Coordinated inductive control method, electronic equipment and computer readable storage medium

Abstract

The invention provides a coordinated inductive control method, electronic equipment and a computer readable storage medium. The coordinated inductive control method comprises the following steps: acquiring traffic flow data of a target intersection at the current moment and operation data of a corresponding traffic signal lamp; according to the operation data and the traffic flow data, determining a stage vehicle state value and a stage pedestrian state value of the target stage at the current moment; determining a stage decision value of the target stage at the current moment according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current moment; and according to the stage decision value of the target stage at the current moment, generating a control instruction for controlling the traffic signal lamp of the target intersection. Therefore, the traffic signal lamp can be correspondingly controlled in real time in response to the dynamic change of the traffic demand, the period duration of the passing scheme, especially the green light duration of each stage in the passing scheme, does not need to be set as a fixed value, the comprehensive technical effect of cooperatively optimizing the vehicle passing efficiency and the pedestrian crossing safety is realized, and the induction control application cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic control, in particular to a coordinated induction control method, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the continuous growth of the number of motor vehicles in cities, traffic congestion has become a prominent problem affecting the efficiency of city operation and the travel experience of residents. As a key control node of the road network, the control strategy of traffic signal lights directly determines the traffic capacity and safety level of the intersection. Currently, on urban arterial roads, the mainstream signal control method is still the timing coordination control method, that is, based on historical traffic flow data, a set of fixed cycle length, green ratio and phase difference parameters are preset for different time periods (such as morning peak, evening peak and flat peak). However, urban traffic flow has significant randomness, volatility and tidal characteristics, and the above fixed timing scheme cannot respond to the dynamic changes of traffic demand in real time. SUMMARY

[0003] In view of the above technical problems, the present application provides a coordinated induction control method, an electronic device and a computer readable storage medium, which can respond to the dynamic changes of traffic demand in real time and control the traffic signal lights accordingly, without setting the cycle length of the traffic plan as a fixed value, and achieving the comprehensive technical effect of optimizing the vehicle traffic efficiency and pedestrian crossing safety in coordination.

[0004] The present application provides a coordinated induction control method, comprising: obtaining traffic flow data of a target intersection at a current time and operation data of a corresponding traffic signal light; the operation data includes an operation scheme, an executed target phase and light states of each light group in the target phase; determining a phase vehicle state value and a phase pedestrian state value of the target phase at the current time according to the operation data and the traffic flow data; determining a phase decision value of the target phase at the current time according to the phase vehicle state value and the phase pedestrian state value of the target phase at the current time; generating a control instruction for controlling the traffic signal light of the target intersection according to the phase decision value of the target phase at the current time.

[0005] In an embodiment, the operation scheme includes operation control logic and target object quantity thresholds corresponding to each light group in the target phase; determining the phase vehicle state value and the phase pedestrian state value of the target phase at the current time according to the operation data and the traffic flow data comprises: performing light group association detection on the traffic flow data to obtain a detection result of traffic flow sub-data associated with each light group in the target phase; determining, according to the target object quantity threshold corresponding to each light group in the target stage and the detection result of the traffic flow sub-data associated with each light group in the target stage, the vehicle state value and the pedestrian state value of each light group in the target stage at the current time; determining, according to the vehicle state value and the pedestrian state value of each light group in the target stage at the current time and the operation control logic, the stage vehicle state value and the stage pedestrian state value of the target stage at the current time.

[0006] In an embodiment, the detection result includes the target object quantity in the detection area corresponding to the light group; the target object includes a vehicle and a pedestrian, the detection area includes an import vehicle detection area and a pedestrian detection area, and the target object quantity threshold includes an import vehicle quantity threshold and a pedestrian quantity threshold; determining, according to the target object quantity threshold corresponding to each light group in the target stage and the detection result of the traffic flow sub-data associated with each light group in the target stage, the vehicle state value and the pedestrian state value of each light group in the target stage at the current time, comprising: at the current time, if the number of vehicles in the import vehicle detection area corresponding to the target light group is empty, marking the vehicle detection state value of the target light group at the current time as a third preset value; if the number of vehicles in the import vehicle detection area corresponding to the target light group is greater than or equal to the import vehicle quantity threshold, marking the vehicle detection state value of the target light group at the current time as a first preset value, otherwise marking the vehicle detection state value of the target light group at the current time as a second preset value; the target light group is any light group in the target stage with a green light state; when tracing back from the current time to the continuous m time, if the number of times that the vehicle detection state value of the target light group is the third preset value is greater than or equal to a first preset number of times, marking the vehicle state value of the target light group at the current time as the third preset value; if the number of times that the vehicle detection state value of the target light group is the second preset value is greater than or equal to the first preset number of times, marking the vehicle state value of the target light group at the current time as the second preset value, otherwise marking the vehicle state value of the target light group at the current time as the first preset value; if the number of pedestrians in the pedestrian detection area corresponding to the target light group is greater than or equal to the pedestrian quantity threshold, marking the pedestrian state value of the target light group at the current time as a first preset value, otherwise marking the pedestrian state value of the target light group at the current time as a second preset value.

[0007] In an embodiment, according to the vehicle state value and the pedestrian state value of each light group in the target stage at the current time and the operation control logic, determining the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, comprising at least one of: When the operation control logic is the first operation logic, the stage vehicle state value of the target stage at the current time is marked as the minimum value of the vehicle state values of all the light groups in the target stage at the current time, and the stage pedestrian state value of the target stage at the current time is marked as the minimum value of the pedestrian state values of all the light groups in the target stage at the current time; When the operation control logic is the second operation logic, if there is at least one light group in the target stage whose vehicle state value at the current time is the first preset value, the stage vehicle state value of the target stage at the current time is marked as the first preset value, otherwise, the stage vehicle state value of the target stage at the current time is marked as the minimum value of the vehicle state values of all the light groups in the target stage at the current time; if there is at least one light group in the target stage whose pedestrian state value is the first preset value, the stage pedestrian state value of the target stage at the current time is marked as the first preset value, otherwise, the stage pedestrian state value of the target stage at the current time is marked as the second preset value.

[0008] In an embodiment, the stage decision value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, including: The stage signal value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time. The stage decision value of the target stage at the current time is determined according to the stage signal value of the target stage at the current time.

[0009] In an embodiment, the stage signal value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, including: If the stage vehicle state value of the target stage at the current time is the first preset value and all the light groups in the target stage satisfy the vehicle empty confirmation rate, and the stage pedestrian state value of the target stage at the current time is the second preset value and all the light groups in the target stage satisfy the pedestrian empty confirmation rate, the stage signal value of the target stage at the current time is marked as the fourth preset value; If the stage vehicle state value of the target stage at the current time is the third preset value and all the light groups in the target stage satisfy the offline confirmation rate, the stage signal value of the target stage at the current time is marked as the fifth preset value; Otherwise, the stage signal value of the target stage at the current time is marked as the sixth preset value; The light group meets a vehicle empty confirmation rate, and the number of vehicles in the import vehicle detection area corresponding to the light group is less than the preset vehicle number for more than or equal to the first preset number of times in the n continuous time instants from the current time instant.

[0010] The application further provides an electronic device, comprising a memory and a processor, wherein the memory stores computer program instructions for execution on the processor, and the processor implements the coordinated inductive control method as described above when executing the computer program instructions.

[0011] The application further provides a computer readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the coordinated inductive control method as described above.

[0012] As described above, the coordinated inductive control method provided by the application realizes full-factor and real-time perception of the traffic environment and signal state of the target intersection by acquiring the traffic flow data and the operation data of the traffic signal light at the current time instant, and improves the decision dimension of the pedestrian traffic demand to the same importance as the vehicle traffic demand by determining the stage vehicle state value and the stage pedestrian state value of the target phase at the current time instant according to the operation data and the traffic flow data, and realizes a fundamental change from static timing control to dynamic demand driving by determining the stage decision value of the target phase at the current time instant according to the stage vehicle state value and the stage pedestrian state value of the target phase at the current time instant, so that the signal timing can be self-adaptive to the real-time traffic flow change, and the green light time utilization efficiency is significantly improved, and the intelligent decision result is converted into an action executed by a field device without loss and efficiently by generating a control instruction for controlling the traffic signal light of the target intersection according to the stage decision value of the target phase at the current time instant, forming a complete closed-loop automatic control from perception, decision to execution. That is, the coordinated inductive control method provided by the application can respond to the dynamic change of the traffic demand in real time and control the traffic signal light accordingly, without setting the cycle length of the traffic plan as a fixed value, and realizes the comprehensive technical effect of optimizing the vehicle traffic efficiency and the pedestrian crossing safety, while greatly reducing the application cost of inductive control, and lays a foundation for building a low-cost and high-reliability intelligent traffic control system. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 Schematic diagram for detection area Figure One ; Figure 2 Schematic diagram for detection area Figure Two ; Figure 3 A flowchart of a coordinated inductive control method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0014] The exemplary embodiments will be described in detail herein below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended for explaining the present application and are not intended to limit the present application.

[0015] First, the related terms involved in the embodiments of the present application are explained.

[0016] A light group: used to indicate the direction and turning information of at least one traffic flow that obtains the right-of-way at the same time, each light group corresponds to a unique light group identifier. Taking the example of using numbers to represent the light group identifier, 1 can represent the east left-turn light group, 2 can represent the east straight light group, 3 can represent the east right-turn light group, 4 can represent the west left-turn light group, 5 can represent the west straight light group, 6 can represent the west right-turn light group, 7 can represent the south left-turn light group, 8 can represent the south straight light group, 9 can represent the south right-turn light group, 10 can represent the north left-turn light group, 11 can represent the north straight light group, and 12 can represent the north right-turn light group. In actual applications, the right-turn light group can also be not considered. It should be noted that the name of the light group can adopt the rule of “import direction + passing direction”, for example, the “south straight light group” controls the traffic flow that enters from the south import and passes through the intersection in the north direction.

