CN110322687B

CN110322687B - Method and device for determining running state information of target intersection

Info

Publication number: CN110322687B
Application number: CN201810292311.8A
Authority: CN
Inventors: 郑立勇; 郝勇刚; 沈烨峰; 杨旭; 郭旭; 杨宇辰
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2018-03-30
Filing date: 2018-03-30
Publication date: 2021-06-11
Anticipated expiration: 2038-03-30
Also published as: CN110322687A

Abstract

The invention discloses a method and a device for determining running state information of a target intersection, and belongs to the field of intelligent traffic systems. The method comprises the following steps: acquiring a vehicle passing video of each entrance lane of the target intersection, which is acquired by a camera device; determining traffic flow parameters of the target intersection based on the vehicle passing video of each entrance lane of the target intersection; and simulating the vehicle running process of the target intersection based on the traffic flow parameters of the target intersection, and determining the running state information of the target intersection based on the vehicle running process obtained by simulation. By adopting the invention, the accuracy of the running state information of the target intersection can be improved.

Description

Method and device for determining running state information of target intersection

Technical Field

The invention relates to the field of intelligent traffic systems, in particular to a method and a device for determining running state information of a target intersection.

Background

The intersection of the urban road is a place with high congestion and high accident occurrence, intersection improvement and optimization need to be implemented, and accurate and comprehensive evaluation of the running state of the intersection is a precondition for implementing the intersection improvement and optimization.

A coil detector can be embedded in the entrance way of the intersection. When the vehicle passes through the coil detector, the coil detector can detect the arrival time and the running speed of the vehicle and upload the detected traffic flow parameters to the server. Furthermore, the server can perform statistical analysis on the traffic distribution of the lanes, the lane occupancy and the like, evaluate the running state of the intersection and obtain running state information such as the delay time of the vehicle average, the number of times of the vehicle average parking, the average queuing length and the like.

In the process of implementing the invention, the inventor finds that the prior art has at least the following problems:

the existing coil detectors generally have the problems of high damage rate, short battery life, easiness in electromagnetic interference and the like, and errors exist between detected traffic flow parameters and actual conditions easily, so that the method for acquiring the traffic flow parameters by adopting the coil detectors is low in reliability, and the accuracy of running state information of intersections obtained based on the traffic flow parameters is low.

Disclosure of Invention

In order to solve the problems in the prior art, embodiments of the present invention provide a method and an apparatus for determining running state information of a target intersection. The technical scheme is as follows:

in a first aspect, a method for determining running state information of a target intersection is provided, and the method includes:

acquiring a vehicle passing video of each entrance lane of the target intersection, which is acquired by a camera device;

determining traffic flow parameters of the target intersection based on the vehicle passing video of each entrance lane of the target intersection;

and simulating the vehicle running process of the target intersection based on the traffic flow parameters of the target intersection, and determining the running state information of the target intersection based on the vehicle running process obtained by simulation.

Optionally, the traffic flow parameter includes one or more parameters of an average vehicle speed, a vehicle flow rate corresponding to each entrance lane, a vehicle proportion in each driving direction corresponding to each entrance lane, and a large vehicle proportion corresponding to each entrance lane;

the running state information comprises one or more of vehicle average delay time, vehicle average stop times, average queuing length and simulated vehicle average speed.

Optionally, each entrance lane includes at least one lane, and determining the traffic flow parameter of the target intersection based on the vehicle-passing video of each entrance lane of the target intersection includes:

determining vehicle passing data of each vehicle in the vehicle passing videos based on the vehicle passing videos of each entrance lane of the target intersection, wherein the vehicle passing data comprises one or more data of license plate numbers, vehicle type information, lane information and vehicle speeds;

and determining traffic flow parameters of the target intersection based on the vehicle passing data of each vehicle at the target intersection.

Optionally, if the traffic flow parameter includes an average vehicle speed, the vehicle speed is included in the vehicle passing data, and determining the traffic flow parameter of the target intersection based on the vehicle passing data of each vehicle at the target intersection includes:

determining an average speed of vehicles at the intersection based on the vehicle speed of each vehicle at the intersection.

