, characterized in that, Signal status includes prohibited and permitted states. When the first moving object is a pedestrian and the second moving object is a vehicle, the corresponding warning measures are determined and executed in the following manner: If it is determined that pedestrians are crossing the road and vehicles are in a safe condition, then no warning measures will be implemented. When it is determined that a pedestrian is crossing the road and the vehicle is in a dangerous state, if the pedestrian crossing has already occurred, then the second warning measure is determined and implemented; if the pedestrian crossing has not occurred, then the first warning measure is determined and implemented. When it is determined that pedestrians are in a prohibited state and vehicles are in a safe state, if pedestrian crossing has not occurred, no warning measures will be implemented; if pedestrian crossing has occurred, the first warning measure will be determined and implemented. When it is determined that a pedestrian is in a prohibited state and the vehicle is in a dangerous state, if the pedestrian crossing has not occurred, no warning measures will be implemented; if the pedestrian crossing has occurred, a second warning measure will be determined and implemented.

5. The road cooperative early warning method according to claim 4, characterized in that, The first early warning measures include: Warning information is broadcast through the radio at the target intersection, warning information is displayed on the guidance screen at the target intersection, and warning information is sent to the vehicle-mounted terminals of vehicles in the third preset area. The second early warning measures include: Warning information is broadcast through a radio station set up at the target intersection, warning information is displayed through a guidance screen set up at the target intersection, warning information is sent to the vehicle terminals of vehicles in a third preset area, and all traffic lights at the target intersection are set to flashing yellow or red. The third preset area is larger than the first preset area and the second preset area.

6. A road cooperative early warning device, characterized in that, The road cooperative early warning device includes: The signal determination module is used to determine the signal status of the target traffic light, which is a traffic light installed at the target intersection to direct the traffic flow of the first moving object in the first direction of travel. The first motion state determination module is used to determine the first motion state of the first moving object under the signal state. The second motion state determination module is used to determine the second motion state of the second moving object under the signal state. The second moving object is a moving object located on the road in the second direction of travel at the target intersection. The traffic operation indications of the traffic lights in the first direction of travel and the second direction of travel are opposite. The execution module is used to determine and execute corresponding early warning measures based on the first motion state of the first moving object and the second motion state of the second moving object under the signal state; The trigger module is used to acquire monitoring data collected by all target road monitoring devices. Each target road monitoring device is set on a driving road that forms the target intersection to collect monitoring data within a preset range on the driving road. For each monitoring data, pedestrians or vehicles moving along the first traffic direction on the driving road corresponding to the monitoring data are identified. For each identified pedestrian or vehicle, the distance between the pedestrian or vehicle and the base point of the target intersection is determined based on the scanning data collected by the target millimeter-wave radar. For each identified pedestrian or vehicle, if the distance between the pedestrian or vehicle and the base point of the target intersection is less than or equal to the standard distance value, the pedestrian or vehicle is identified as the first moving object, and the step of determining the signal status of the target traffic light is executed. The target intersection is formed by the intersection of multiple driving roads. The first identification module is used to identify pedestrians moving along the first traffic direction on the road corresponding to each monitoring data in the following way: based on each frame of the monitoring image of the monitoring data, extract the position coordinates of the skeletal joints of each pedestrian in the monitoring image; for each pedestrian, determine the change of the position coordinates of the skeletal joints of the pedestrian in a preset number of consecutive monitoring images, determine the movement distance and movement speed of the pedestrian, and determine the movement direction of the pedestrian based on the movement distance; when it is determined that the movement direction of the pedestrian is in the same direction as the first traffic direction and the movement speed is greater than zero, then it is determined that the pedestrian moving along the first traffic direction on the road corresponding to the monitoring data has been identified.

7. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the road cooperative warning method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the road cooperative early warning method as described in any one of claims 1 to 5.

Images