[0017] A phase: including east-west straight, east-west left-turn, south-north straight, south-north left-turn, east phase release, west phase release, south phase release, north phase release, etc. In a phase of execution, usually two light groups that are allowed to release are included. Taking the example of the south-north straight phase, it includes the south straight light group and the north straight light group.

[0018] A passing scheme: including the combination of phase sequence and phase duration. For example, for a passing scheme, the phases included can be in turn south-north straight, south-north left-turn, east-west straight, and east-west left-turn, and the phase duration of each phase can be a preset value such as 30 seconds.

[0019] Detection area: refers to a virtual area set at an intersection for sensing a traffic participant (i.e., a target object) and is associated with a specific signal lamp group, including a vehicle detection area and a pedestrian detection area. The vehicle detection area can include an exit vehicle detection area and an entrance vehicle detection area. The exit vehicle detection area is set behind an exit lane and is used to detect a vehicle that has crossed a stop line at the intersection. The data of the exit vehicle detection area is mainly used to determine whether there is an overflow congestion risk at the intersection. The entrance vehicle detection area is set at an entrance lane of the intersection and is used to detect a vehicle that is about to or is waiting to pass through the intersection. According to the distance from the stop line and the function, the entrance vehicle detection area can be divided into an entrance tactical detection area close to the stop line (used to sense the immediate traffic demand) and an entrance strategic detection area far from the stop line (used to sense the medium- and long-term arriving vehicles and can support strategic functions such as priority for special vehicles). In addition, in order to more accurately sense or count the number of entrance vehicles on each lane, the entrance vehicle detection area can be divided into entrance vehicle sub-detection areas corresponding to each lane. The pedestrian detection area is set in a pedestrian crossing (zebra crossing) area and is used to detect pedestrians waiting to cross or crossing. It should be noted that in the standard phase design of a cross intersection, for a straight-through motor vehicle lamp group, the pedestrian detection area associated with the release stage of the lamp group is usually the adjacent zebra crossing area on the left or right side of the traffic direction indicated by the lamp group. For example, for a cross intersection, the zebra crossing area includes a south zebra crossing area, an east zebra crossing area, a north zebra crossing area, and a west zebra crossing area. If the south-north straight-through stage is executed, the lamp groups that obtain the right-of-way are the south straight-through lamp group and the north straight-through lamp group. At this time, the pedestrians and vehicles in the east-west direction obtain the right-of-way. In this case, the pedestrian detection area corresponding to the north straight-through lamp group can be the west zebra crossing area, Figure 1 and the vehicle detection area corresponding to the north straight-through lamp group is shown in FIG. 7A; the pedestrian detection area corresponding to the south straight-through lamp group can be the east zebra crossing area, Figure 2 and the vehicle detection area corresponding to the south straight-through lamp group is shown in FIG. 7B.

[0020] The embodiment provides a coordinated induction control method, as shown in Figure 3 FIG. 1, the coordinated induction control method can be applied to a signal control intelligent device, the signal control intelligent device is used for directly or indirectly controlling traffic signal lamps at an intersection, and can be an electronic device such as an edge computing device in communication connection with a traffic monitoring device and a signal machine at the intersection. The method comprises the following steps. Step S101, acquiring traffic flow data of a target intersection at a current time and operation data of corresponding traffic signal lamps; the operation data includes an operation scheme, an executed target stage, and a lamp state of each lamp group in the target stage.

[0021] Step S102, determining a stage vehicle state value and a stage pedestrian state value of the target stage at the current time according to the operation data and the traffic flow data.

[0022] In step S103, a stage decision value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time.

[0023] In step S104, a control instruction for controlling the traffic signal lamp of the target intersection is generated according to the stage decision value of the target stage at the current time.

[0024] The target intersection is an intersection that needs traffic control, and can be a cross-shaped intersection, a T-shaped intersection, or other forms of intersections, which are not limited herein. The traffic flow data refers to real-time data collected by a traffic monitoring device for describing the traffic condition of the target intersection. In the embodiment, the traffic monitoring device can include a video monitoring device and / or a radar device, and correspondingly, the traffic flow data can include video stream data collected by the video monitoring device at the target intersection, and can also include radar detection data collected by a 4D radar or other radar devices. Of course, the traffic flow data can also be data including video stream data and radar detection data collected by a video-radar integrated machine. The video monitoring device includes but is not limited to an electric police, a card mouth, a flow camera and other devices that can collect video and / or image to provide stable video stream data. In an embodiment, the video stream data of the entire exit vehicle detection area and the pedestrian detection area can be collected by the electric police device, and the video stream data of the entrance vehicle detection area can be collected by the card mouth device. It should be noted that the detection ranges of different traffic monitoring devices can partially overlap or completely not overlap.

[0025] The running data of the traffic signal lamp of the target intersection at the current time can be acquired in real time or periodically, such as every 1 second. The running data refers to data acquired in real time from the signal machine of the target intersection, which describes the current working state of the traffic signal lamp. The running data can include a running scheme, a target stage being executed, and the light state of each lamp group in the target stage, etc. The running scheme is used to indicate the traffic control rule of the traffic flow in each direction, i.e., the number of the timing scheme being executed by the signal machine and the scheme parameters, which can include the passing scheme, the operation control logic, and the pedestrian quantity threshold of the pedestrian detection area corresponding to each lamp group in the target stage, the stage minimum green light time, the stage maximum green light time, the stage degradation time, the stage advance time, the stage time, and the stage delay time, etc. The target stage refers to the signal stage being executed (i.e., released) by the signal machine at the current time, such as the "north-south straight stage". The light state of each lamp group refers to the current light color state (such as red light, green light, yellow light) of each signal lamp group (such as "east straight", "west left turn").

[0026] The operation scheme of the traffic signal lights of the target intersection can be different at different time periods. For example, the operation scheme corresponding to 8:00-9:00 am can be an early peak operation scheme, and the operation scheme corresponding to 9:00 am-5:00 pm can be a flat peak operation scheme, and the like. Meanwhile, the target phase executed at different time can also be different. For example, the target phase executed at 7:11:10 am can be a straight north-south phase, and the target phase executed at 7:12:00 am can be a left turn north-south phase, and the like. The lamp groups in the target phase can be lamp groups related to the target phase. For example, when the target phase is a straight north-south phase, the lamp groups in the target phase include a north straight lamp group and a south straight lamp group with green lights. At the current time, the light states of the lamp groups in the target phase can be the same or different. For example, the light states of some lamp groups in the target phase can be green, and the light states of some lamp groups in the target phase can be red.

[0027] When the signal machine for controlling the traffic signal lights of the target intersection is not integrated on the signal control intelligent device, the signal control intelligent device can periodically acquire the operation data of the traffic signal lights of the target intersection at the current time from the signal machine. In addition, when the signal control intelligent device has stored different operation schemes of the traffic signal lights of the target intersection, the operation scheme in the operation data can be an operation scheme identifier such as an operation scheme number, and the signal control intelligent device can determine the corresponding operation scheme based on the operation scheme identifier and the current time. Of course, the signal machine can also be integrated on the signal control intelligent device.

[0028] The phase vehicle state value is used to quantitatively represent whether all motor vehicle directions served by the target phase still have traffic demand at the current time. The phase pedestrian state value is used to quantitatively represent whether all pedestrian directions associated with the target phase still have traffic demand at the current time. The phase decision value is used to represent the control strategy of the target phase at the current time, i.e., indicating whether the current target phase should continue to run or should be immediately ended. According to the phase decision value of the target phase at the current time, a control instruction for controlling the traffic signal lights of the target intersection can be generated, so as to adjust the states of the lamp groups and / or adjust the released phase based on the control instruction through the signal machine, thereby achieving the comprehensive technical effect of synergistically optimizing the vehicle traffic efficiency and the pedestrian crossing safety, and greatly reducing the application cost of induction control, and the like. The control instruction is an instruction generated and issued by the signal control intelligent device to the signal machine, which is used to directly control the change of the signal lights, such as a “step instruction” (ending the current phase and entering the next phase) or a “lamp group early termination instruction” (ending the green light of a specified lamp group in advance).

[0029] Exemplarily, the signal control intelligent device first acquires, through the communication interface, the running data of the current time from the signal machine and the traffic flow data of the current time from the video monitoring device and the 4D radar in real time (for example, once per second). Then, the edge computing device performs fusion analysis on the acquired data, such as first analyzing the video stream through a visual algorithm such as YOLO, and / or combining radar detection data to count the number of vehicles in each import lane, export lane, and the number of pedestrians on the sidewalk, and then combining the light group information contained in the target stage in the running data, associating the detected traffic data with specific light groups, and through a preset threshold logic (for example, whether the number of vehicles in the import vehicle detection area corresponding to a certain light group is greater than the corresponding threshold value) and operation rules, comprehensively calculating two key indicators: the stage vehicle state value and the stage pedestrian state value of the target stage at the current time. Then, according to the stage vehicle state value and the stage pedestrian state value, it is determined whether the current stage should be ended, and a clear and executable stage decision value is generated. Finally, specific control instructions are generated based on the stage decision value.

[0030] In an embodiment, the running scheme includes operation control logic and target object quantity thresholds corresponding to each light group in the target stage; and the stage vehicle state value and the stage pedestrian state value of the target stage at the current time are determined according to the running data and the traffic flow data, including: performing light group association detection on the traffic flow data to obtain the detection results of the traffic flow sub-data associated with each light group in the target stage; determining the vehicle state value and the pedestrian state value of each light group in the target stage at the current time according to the target object quantity thresholds corresponding to each light group in the target stage and the detection results of the traffic flow sub-data associated with each light group in the target stage; determining the stage vehicle state value and the stage pedestrian state value of the target stage at the current time according to the vehicle state value and the pedestrian state value of each light group in the target stage at the current time and the operation control logic.