Optionally, the determining the average speed of the vehicles at the intersection based on the vehicle speed of each vehicle at the intersection comprises:

and sequencing the vehicle speeds of all the vehicles at the target intersection, and determining the median of all the vehicle speeds as the average vehicle speed of the target intersection.

Optionally, if the traffic flow parameter includes a vehicle flow corresponding to each entrance lane, the determining the traffic flow parameter of the target intersection based on the vehicle passing data of each vehicle at the target intersection includes:

and determining the traffic flow corresponding to each entrance lane of the target intersection based on the number of the vehicle passing data corresponding to each entrance lane of the target intersection.

Optionally, if the traffic flow parameters include vehicle proportions in each driving direction corresponding to each entrance lane, the vehicle passing data includes lane information, and the determining the traffic flow parameters of the target intersection based on the vehicle passing data of each vehicle at the target intersection includes:

determining the driving direction of each vehicle corresponding to each entrance way of the target intersection based on the lane information of each vehicle corresponding to each entrance way of the target intersection and the corresponding relationship between the lane information of each entrance way and the driving direction, which is stored in advance;

and determining the vehicle proportion of each driving direction corresponding to each entrance lane of the target intersection based on the number of the vehicles in different driving directions corresponding to each entrance lane.

Optionally, if the traffic flow parameters include vehicle proportions in each driving direction corresponding to each entrance lane, the vehicle passing data includes a license plate number, and the determining the traffic flow parameters of the target intersection based on the vehicle passing data of each vehicle at the target intersection includes:

for each entrance lane of the target intersection, searching all target passing data with the same license plate number as the passing data of the entrance lane in the passing data of each adjacent intersection of the target intersection, and determining the vehicle proportion of each driving direction corresponding to the entrance lane according to the number of the searched target passing data of each adjacent intersection.

Optionally, if the traffic flow parameters include a ratio of large vehicles corresponding to each entrance lane, the vehicle passing data includes vehicle type information, and the determining the traffic flow parameters of the target intersection based on the vehicle passing data of each vehicle at the target intersection includes:

and determining the proportion of the large vehicles corresponding to each entrance lane of the target intersection based on the number of the vehicle passing data of the large vehicles corresponding to each entrance lane and the number of the vehicle passing data corresponding to each entrance lane.

Optionally, the acquiring the vehicle-passing video of each entrance lane of the target intersection, which is acquired by the camera device, includes:

when a preset detection period is reached, acquiring a vehicle passing video of each entrance lane of the target intersection, which is acquired by a camera in the current detection period;

the method comprises the following steps of simulating the vehicle running process of the target intersection based on the traffic flow parameters of the target intersection, and determining the running state information of the target intersection based on the vehicle running process obtained by simulation, wherein the steps comprise:

and simulating the vehicle running process of the current detection period of the target intersection based on the traffic flow parameters of the target intersection, and determining the running state information of the target intersection in the current detection period based on the vehicle running process of the current detection period obtained by simulation.

Optionally, the simulating a vehicle running process of the target intersection in the current detection period based on the traffic flow parameter of the target intersection includes:

keeping the current simulated vehicle in the simulated traffic scene of the target intersection to continue running, and adding a new simulated vehicle in the simulated traffic scene based on the traffic flow parameter of the target intersection, wherein the current simulated vehicle is the simulated vehicle which is added to the simulated traffic scene and does not leave the simulated traffic scene in the running process of the vehicle at the target intersection simulated in the last detection period.

In a second aspect, there is provided an apparatus for determining operational status information for a target intersection, the apparatus comprising:

the acquisition module is used for acquiring the vehicle passing video of each entrance lane of the target intersection, which is acquired by the camera equipment;

the determining module is used for determining traffic flow parameters of the target intersection based on the vehicle passing videos of each entrance lane of the target intersection;

and the simulation module is used for simulating the vehicle running process of the target intersection based on the traffic flow parameters of the target intersection and determining the running state information of the target intersection based on the vehicle running process obtained by simulation.