[0031] The operation control logic is used to indicate the operation logic in the generation process of the stage vehicle state value and the stage pedestrian state value of the target stage, and includes first operation logic and second operation logic. The first operation logic, also referred to as tight logic, is cautious to the traffic demand determination of the whole stage. As long as the traffic demand of any one direction in the stage does not reach the threshold (i.e., the state value is not "demand"), the whole stage is determined to be no demand. In the scene of large traffic flow, the need for efficient emptying of the queue, or the requirement of high safety, the situation that a certain direction is "over-served" and the other direction is "starved" can be effectively prevented, and it is ensured that all directions have no significant traffic demand at the end of the stage. The second operation logic, also referred to as loose logic, is more positive to the determination of traffic demand. As long as there is traffic demand in any one direction in the stage, the whole stage is determined to be demand. In the scene of small traffic flow, the need to minimize the waiting time of vehicles and pedestrians, the sudden traffic flow can be quickly responded, the service opportunity is not missed due to the small error of a single detector, and the response speed and user experience of the system are improved.

[0032] The target objects include vehicles and pedestrians, different light groups are used to control vehicles or pedestrians, and the number of target objects corresponding to different light groups may be the same or different. At the same time, a light group can correspond to multiple target object number thresholds, such as the import vehicle number threshold corresponding to the import vehicle detection area and the import vehicle number threshold corresponding to the export vehicle detection area. It can be understood that the traffic flow sub-data associated with the light group refers to the data associated with the light group in the traffic flow data, which is used to evaluate the local data of the traffic demand of a specific light group. For video stream data, the traffic flow sub-data associated with the light group may be image frames within a specified detection area; for radar detection data, the traffic flow sub-data associated with the light group may be a structured vehicle information list or a pedestrian information list within a specified detection area. For example, taking the east straight light group as an example, the traffic flow sub-data associated with the east straight light group can include video data of the import vehicle detection area, the export vehicle detection area and the pedestrian detection area of the east straight light group.

[0033] It can be understood that, since the traffic flow sub-data associated with different light groups are different, it is necessary to perform light group association detection on the traffic flow data to filter and extract the part of data corresponding to the traffic flow direction controlled by a specific light group, i.e., the traffic flow sub-data associated with each light group, from the traffic flow data. The detection result can include whether the traffic flow sub-data (including video stream sub-data and / or radar detection sub-data) associated with the light group is obtained, and in the case where the traffic flow sub-data associated with the light group is obtained, the number of target objects in the detection area corresponding to the light group, etc. It should be noted that, according to the detection result, it can be determined that the traffic monitoring device corresponding to the light group, such as the video monitoring device and the radar device, is disconnected, etc. In the embodiment, after obtaining the traffic flow data of the target intersection at the current time, the video stream data can be analyzed by using the existing YOLO visual algorithm to obtain the detection result of the traffic flow sub-data associated with each light group in the target phase, which will not be described herein again.

[0034] The vehicle state value and the pedestrian state value are state identifiers representing the current traffic demand of a single light group based on the comparison between the detection result corresponding to the single light group and the target object quantity threshold. According to the vehicle state value and the pedestrian state value of each light group at the current time and the operation control logic, the phase vehicle state value and the phase pedestrian state value of the target phase at the current time can be determined. It should be noted that, in the embodiment, the vehicle state value and the pedestrian state value of each light group in the target phase at the current time are obtained, which can be understood as obtaining the vehicle state value and the pedestrian state value of each light group in the target phase with the light state being green at the current time. In this way, the phase vehicle state value and the phase pedestrian state value of the target phase at the current time can be accurately obtained, and the vehicle traffic efficiency and the pedestrian crossing safety are further improved.

[0035] In an embodiment, the traffic flow data is subjected to light group association detection to obtain the detection result of the traffic flow sub-data associated with each light group in the target phase, including: determining target video stream data associated with the target light group from the video stream data, and determining target radar detection data associated with the target light group from the radar detection data; the target light group is any light group in the target phase; performing recognition detection on the target objects in at least one first detection area corresponding to the target light group in the target video stream data to obtain a first number of target objects in each first detection area corresponding to the target light group; performing recognition detection on the target objects in a second detection area corresponding to the target light group in the target radar detection data to obtain a second number of target objects in the second detection area corresponding to the target light group; the second detection area is non-overlapping with the first detection area.

[0036] It can be understood that the monitoring ranges of different traffic monitoring devices arranged at the target intersection can partially overlap, but according to the monitoring ranges of different traffic monitoring devices, it can be determined which video stream data associated with each light group can be captured by which video monitoring device or which radar detection data associated with each light group can be collected by which radar device. For example, for the east straight-through light group, the video stream data captured by the video monitoring device arranged on the east side of the target intersection, which has a shooting range covering the exit vehicle detection area of the vehicle driving from east to west and the north zebra crossing area as the pedestrian detection area, and the video stream data captured by the video monitoring device having a shooting range covering the entrance vehicle detection area of the vehicle driving from east to west can be taken as the video stream data associated with the east straight-through light group.

[0037] In the embodiment, the target object can be a vehicle and / or a pedestrian. Alternatively, after the target video stream data and the target radar detection data associated with the target light group are determined, i.e., after the traffic flow sub-data associated with each light group in the target stage is obtained, the identification detection can be performed based on the vehicle identification algorithm and / or the pedestrian identification algorithm to obtain the number of target objects in different detection areas. It should be noted that before the identification detection of the target objects in the corresponding detection area in the target video stream data is performed, a rectangle can be set as the analysis range of the video stream picture based on the detection requirement to minimize the interference. Meanwhile, when the exit vehicle detection area is set, in order to make the exit vehicle detection area cover as many vehicles that have entered the intersection as possible, the shape of the exit vehicle detection area can be set as a polygon, such as a hexagon or an octagon. In this way, the detection result of the traffic flow sub-data associated with each light group in the target stage can be accurately obtained, which facilitates the subsequent accurate control of the traffic signal lights at the target intersection.

[0038] In an embodiment, the detection result includes the number of target objects in the detection area corresponding to the light group; the target object includes a vehicle and / or a pedestrian, the detection area includes a vehicle detection area and / or a pedestrian detection area, and the target object number threshold includes a vehicle number threshold and / or a pedestrian number threshold; According to the target object number threshold corresponding to each light group in the target stage and the detection result of the traffic flow sub-data associated with each light group in the target stage, the vehicle state value and the pedestrian state value of each light group in the target stage at the current time are determined, including: At the current time, if the number of vehicles in the entrance vehicle detection area corresponding to the target light group is empty, the vehicle detection state value of the target light group at the current time is marked as a third preset value; if the number of vehicles in the entrance vehicle detection area corresponding to the target light group is greater than or equal to the entrance vehicle number threshold, the vehicle detection state value of the target light group at the current time is marked as a first preset value, otherwise, the vehicle detection state value of the target light group at the current time is marked as a second preset value; the target light group is any light group in the target stage with a green light state. If the number of times that the vehicle detection state value of the target light group is the third preset value in the m continuous time instants traced back from the current time instant is greater than or equal to the first preset number, the vehicle state value of the target light group at the current time instant is marked as the third preset value; if the number of times that the vehicle detection state value of the target light group is the second preset value is greater than or equal to the first preset number, the vehicle state value of the target light group at the current time instant is marked as the second preset value, otherwise, the vehicle state value of the target light group at the current time instant is marked as the first preset value; If the number of pedestrians in the pedestrian detection area corresponding to the target light group is greater than or equal to the pedestrian number threshold, the pedestrian state value of the target light group at the current time instant is marked as the first preset value, otherwise, the pedestrian state value of the target light group at the current time instant is marked as the second preset value.

[0039] The target object refers to a traffic participant entity that needs to be monitored and counted in a traffic scene, mainly including vehicles and pedestrians. The import vehicle detection area corresponding to the light group is used to detect vehicles that are about to enter the intersection to judge the real-time traffic demand, and the export vehicle detection area is used to detect vehicles that have entered the intersection but have not left to judge whether there is an overflow risk. Correspondingly, the vehicle number threshold can include an import vehicle number threshold and / or an export vehicle number threshold. It should be noted that when the vehicle detection area corresponding to the light group is only the import vehicle detection area corresponding to the light group, the number of vehicles in the vehicle detection area greater than or equal to the vehicle number threshold can be understood as the number of vehicles in the import vehicle detection area corresponding to the light group greater than or equal to the import vehicle number threshold corresponding to the import vehicle detection area. The vehicle number threshold and the pedestrian number threshold refer to the minimum number of traffic participant entities that determine whether a light group has a traffic demand. When the number of target objects in the detection area reaches or exceeds the threshold, it is considered that there is an effective traffic demand in the direction. The vehicle detection state value refers to the instantaneous state identifier obtained by judging the condition in the import vehicle detection area corresponding to the target light group based on single detection (i.e. one frame of data at the current time instant).

[0040] If the number of vehicles in the import vehicle detection area corresponding to the target light group is empty, it means that the traffic monitoring device associated with the target light group may be offline or transmission interrupted, etc., resulting in no traffic flow sub-data associated with the target light group being obtained. The first preset value, the second preset value and the third preset value can be set according to actual needs, for example, the first preset value can be set to 1, the second preset value can be set to 0, and the third preset value can be set to 2, etc. The import vehicle number threshold can be set to 1 or 3, etc.; m can be set to 8 or 10, etc.; the first preset number is less than m, and the first preset number can be set to 4 or 5, etc.; the pedestrian number threshold can be set to 1 or 2, etc.

[0041] If the number of vehicles in the import vehicle detection area corresponding to the target light group is greater than or equal to the import vehicle quantity threshold, it is indicated that there are vehicles or many vehicles in the import vehicle detection area corresponding to the light group at the current moment, and the vehicle detection state value of the target light group at the current moment is marked as the first preset value. If the number of vehicles in the import vehicle detection area corresponding to the target light group is less than the import vehicle quantity threshold, it is indicated that there may be no vehicle or there are few vehicles in the import vehicle detection area corresponding to the light group at the current moment, and the vehicle detection state value of the target light group at the current moment is marked as the second preset value. When the continuous m moments from the current moment are traced back, if the number of times that the vehicle detection state value of the target light group is the third preset value is greater than or equal to the first preset number, it is indicated that the traffic monitoring device associated with the target light group may have been offline, and the vehicle state value of the target light group at the current moment is marked as the third preset value; if the number of times that the vehicle detection state value of the target light group is the second preset value is greater than or equal to the first preset number, it is indicated that the condition that there is no vehicle or there are few vehicles in the import vehicle detection area corresponding to the light group has lasted for a period of time, and the vehicle state value of the target light group at the current moment is marked as the second preset value; except for the above two cases, the vehicle state value of the target light group at the current moment is marked as the first preset value. In this way, the vehicle state value and the pedestrian state value of each light group in the target stage at the current moment can be accurately and comprehensively obtained, and the vehicle passing efficiency and the pedestrian crossing safety are further improved.

[0042] In an embodiment, according to the vehicle state value and the pedestrian state value of each light group in the target stage at the current moment and the operation control logic, the stage vehicle state value and the stage pedestrian state value of the target stage at the current moment are determined, including at least one of the following: When the operation control logic is the first operation logic, the stage vehicle state value of the target stage at the current moment is marked as the minimum value of the vehicle state value of all light groups in the target stage at the current moment, and the stage pedestrian state value of the target stage at the current moment is marked as the minimum value of the pedestrian state value of all light groups in the target stage at the current moment; When the operation control logic is the second operation logic, if there is at least one light group in the target stage whose vehicle state value at the current moment is the first preset value, the stage vehicle state value of the target stage at the current moment is marked as the first preset value, otherwise the stage vehicle state value of the target stage at the current moment is marked as the minimum value of the vehicle state value of all light groups in the target stage at the current moment; if there is at least one light group whose pedestrian state value is the first preset value, the stage pedestrian state value of the target stage at the current moment is marked as the first preset value, otherwise the stage pedestrian state value of the target stage at the current moment is marked as the second preset value.

[0043] The stage vehicle state value and the stage pedestrian state value refer to comprehensive state judgment conclusions applied to the entire signal stage, and represent the overall traffic demand state of all traffic flows (vehicle flow or pedestrian flow) in the current stage. When the operation control logic is the second operation logic, for the stage vehicle state value, first check whether there is at least one vehicle state value of the vehicle light group in the target stage being the first preset value, such as 1. If there is, directly mark the corresponding stage vehicle state value as the first preset value. Otherwise, mark the minimum value of the vehicle state values of all vehicle light groups. For the stage pedestrian state value, first check whether there is at least one pedestrian state value of the pedestrian light group in the target stage being the first preset value, such as 1. If there is, directly mark the corresponding stage pedestrian state value as the first preset value. Otherwise, mark the second preset value, such as 0. In this way, the operation logic can be configured or dynamically switched according to the time period, the intersection characteristics or the real-time traffic state, so as to balance the control precision and sensitivity and improve the control flexibility.

[0044] In an embodiment, the stage decision value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, including: The stage signal value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time. The stage decision value of the target stage at the current time is determined according to the stage signal value of the target stage at the current time.

[0045] The stage signal value refers to a comprehensive signal based on the current stage vehicle and pedestrian state, which is used to represent the overall traffic condition and health degree of the target stage. It is usually represented by a multi-state discrete value, such as the sixth preset value, such as 1, indicating that there is a clear vehicle or pedestrian traffic demand in at least one direction in the current stage, the fourth preset value, such as 0, indicating that the vehicle and pedestrian traffic demand of all directions in the current stage has been met, and the detection system has failed, and cannot obtain reliable traffic data. Since the stage vehicle state value and the stage pedestrian state value can reflect the overall traffic demand state of all traffic flows (vehicle flow or pedestrian flow) in the current stage, the stage signal value of the target stage at the current time can be determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, and then the stage decision value of the target stage at the current time can be determined according to the stage signal value of the target stage at the current time.

[0046] In an embodiment, the stage signal value of the target stage at the current time is determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, including: If the stage vehicle state value of the target stage at the current time is the first preset value, all light groups in the target stage satisfy the vehicle empty confirmation rate, the stage pedestrian state value of the target stage at the current time is the second preset value, and all light groups in the target stage satisfy the pedestrian empty confirmation rate, the stage signal value of the target stage at the current time is marked as the fourth preset value. If the stage vehicle state value of the target stage at the current time is the third preset value, and all light groups in the target stage satisfy the offline confirmation rate, the stage signal value of the target stage at the current time is marked as the fifth preset value. Otherwise, the stage signal value of the target stage at the current time is marked as the sixth preset value.

[0047] Wherein, the light group satisfies the vehicle empty confirmation rate is that the number of vehicles in the import vehicle detection area corresponding to the light group is less than the preset vehicle number in the first preset number of times of occurrence greater than or equal to the first preset number of times of occurrence in the continuous n time from the current time; The light group satisfies the pedestrian empty confirmation rate is that the number of pedestrians in the pedestrian detection area corresponding to the light group is less than the preset number of pedestrians in the second preset number of times of occurrence greater than or equal to the second preset number of times of occurrence in the continuous n time from the current time; The light group satisfies the offline confirmation rate is that the number of vehicle objects in the import vehicle detection area corresponding to the light group is empty in the third preset number of times of occurrence greater than or equal to the third preset number of times of occurrence in the continuous n time from the current time.

[0048] If the stage vehicle state value of the target stage at the current time is the first preset value, all light groups in the target stage satisfy the vehicle empty confirmation rate, the stage pedestrian state value of the target stage at the current time is the second preset value, and all light groups in the target stage satisfy the pedestrian empty confirmation rate, the stage signal value of the target stage at the current time is marked as the fourth preset value. If the stage vehicle state value of the target stage at the current time is the third preset value, and all light groups in the target stage satisfy the offline confirmation rate, the stage signal value of the target stage at the current time is marked as the fifth preset value. Otherwise, the stage signal value of the target stage at the current time is marked as the sixth preset value.

[0049] The light group meets a vehicle empty confirmation rate if the number of vehicles in the vehicle detection area corresponding to the light group is less than the preset number of vehicles for more than or equal to a first preset number of times in n continuous time instants from the current time instant.

[0050] The phase signal value is a comprehensive signal obtained based on the current phase vehicle and pedestrian state, and is used to represent the overall traffic condition and health degree of the phase. The phase signal value is usually represented by a multi-state discrete value. For example, the sixth preset value, such as 1, is used to represent that there is a clear vehicle or pedestrian traffic demand in at least one direction of the current phase, the fourth preset value, such as 0, is used to represent that the vehicle and pedestrian traffic demands of all directions of the current phase have been met, and the fifth preset value, such as 2, is used to represent that the traffic monitoring device fails to obtain reliable traffic flow data.

[0051] The preset number of vehicles and the preset number of pedestrians can be set according to actual needs. For example, n can be set to 6 or 8, the preset number of vehicles can be set to 2 or 4, and the preset number of pedestrians can be set to 2 or 3. The first preset number of times, the second preset number of times, and the third preset number of times can be set according to the size of n, and are all less than n. For example, the first preset number of times, the second preset number of times, and the third preset number of times can all be set to 2, 3, or 4. In the case that the phase vehicle state value of the target phase at the current time instant is not the first preset value, and / or all light groups of the target phase do not meet the vehicle empty confirmation rate, and / or the phase pedestrian state value of the target phase at the current time instant is not the second preset value and all light groups of the target phase do not meet the pedestrian empty confirmation rate, and / or the phase vehicle state value of the target phase at the current time instant is not the third preset value and / or all light groups of the target phase do not meet the offline confirmation rate, the phase signal value of the target phase at the current time instant is marked as the sixth preset value.

[0052] In an embodiment, the phase decision value of the target phase at the current time instant is determined according to the phase signal value of the target phase at the current time instant, including: determining that the stage decision value of the target stage at the current time is a seventh preset value when a first target condition is met; the first target condition includes any one of the following conditions: the current time has not reached a stage minimum decision time of the target stage, the stage minimum decision time is a difference between a stage length of the target stage and a first preset time length threshold, the first preset time length threshold is a sum of a stage advanceable length of the target stage and a first preset time length; the current time has reached the stage minimum decision time of the target stage but has not reached a stage maximum decision time of the target stage, and a second target condition is met, the stage maximum decision time is a difference between the stage length of the target stage and a second preset time length threshold, the second preset time length threshold is a difference between a stage delayable length and a second preset time length; wherein the second target condition includes any one of the following conditions: the stage signal value of the target stage at the current time is a sixth preset value and there is one target vehicle signal priority request value of a non-target stage that is not a ninth preset value; the stage signal value of the target stage at the current time is the sixth preset value and a stage pedestrian state value of the target stage at the current time is a first preset value; the stage signal value of the target stage at the current time is a fifth preset value, an already running length of the target stage is less than a difference between a stage degradation length of the target stage and a third preset time length threshold, and there is one target vehicle signal priority request value of a non-target stage that is not the ninth preset value; the stage signal value of the target stage at the current time is the fifth preset value, the already running length of the target stage is greater than or equal to a difference between the stage degradation length of the target stage and a fourth preset time length threshold, and the stage pedestrian state value of the target stage at the current time is the first preset value; determining that the stage decision value of the target stage at the current time is an eighth preset value when a third target condition is met; wherein the third target condition includes any one of the following conditions: the current time reaches the stage maximum decision time of the target stage; the current time has reached the stage minimum decision time of the target stage but has not reached the stage maximum decision time of the target stage, and a fourth target condition is met; the fourth target condition includes any one of the following conditions: the stage signal value of the target stage at the current time is a fourth preset value; the stage decision value of the target stage at a previous time is the eighth preset value; the stage signal value of the target stage at the current time is the fifth preset value, the already running length of the target stage is greater than or equal to a difference between the stage degradation length of the target stage and a fifth preset time length threshold, and the stage pedestrian state value of the target stage at the current time is a second preset value; there is one target vehicle signal priority request value of a non-target stage that is the ninth preset value and the stage pedestrian state value of the target stage at the current time is the second preset value.

[0053] If the duration of the target vehicle signal priority state value of the light group existing in the non-target stage being the tenth preset value is greater than or equal to the third preset time length before the current time, the target vehicle signal priority request value of the non-target stage at the current time is marked as the ninth preset value. If the number of target vehicles in the import vehicle detection area corresponding to the light group in the non-target stage at the current time is greater than the preset target vehicle number, the target vehicle signal priority state value of the target light group at the current time is marked as the tenth preset value.

[0054] The stage vehicle state value and the stage pedestrian state value can reflect the overall traffic demand state of all traffic flows (vehicle flow or pedestrian flow) in the current stage. Therefore, the stage signal value of the target stage at the current time can be determined according to the stage vehicle state value and the stage pedestrian state value of the target stage at the current time, and the stage decision value of the target stage at the current time can be determined according to the stage signal value of the target stage at the current time. The target vehicle is a special vehicle with priority right of way, including an ambulance, a fire truck, a police car or other special vehicles. The non-target stage is any stage in the traffic plan except the target stage.

[0055] The stage minimum decision time point refers to the time point at which the system is allowed to make a decision to end the current stage after the start of a signal stage. Before this time point, the current stage must continue regardless of traffic demand to ensure the basic travel time. The stage advanceable time length refers to the maximum time window in which the stage is allowed to start earlier than the planned stage, that is, the stage green light can be turned on earlier than the preset cycle stage, such as 3 seconds or 6 seconds. The first preset time length is a fixed safety buffer time (such as 4 or 5 seconds) to ensure the stability and safety of the decision. The stage maximum decision time point refers to the time point at which the system is allowed to make a decision to end the current stage within a signal stage. After this time point, the system will be forced to end or maintain the stage according to the rules to prevent the stage from being extended indefinitely. The stage delayable time length refers to the maximum time window in which the stage is allowed to end later than the planned stage, that is, the stage green light can be turned off later than the preset cycle stage, such as 4 seconds or 6 seconds. The second preset time length is a fixed processing buffer time (for example, 4 or 5 seconds) to ensure that the control instruction can be issued and executed before the stage actually ends. The stage degradation time length is a kind of backup fixed green light time length, such as 20 seconds or 30 seconds. The target vehicle signal priority request value is a signal used to identify whether an emergency or priority passage request is issued for a non-target stage. For example, it is triggered when a special vehicle such as an ambulance or a fire truck is detected by a 4D radar. The target vehicle signal priority state value refers to the instantaneous state of whether a target vehicle (such as a special vehicle) exists in the import detection area of a single light group. The seventh preset value, the eighth preset value, the ninth preset value, and the tenth preset value can be set according to actual needs, such as setting the seventh preset value to 1, the eighth preset value to 0, the ninth preset value to 3, and the tenth preset value to 1.

[0056] Optionally, when the current time does not reach the stage minimum decision time point of the target stage, it is determined that the target stage cannot be adjusted, and the stage decision value of the target stage at the current time is determined as the seventh preset value. When the current time has reached the stage minimum decision time point of the target stage but has not reached the stage maximum decision time point of the target stage, it is determined that the target stage can be adjusted, and the stage decision value of the target stage at the current time is determined according to one or more of the stage signal value of the target stage at the current time, the stage pedestrian state value of the target stage at the current time, the running time length of the target stage, and the target vehicle signal priority request value of the non-target stage.

[0057] In an embodiment, the running scheme further includes an exit vehicle quantity threshold value corresponding to each light group in the target stage, and the detection area further includes an exit vehicle detection area; the control instruction for controlling the traffic signal lamp of the target intersection is generated according to the stage decision value of the target stage at the current time, and includes: When the stage decision value of the target stage at the current time is the seventh preset value, if there is an overflow signal value of the target light group at the current time being a preset target value and a light state of the target light group being green light, a light group overflow early termination instruction for the target light group is generated; the target light group is any light group in the target stage; When the stage decision value of the target stage at the current time is the eighth preset value, a step instruction for ending the target stage is generated. When the number of vehicles in the exit vehicle detection area corresponding to the target light group is greater than or equal to the exit vehicle quantity threshold, the overflow state value of the target light group at the current time is marked as the first state value, otherwise it is marked as the second state value; when the number of times that the overflow state value of the target light group is the first state value in the k consecutive time instants from the current time reaches the preset overflow number of times, the overflow signal value of the target light group at the current time is marked as the preset target value.

[0058] It should be noted that when the stage signal value of the target stage at the current time is the fifth preset value, and the running duration of the target stage is greater than or equal to the difference between the stage degradation duration of the target stage and the fifth preset duration threshold, it indicates that the traffic monitoring device corresponding to the target light group has offline or other situations, and at this time the running duration of the target stage satisfies the stage end condition, but since the stage pedestrian state value of the target stage at the current time is the second preset value, i.e. there are still pedestrians in the pedestrian detection area corresponding to the target light group, the target stage needs to be continued to execute at this time to ensure the safety of pedestrians crossing the street or pedestrians crossing the street at a slow speed when the green light is about to end, greatly reducing the phenomenon of pedestrian-vehicle conflict.

[0059] Optionally, when the stage decision value of the target stage at the current time is the seventh preset value, it indicates that the target stage can continue to be executed, but when the overflow signal value of the target light group (i.e. any light group in the target stage) at the current time is a preset target value such as 1, it indicates that there are many vehicles in the exit vehicle detection area corresponding to the target light group at the current time, and the vehicles need to be stopped from entering the exit vehicle detection area from the entrance vehicle detection area corresponding to the target light group. Therefore, if the light state of the target light group is green light, a light group overflow early termination instruction for the target light group is generated to adjust the light state of the target light group to red light, and if the light state of the target light group is red light, no control instruction for the target light group is generated. When the stage decision value of the target stage at the current time is the eighth preset value, it indicates that the target stage needs to be ended, and a step instruction for ending the target stage is generated to quickly end the target stage.

[0060] It should be noted that when the signal machine is not integrated on the signal control intelligent device, the signal control intelligent device can send detector instructions corresponding to different lamp groups to the signal machine according to the control instructions, so that the signal machine performs corresponding control operations on the traffic signal lights of the target intersection. In the embodiment, the signal machine and the signal control intelligent device are in communication connection, for example, the signal machine and the signal control intelligent device can communicate through protocol messages. The signal machine can include a local periodic control mode and a coordinated induction control mode. In the local periodic control mode, the signal machine will control the traffic signal lights to perform different traffic plans according to the preset period. In the coordinated induction control mode, the signal machine will control the traffic signal lights according to the control instructions sent by the signal control intelligent device. For example, after receiving the induction control instructions issued by the signal control intelligent device, the signal machine enters the coordinated induction control mode, periodically or in real time sends the running data of the current time to the signal control intelligent device, and at the same time, can control the lamp state of each lamp group of the traffic signal lights of the target intersection according to the control instructions sent by the signal control intelligent device.

[0061] Optionally, the coordinated induction control method provided in the embodiment can further include a parameter configuration page, and a user can configure all the parameters mentioned in the embodiment according to actual needs to adapt to different control scenarios. In addition, it should be understood that the first preset value, the second preset value, the tenth preset value, etc. mentioned in the application are identifiers introduced for the purpose of clearly describing the logical differentiation relationship between different states, signals or requests. The specific values of these preset values (for example, defining the first preset value as 1 and the second preset value as 0) can be any agreement, and the core is that the states they represent are different from each other, and the logical judgment rule is established based on the difference between these states. Those skilled in the art can assign appropriate specific values or enumeration types to them according to actual implementation needs without departing from the protection scope of the application.

[0062] It should be noted that in the embodiment, the stage vehicle state value, the stage pedestrian state value, the stage signal value, the stage decision value and other parameters of other stages at the current time can also be obtained according to the traffic flow data of the target intersection at the current time and the running data of the corresponding traffic signal lights, with reference to the acquisition method of the parameters of each stage of the target stage in the embodiment.

[0063] In summary, the coordination induction control method provided in the above embodiments achieves full-factor and real-time perception of the traffic environment and signal state of the target intersection by obtaining the traffic flow data and operation data of the traffic signal light of the target intersection at the current time. The technical feature of determining the stage vehicle state value and the stage pedestrian state value of the target phase at the current time according to the operation data and the traffic flow data achieves the effect of promoting the pedestrian passing demand to the same importance as the vehicle passing demand in the decision dimension. The technical feature of determining the stage decision value of the target phase at the current time according to the stage vehicle state value and the stage pedestrian state value of the target phase at the current time achieves the fundamental change from static timing control to dynamic demand driving, so that the signal timing can be self-adaptive to the real-time traffic flow change, and the green light time utilization efficiency is significantly improved. The technical feature of generating the control instruction for controlling the traffic signal light of the target intersection according to the stage decision value of the target phase at the current time achieves the effect of converting the intelligent decision result into the action of the on-site device without loss and high efficiency, forming a complete closed-loop automatic control from perception, decision to execution. That is, the coordination induction control method provided in the present application can respond to the dynamic change of the traffic demand in real time and control the traffic signal light accordingly, without setting the cycle length of the passing scheme as a fixed value, especially without setting the green light length of each phase in the passing scheme as a fixed value, and achieving the comprehensive technical effect of optimizing the vehicle passing efficiency and pedestrian crossing safety, while greatly reducing the application cost of induction control, laying a foundation for building a low-cost and high-reliable intelligent traffic control system.

[0064] Based on the same inventive concept as the foregoing embodiments, the coordination induction control method provided in the present embodiment will be specifically described below through a specific example. In the example, the traffic monitoring device is taken as the perception device, the signal control intelligent device is taken as the signal control intelligent agent, the target vehicle is taken as the special vehicle, the stage vehicle state value is taken as the stage-level vehicle light group state value, and the stage pedestrian state value is taken as the stage-level pedestrian light group state value.

[0065] The coordination induction control method provided in the present embodiment can be implemented by a coordination induction control system, which can include a perception device, a signal machine, a signal control intelligent agent in communication connection with the perception device and the signal machine, and an intelligent signal control platform in communication connection with the signal machine and the signal control intelligent agent. The functions of each part of the system will be described below: 1) Perception device: including but not limited to 4D radar, electric police, card slot, flow camera and radar vision device, etc., providing stable video stream and radar detection data for the signal control intelligent agent.

[0066] 2) Signal control intelligent agent (also referred to as edge computing box) includes four functional modules or functions of detection analysis, scheme reading, control decision and instruction output. Among them, 21) Detection analysis: video picture object recognition extracts detection parameters or receives structured data obtained through radar detection data, obtains the number of motor vehicles and / or the number of pedestrians in the target detection area. The target detection area includes a vehicle detection area and / or a pedestrian detection area.

[0067] 211) Generation of structured data based on secondary analysis of video stream: ① Full-amount recognition: full-amount recognition of traffic objects in video stream pictures; ② Data statistics: set a target detection area in the form of an arbitrary octagon in the video annotation range, and select motor vehicle or pedestrian recognition algorithm to count the number of motor vehicles or pedestrians in the detection area.

[0068] 212) Reception of structured data: receive the number of motor vehicles or pedestrians in the target detection area detected by radar-type equipment according to the protocol.

[0069] 22) Scheme reading: ① Light state reading: the intelligent signal control body reads the signal machine message through the protocol or the intelligent signal control platform, and obtains the running scheme number, stage number and light state at the current time; ② Parameter configuration: comprehensively configure the global general parameters of the current running timing scheme, intersection channelization and traffic organization initialization.

[0070] 23) Control decision: ① Coordination control: determine whether the current stage is continued based on the light state, traffic state, coordination period and the advanceable and delayable lengths of the current stage; ② Overflow control: early terminate the current release to the overflow exit light group for the overflow of exit vehicles; ③ Period switching: switch the period within the time period and the period at the time period transition based on the time period; ④ Clock calibration: evaluate whether the preset light group difference is met at a certain interval, and automatically calibrate and record the running time of the intersection signal machine.

[0071] 24) Instruction output: ① Light group instruction: the signal machine in the sensing mode communicates with the light group and the instruction; ② Detection data: the signal machine in the sensing mode communicates with the light group and the detection data; ③ Step-by-step instruction: the intelligent signal control body issues a step-by-step instruction to the signal machine to quickly end the current stage and enter the next stage; ④ Calibration instruction: the intelligent signal control body issues a calibration instruction to the signal machine, and the signal machine interacts with the intelligent signal control platform to update the clock.

[0072] 3) The signal machine includes scheme configuration, control mode setting and output light state, and receives execution instructions. Among them: ① Scheme configuration: the light group setting, stage setting, scheme setting, time period setting and plan setting required by the signal machine in the "local fixed period" mode; ② Control mode setting: at least provide "local fixed period" and "local sensing" modes; ③ Output light state: provide the signal control intelligent body with the scheme number, stage number and light group light state running at the current time; ④ Receive execution instruction: the signal machine receives the instruction issued by the intelligent signal control body, and performs stage extension, stage termination, light group early termination, stage control mode degradation and recovery, etc.

[0073] Based on the above coordinated induction control system, the coordinated induction control method provided by the embodiment includes the following processes: S1) Signal machine scheme configuration.

[0074] Specifically, based on the timing scheme of the target intersection, the signal machine respectively performs group setting, stage setting, scheme setting, period setting and plan setting. Among them, the group setting: configuring the number of corresponding traffic monitoring devices, the minimum green light time, the maximum green light time and the unit green light parameter for each group on the group setting interface. Stage setting: configuring corresponding group, yellow flash, all red, delay, early break and other parameters for each stage on the stage setting interface. Scheme setting: adding target stages one by one on the scheme setting interface and configuring corresponding green light time parameters. Period setting: configuring schemes for each time period on the period setting interface, and selecting control modes in the corresponding operation mode. Plan setting: setting the operation scheme on the plan setting interface, such as selecting the operation scheme from Sunday to Saturday if it is the same every day.

[0075] S2) Signal control agent communicates with signal machine, sensing device and system configuration.

[0076] S21) Signal machine access: protocol docking between signal control agent and signal machine, realizing real-time state active reporting, real-time state query and response and control instruction issuing.

[0077] S211) Signal machine real-time state active reporting: signal machine actively sends real-time state information to the host computer, i.e. intelligent signal control platform and signal control agent, every message sending interval is 1 second, and the message should include at least the following state information, see Table 1.

[0078] Table 1 S212) Query signal machine state: the host computer sends real-time state query to the signal machine the running scheme number and stage number of the signal machine at the moment and the group light state instruction, the signal machine immediately replies the real-time state information, the message content is the same as shown in Table 1.

[0079] S213) Issue control instruction: signal control agent sends control instruction to signal machine or intelligent signal control platform, and requires signal machine to execute immediately.

[0080] S22) Access multi-modal data and convert into structured data: if it is radar data, directly generate structured data and enter step S221); if it is video data, secondary video analysis is needed and enter S222).

[0081] S221) Access structured data: receive structured data to directly enable subsequent calculation.

[0082] S222)Access video stream data: Use the trained YOLO model to identify objects in the target video stream, then configure the vehicle detection area (i.e. vehicle detection area) and pedestrian detection area bound to the light group to generate structured data in real time.

[0083] S2221)Video management: Configure the information of the video, for example, set the police number, police number, police IP, online video stream address, police direction, model parameter, whether to enable, video width, video height information.

[0084] S2222)Object recognition: Use the trained YOLO model to identify objects, then configure the vehicle detection area (i.e. import vehicle detection area and export vehicle detection area) and pedestrian detection area bound to the light group to generate structured data in real time.

[0085] S2223)Classification configuration detection area: Select the target video, screenshot, add the octagonal coil and name, such as east straight lane 1.

[0086] S2224)Edit coil information: Configure coil ID, coil name, whether to enable, bind video number, light group number, coil type and coil detection target information, and confirm saving.

[0087] S2225)Coil configuration: Includes import lane detection, export lane detection and sidewalk detection.

[0088] S23)System configuration: Includes scheme editing, stage editing, light group editing and confirmation rate editing.

[0089] S231)Scheme editing: Based on the operation scheme of the signal machine, configure the parameters of the corresponding stage in the intelligent body, such as selection stage, jump stage, main stage, whether to start induction coordination, light group difference and stage parameters.

[0090] S2311)Selection stage: Select the stage already configured in the selection stage editing.

[0091] S2312)Jump stage: If the jump stage is started, it supports skipping the stage without demand when running the current scheme; otherwise, it runs according to the preset stage order.

[0092] S2313)Main stage: The most critical stage in the scheme, if there is no demand for each stage, run the main stage.

[0093] S2314)Start induction coordination: If the induction coordination is started, after entering the coordination induction mode, each stage calls the light group difference, operation logic, stage duration, stage can be ahead of time and stage delay time parameters.

[0094] S23141) Lamp group difference: the calculation interval of the start time of the first stage in the cycle and the system unified reference time, in seconds.

[0095] S232) Stage editing: configure stage parameters, operation logic, stage minimum green light duration, stage maximum green light duration, stage degradation duration, stage delayable duration, stage duration, stage advanceable duration, stage delayable duration (coordination parameters).

[0096] S2321) Configure stage parameters: synchronize the phase number of the signal with the control agent, or configure the phase name, vehicle lamp group and pedestrian lamp group according to the phase number; S2322) Operation logic: provide "tight" and "loose" two kinds of logic operation to adapt to the number of pedestrians and vehicles required for the termination of the timing scheme in different periods and threshold logic judgment.

[0097] S2323) Stage minimum green light duration : the minimum green light duration of the stage under the current scheme (not including yellow flash, all red), in seconds.

[0098] S2324) Stage maximum green light duration : the maximum green light duration of the stage under the current scheme (not including yellow flash, all red), in seconds.

[0099] S2325) Stage degradation duration : the green light duration of the stage under the current period control scheme, in seconds.

[0100] S2326) Stage delayable duration : the green light duration that continues to delay when the number of current stages is less than the threshold value and will terminate, in seconds.

[0101] S2327) Stage advanceable duration : the duration of the current stage green light based on the actual demand compared to the preset period stage, in seconds.

[0102] S2328) Stage delayable duration : the duration of the current stage green light based on the actual demand compared to the preset period stage, in seconds.

[0103] S233) Lamp group editing: configure lamp group name, lamp group type, priority vehicle threshold, import vehicle number threshold, export vehicle number threshold and pedestrian number threshold for each lamp group number.

[0104] S2331) Lamp group name: set the lamp group name according to the general lamp group direction, such as east straight.

[0105] S2332) Light type: Includes three types: motor vehicles, pedestrians and non-motor vehicles; S2333) Threshold for the number of imported vehicles : Imported vehicle inspection area linked to the light cluster The threshold for the number of vehicles.

[0106] S2334) Threshold for the number of exported vehicles : The exit inspection area bound to the light assembly The threshold for the number of vehicles.

[0107] S2335) Pedestrian Threshold : Pedestrian detection zone linked to the light group The threshold for the number of pedestrians.

[0108] S233) Confirmation Rate Editing: Includes abnormal parking confirmation rate, overflow demand confirmation rate, offline confirmation rate, empty vehicle confirmation rate, empty pedestrian confirmation rate, and stage demand confirmation rate.

[0109] S2331) Abnormal Parking Confirmation Rate :continuous This time, vehicles in the import lane repeatedly appeared at the same location. Second-rate.

[0110] S2332) Overflow Demand Confirmation Rate :continuous The number of vehicles overflowing the coil exceeds the threshold. The cumulative number of times reached Second-rate.

[0111] S2334) Offline Confirmation Rate :continuous The cumulative number of times frames could not be retrieved reached [number]. Second-rate.

[0112] S2335) Vehicle Emptying Confirmation Rate :continuous Next, current traffic light group The number of vehicles in the designated imported vehicle inspection area is less than the threshold. The number of times it appears at least Second-rate.

[0113] S2336) Pedestrian Vacancy Confirmation Rate :continuous Next, current traffic light group The number of pedestrians in the bound pedestrian detection area is less than the threshold. The number of times it appears at least Second-rate.

[0114] S3) Edge computing box operation coordination sensing mode: The signal control agent issues temporary cycle plans to the signal controller, analyzes the preset stage parameters, and makes stage decisions based on the signal controller's operating status and real-time traffic environment.

[0115] S31) Issuing a temporary cycle plan: At the end of each cycle, the signal control agent issues a temporary cycle plan to the signal controller. The duration of each phase is the maximum green light duration of the phase by default. S32) Analyze preset stage parameters: based on time period parameters, coordination stage, light group difference, cycle plan and system reference time. T 0 (Default is 0:00:00), etc., determine the preset start time of the periodic scheme, the preset end time of the periodic scheme stage, the preset start segment of the stage, the transition duration of the scheme, and the stage duration of the transition scheme. The calculation method is as follows: S321) Preset start time for the calculation period scheme: the first The first time period Each cycle scheme has a preset start time. : : No. The cycle duration of the signal scheme for each time period; : No. The absolute phase difference of the signal scheme for each time period.

[0116] S322) Preset termination time for the calculation cycle scheme stage: the first The first time period The first cycle scheme The preset termination time of each stage : : No. The signal scheme for the [number] time period [number] Each stage lasts for a period of time.

[0117] S323) Preset starting section in the calculation stage : No. The first time period The first cycle scheme The preset starting section of each stage : S324) Calculate the duration of the transition scheme If the start time of the new phase If the current frame is in the preset start section of the corresponding cycle plan phase, the transition duration is 0 (phase alignment); otherwise, the transition duration is the start time of the next cycle Subtract the start time of the current phase (Phase misalignment), that is .

[0118] S325) Calculate the phase duration of the transition plan : If the transition duration is not less than the phase transition threshold times the sum of the remaining phase duration containing the current phase (default 0.8), the phase duration is scaled by equal ratio; otherwise, the phase duration of the transition is scaled by equal ratio Add the cycle value to scale by equal ratio, that is .

[0119] S33) Phase decision: based on the device online state, export overflow state, import detection area vehicle number and pedestrian number and system parameters to make phase decision, including phase level vehicle and pedestrian state value, phase signal value, phase decision value and instruction issuing, the specific steps are as follows: S331) Phase vehicle and pedestrian state value: judge whether the vehicle and pedestrian demand in the current frame phase meets the threshold, including calculating vehicle detection state value, vehicle light group state value and pedestrian detection state value.

[0120] S3311) Vehicle detection state value vds_car: if the number of vehicles in the import vehicle detection area corresponding to the light group of the current frame is greater than 1, the value is 1; if the number of vehicles in the import vehicle detection area corresponding to the light group is -1 (due to detector falling off, etc.), the value is 2, otherwise the value is 0.

[0121] S3312) Vehicle light group state value vv_status: take the data of the past m frames, if the vehicle detection state value is 2 and appears at least n times, the vehicle light group state value is 2; if the vehicle detection state value is 0 and appears at least n frames, the vehicle light group state value is 0; otherwise, it is 1.

[0122] S3313) Pedestrian detection state value vds_person: if the number of pedestrians in the pedestrian detection area is greater than 1, the value is 1, otherwise the value is 0.

[0123] S3314) Phase level vehicle and pedestrian state value: calculate the phase level vehicle and pedestrian state value by using "tight logic" and "loose logic".

[0124] ​S33141) "tight logic": the phase-level vehicle group state value takes the minimum value of the vehicle detection state values corresponding to the group within the phase; the phase-level pedestrian group state value takes the minimum value of the pedestrian detection state values corresponding to the group within the phase.

[0125] S33142) "loose logic": if there is a value of 1 in the vehicle detection state values corresponding to the group within the phase, the phase-level vehicle group state value is 1, otherwise the minimum value of the vehicle detection state values corresponding to the group within the phase is taken (e.g. 0, 0 takes 0, 0, 2 takes 2, only 2, 2 takes 2); if there is a value of 1 in the pedestrian detection state values corresponding to the group within the phase, the phase-level pedestrian group state value is 1, otherwise 0 is taken.

[0126] S332) phase signal value: determine whether there is a traffic demand or the detector is empty data in the current phase, the value range is 0, 1, 2, 3.

[0127] S3321) if the phase-level vehicle group state value is 0, all groups in the phase satisfy the car empty release confirmation rate confirmation_null_car, and the phase-level pedestrian group state value is 0 and satisfies the pedestrian empty release confirmation rate confirmation_null_pedestrian, then the phase signal value is 0; if the phase-level vehicle group state value is 2 and satisfies the offline (empty data) confirmation rate confirmation_offline, then the phase signal value is 2, otherwise the phase signal value is 1.

[0128] S3322) if the phase signal value is 2, then at the time when the current phase has been running for a time equal to (phase degradation duration - phase minimum decision time), the pedestrian group can be controlled to end at this time, and the motor vehicle group continues to run until the degradation time. If the phase-level pedestrian group state value is > 0, the motor vehicle group of the current phase continues, otherwise the current phase ends. In this way, the safety of green tail crossing or pedestrians with slow crossing speed is ensured, and the conflict between this part of people and vehicles is greatly reduced.

[0129] S333) phase decision: determine whether the current phase continues or terminates based on the phase signal value.

[0130] S3331) phase continuation: if the phase decision value value_stage_decision is 1, the phase continues to run, and the phase decision value is initialized to 1, the following cases take 1: S33311) the current time < phase minimum decision time min_stage_decision, then the phase decision value takes 1. Wherein, the phase minimum decision time = phase duration - phase advanceable duration - 5; the phase maximum decision time = phase duration + phase delayable duration - 5.

[0131] S33312) The current time is between the minimum decision time of the stage min_stage_decision and the maximum decision time of the stage max_stage_decision (closed at the front and open at the rear) and meets one of the following conditions: S333121) The stage signal value is 1, and the target vehicle signal priority request value of the non-P stage is not 3; the non-P stage is any stage other than the current stage (i.e., the P stage); S333122) The stage signal value is 1, and the stage level pedestrian lamp group state value is 1; S333123) The stage signal value is 2, the P stage has been running for < (stage degradation time - 4), and the target vehicle signal priority request value of the non-P stage is not 3; S333124) The stage signal value is 2, the P stage has been running for >= (stage degradation time - 4), and the stage level pedestrian lamp group state value is 1; S333125) The stage signal value is 3.

[0132] S3332) Stage end: when the stage decision value value_stage_decision is 0, the stage ends, and the stage decision value is 0 in the following cases: S33321) When the current time is between the minimum decision time of the stage min_stage_decision and the maximum decision time of the stage max_stage_decision (closed at the front and open at the rear), any of the following conditions is met: ① The stage signal value value_stage_signal is 0; ② The stage decision value of the previous second is 0; ③ The stage signal value takes 2 and the stage has been running for more than stage degradation time - 4, and the P stage (i.e., the current stage) pedestrian lamp group state value is 0; ④ The target vehicle signal priority request value of the non-P stage is 3 and the P stage pedestrian lamp group state value is 0.

[0133] S33322) The current time > the maximum decision time of the stage.

[0134] S334) Issue stage or lamp group end instruction: control the stage or lamp group light state through protocol instruction.

[0135] S3341) End stage instruction: if the current stage is continued and is in green light state, no instruction is sent; otherwise, a "step" instruction is issued.

[0136] S3342) End lamp group instruction in advance: if the current lamp group is continued and is in green light state, no instruction is sent; otherwise, when the exit overflows, an "overflow" instruction is issued to the corresponding lamp group to early break the green light state of the lamp group.

[0137] S335) Update Return to step S331).

[0138] S4) Evaluate and optimize the edge computing box basic parameters.

[0139] In summary, for the light-controlled intersection induction control, expensive traffic detection equipment needs to be installed, the fixed light group phase sequence does not adapt to asymmetric traffic flow, the termination of the pedestrian green light does not consider the safety of pedestrians crossing the street, the outlet overflow cannot be early broken, and the signal machine is degraded as a whole after the light group and detection equipment are offline, etc. The above problems lead to the problem that the application range of the induction light-controlled intersection is less. In the coordination induction control method provided in the above embodiments, based on the existing electric police or card slot facilities of the light-controlled intersection, an edge computing device is installed on the signal machine, video stream is used as input, video analysis technology is used to count the number of import vehicles, the number of pedestrians on the sidewalk and the number of export vehicles, the vehicle and pedestrian induction control method is combined, and the light group signal value is output to the signal machine running in the induction control mode to realize the phase extension, phase termination, light group early stage and phase control mode degradation and recovery of the timing scheme, which greatly reduces the application cost of the induction control, improves the safety of pedestrians crossing the street and the vehicle passing efficiency.

[0140] The embodiments of the present application also provide an electronic device, including a processor and a memory, the memory stores computer program instructions for executing on the processor, and the processor executes the computer program instructions to realize the coordination induction control method as described above. Wherein, the electronic device can be a signal control intelligent device, an edge computing device or a signal control intelligent body.

[0141] The embodiments of the present application also provide a computer readable storage medium, which stores computer instructions, and the computer instructions are run by a processor to realize the coordination induction control method according to the above description.

Claims

1. A coordinated inductive control method, characterized in that, The method includes: Obtain traffic flow data and corresponding traffic light operation data for the target intersection at the current moment; the operation data includes the operation plan, the target stage of execution, and the light status of each light group in the target stage; Based on operational data and traffic flow data, determine the stage vehicle status value and stage pedestrian status value at the current moment for the target stage; Based on the vehicle state value and pedestrian state value of the target stage at the current moment, determine the stage decision value of the target stage at the current moment; Based on the target stage's current stage decision value, generate control instructions for controlling the traffic lights at the target intersection.

2. The method as described in claim 1, characterized in that, The operational plan includes the computational control logic and the threshold number of target objects corresponding to each light group in the target phase; based on operational data and traffic flow data, it determines the phase vehicle state value and phase pedestrian state value at the current moment in the target phase, including: Traffic flow data is analyzed by light group association detection to obtain the detection results of traffic flow sub-data associated with each light group in the target stage; Based on the threshold number of target objects corresponding to each light group in the target phase and the detection results of traffic flow data associated with each light group in the target phase, determine the vehicle status value and pedestrian status value of each light group in the target phase at the current time. Based on the vehicle and pedestrian status values ​​of each light group in the target phase at the current moment, as well as the calculation and control logic, determine the phase vehicle and pedestrian status values ​​of the target phase at the current moment.

3. The method as described in claim 2, characterized in that, The detection results include the number of target objects within the detection area corresponding to the light group; the target objects include vehicles and pedestrians, the detection areas include imported vehicle detection areas and pedestrian detection areas, and the target object number thresholds include imported vehicle number thresholds and pedestrian number thresholds. Based on the threshold number of target objects corresponding to each light group in the target phase and the detection results of traffic flow sub-data associated with each light group in the target phase, the vehicle state value and pedestrian state value of each light group in the target phase at the current time are determined, including: At the current moment, if the number of vehicles in the import vehicle detection area corresponding to the target light group is empty, the vehicle detection status value of the target light group at the current moment is marked as the third preset value; if the number of vehicles in the import vehicle detection area corresponding to the target light group is greater than or equal to the import vehicle number threshold, the vehicle detection status value of the target light group at the current moment is marked as the first preset value; otherwise, the vehicle detection status value of the target light group at the current moment is marked as the second preset value; the target light group is any light group whose light status is green during the target phase. If, in the m consecutive moments preceding the current moment, the number of times the vehicle detection status value of the target light group is greater than or equal to ... If the number of pedestrians in the pedestrian detection area corresponding to the target light group is greater than or equal to the pedestrian number threshold, then the pedestrian status value of the target light group at the current time is marked as the first preset value; otherwise, the pedestrian status value of the target light group at the current time is marked as the second preset value.

4. The method as described in claim 3, characterized in that, Based on the vehicle and pedestrian status values ​​of each light group in the target phase at the current moment, and the calculation control logic, determine the phase vehicle status value and phase pedestrian status value of the target phase at the current moment, including at least one of the following: When the operation control logic is the first operation logic, mark the vehicle state value of the target stage at the current time as the minimum value of the vehicle state value of all light groups in the target stage at the current time, and mark the pedestrian state value of the target stage at the current time as the minimum value of the pedestrian state value of all light groups in the target stage at the current time. When the operation control logic is the second operation logic, if at least one light group in the target stage has a vehicle state value of the first preset value at the current time, then mark the target stage vehicle state value at the current time as the first preset value; otherwise, mark the target stage vehicle state value at the current time as the minimum value of the vehicle state values ​​of all light groups in the target stage at the current time. If at least one light group in the target phase has a pedestrian status value of the first preset value, then mark the pedestrian status value of the target phase at the current moment as the first preset value; otherwise, mark the pedestrian status value of the target phase at the current moment as the second preset value.

5. The method according to any one of claims 1 to 4, characterized in that, Based on the vehicle state value and pedestrian state value of the target stage at the current moment, determine the stage decision value of the target stage at the current moment, including: Based on the vehicle state value and pedestrian state value of the target stage at the current moment, determine the stage signal value of the target stage at the current moment; Based on the target stage's stage signal value at the current moment, determine the target stage's stage decision value at the current moment.

6. The method as described in claim 5, characterized in that, Based on the vehicle state value and pedestrian state value of the target stage at the current moment, determine the stage signal value of the target stage at the current moment, including: If the vehicle status value of the target stage at the current moment is the first preset value and all light groups in the target stage meet the vehicle idle release confirmation rate, and the pedestrian status value of the target stage at the current moment is the second preset value and all light groups in the target stage meet the pedestrian idle release confirmation rate, then mark the stage signal value of the target stage at the current moment as the fourth preset value. If the vehicle status value of the target stage at the current moment is the third preset value and all light groups in the target stage meet the offline confirmation rate, then mark the stage signal value of the target stage at the current moment as the fifth preset value. Otherwise, the stage signal value of the target stage at the current moment is the sixth preset value; Specifically, the vehicle vacancy confirmation rate of a light group is such that, in a consecutive n-timeframe from the current time, the number of times the number of vehicles in the import vehicle detection area corresponding to that light group is less than a preset number of vehicles is greater than or equal to a first preset occurrence number; the pedestrian vacancy confirmation rate of a light group is such that, in a consecutive n-timeframe from the current time, the number of times the number of pedestrians in the pedestrian detection area corresponding to that light group is less than a preset number of pedestrians is greater than or equal to a second preset occurrence number; and the offline confirmation rate of a light group is such that, in a consecutive n-timeframe from the current time, the number of times the number of vehicles in the import vehicle detection area corresponding to that light group is empty is greater than or equal to a third preset occurrence number.

7. The method as described in claim 6, characterized in that, Based on the target stage's stage signal value at the current moment, determine the target stage's stage decision value at the current moment, including: When the first objective condition is met, the stage decision value of the target stage at the current moment is determined to be the seventh preset value; the first objective condition includes any one of the following conditions: the current moment has not reached the minimum decision moment of the target stage, where the minimum decision moment is the difference between the stage duration of the target stage and the first preset duration threshold, and the first preset duration threshold is the sum of the stage advance duration of the target stage and the first preset duration; when the current moment has reached the minimum decision moment of the target stage but has not reached the maximum decision moment of the target stage, and the second objective condition is met, where the maximum decision moment is the difference between the stage duration of the target stage and the second preset duration threshold, and the second preset duration threshold is the difference between the stage delay duration and the second preset duration; wherein, the second objective condition includes any one of the following conditions: target stage The current stage signal value is the sixth preset value and there is a non-target stage target vehicle signal priority request value that is not the ninth preset value; the target stage's current stage signal value is the sixth preset value and the target stage's current stage pedestrian status value is the first preset value; the target stage's current stage signal value is the fifth preset value, the target stage's elapsed duration is less than the difference between the target stage's stage downgrade duration and the third preset duration threshold, and there is a non-target stage target vehicle signal priority request value that is not the ninth preset value; the target stage's current stage signal value is the fifth preset value, the target stage's elapsed duration is greater than or equal to the difference between the target stage's stage downgrade duration and the fourth preset duration threshold, and the target stage's current stage pedestrian status value is the first preset value; When the third objective condition is met, the stage decision value of the target stage at the current moment is determined to be the eighth preset value; wherein, the third objective condition includes any one of the following conditions: the current moment reaches the maximum stage decision time of the target stage; the current moment has reached the minimum stage decision time of the target stage but has not reached the maximum stage decision time of the target stage, and the fourth objective condition is met; the fourth objective condition includes any one of the following conditions: the stage signal value of the target stage at the current moment is the fourth preset value; the stage decision value of the target stage at the previous moment is the eighth preset value; the stage signal value of the target stage at the current moment is the fifth preset value, the running length of the target stage is greater than or equal to the difference between the stage degradation time of the target stage and the fifth preset time threshold, and the stage pedestrian state value of the target stage at the current moment is the second preset value; there exists a target vehicle signal priority request value that is not in the target stage and the stage pedestrian state value of the target stage at the current moment is the second preset value; Specifically, if, up to the current moment, the duration of the target vehicle signal priority status value of a light group in the non-target phase is greater than or equal to the third preset duration, then the target vehicle signal priority request value in the non-target phase at the current moment is marked as the ninth preset value; if, at the current moment, the number of target vehicles in the import vehicle detection area corresponding to that light group in the non-target phase is greater than the preset number of target vehicles, then the target vehicle signal priority status value of the target light group at the current moment is marked as the tenth preset value; the target vehicle is a special vehicle with priority right-of-way.

8. The method as described in claim 7, characterized in that, The operation plan also includes the threshold number of exit vehicles corresponding to each light group in the target phase, and the detection area also includes the exit vehicle detection area; Based on the target stage's stage decision value at the current moment, control instructions are generated for controlling the traffic lights at the target intersection, including: When the stage decision value of the target stage at the current moment is the seventh preset value, if there is a target light group whose overflow signal value at the current moment is the preset target value and the light state of the target light group is green, then a light group overflow early interruption instruction for the target light group is generated; the target light group is any light group within the target stage. When the target stage's stage decision value at the current moment is the eighth preset value, a step instruction to end the target stage is generated. Specifically, when the number of vehicles in the exit vehicle detection area corresponding to the target light group is greater than or equal to the exit vehicle number threshold, the overflow state value of the target light group at the current moment is marked as the first state value; otherwise, it is marked as the second state value. When the number of times the overflow state value of the target light group is the first state value in the k consecutive moments traced back from the current moment reaches the preset overflow number, the overflow signal value of the target light group at the current moment is marked as the preset target value.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer program instructions for execution on the processor, wherein when the processor executes the computer program instructions, it implements the coordinated sensing control method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, It stores computer instructions, which, when executed by a processor, implement the coordinated sensing control method as described in any one of claims 1-8.

Images