Optionally, each entrance lane comprises at least one lane, the determining module is configured to:

Optionally, if the traffic flow parameter includes an average vehicle speed, the vehicle passing data includes a vehicle speed, and the determining module is configured to:

Optionally, the determining module is configured to:

Optionally, if the traffic flow parameter includes a vehicle flow corresponding to each entrance lane, the determining module is configured to:

Optionally, if the traffic flow parameter includes a vehicle ratio in each driving direction corresponding to each entrance lane, the vehicle passing data includes lane information, and the determining module is configured to:

Optionally, if the traffic flow parameters include vehicle proportions in each driving direction corresponding to each entrance lane, the passing data includes license plate numbers, and the determining module is configured to:

Optionally, if the traffic flow parameter includes a ratio of large vehicles corresponding to each entrance lane, the vehicle passing data includes vehicle type information, and the determining module is configured to:

Optionally, the obtaining module is configured to:

the simulation module is used for:

Optionally, the simulation module is configured to:

In a third aspect, a terminal is provided, which includes a processor and a memory, where the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method for determining operational status information of an intersection according to the first aspect.

In a fourth aspect, there is provided a computer readable storage medium having stored therein at least one instruction which is loaded and executed by a processor to implement the method of determining operational status information for a goal intersection according to the first aspect.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, the server can acquire the traffic flow parameters according to the vehicle passing video of the target intersection, so as to simulate the vehicle running process of the target intersection according to the traffic flow parameters, and determine the running state information based on the simulation process. The accuracy of traffic flow parameters obtained based on the vehicle passing video is high, and the subsequent simulation process can be closer to the actual situation of the target intersection, so that the accuracy of the running state information of the target intersection can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a diagram illustrating an implementation environment in accordance with an illustrative embodiment;

FIG. 2 is a flow diagram illustrating a scheme in accordance with an exemplary embodiment;

FIG. 3 is a flow diagram illustrating a method of determining operational status information for a goal intersection in accordance with an exemplary embodiment;

FIG. 4 is a schematic illustration of a goal intersection shown in accordance with an exemplary embodiment;

FIG. 5 is a schematic diagram illustrating a goal intersection traffic flow parameter according to an exemplary embodiment;

FIG. 6 is a flow chart illustrating a direction of vehicle travel determination at a target intersection in accordance with one illustrative embodiment;

FIG. 7 is a flow diagram illustrating an input of traffic flow parameters according to an exemplary embodiment;

FIG. 8 is a schematic diagram illustrating a simulation loop process according to an exemplary embodiment;

FIG. 9 is an illustration of a road traffic network monitoring system in accordance with an exemplary embodiment;

FIG. 10 is a diagram illustrating an optimization simulation analysis result according to an exemplary embodiment;

FIG. 11 is a schematic diagram illustrating an apparatus for determining operational status information for a target intersection in accordance with one illustrative embodiment;

fig. 12 is a schematic diagram illustrating a configuration of a server according to an example embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The embodiment of the invention provides a method for determining running state information of a target intersection, which can be realized by a server.

The server may include a processor, memory, transceiver, etc. The processor, which may be a CPU (Central Processing Unit), may be used to determine traffic flow data of the target intersection, simulate a vehicle running process of the target intersection, determine running state information of the target intersection, and the like. The Memory may be a RAM (Random Access Memory), a Flash Memory, and the like, and may be configured to store received data, data required by the processing process, data generated in the processing process, and the like, such as a vehicle-passing video, vehicle-passing data, and operation state information. And the transceiver can be used for carrying out data transmission with the camera equipment, and the transceiver can comprise an antenna, a matching circuit, a modem and the like.

Fig. 1 is a diagram of an implementation environment provided by an embodiment of the invention. The execution environment includes a plurality of image pickup apparatuses 101, a server 102. The plurality of camera devices 101 may be electronic police or public security checkpoints installed at intersections of a road traffic network, and may capture a video of passing vehicles passing through a target intersection, and some camera devices 101 having a processing function may also directly convert collected video image data into data of passing vehicles. The camera device 101 is in communication connection with the server 102, and can transmit the acquired vehicle passing video or vehicle passing data to the server 102. Further, the server 102 may acquire a traffic flow parameter of the target intersection based on the received data, simulate a traffic operation condition of the target intersection based on the traffic flow parameter, and output operation state information of the target intersection to evaluate an operation state of the target intersection. For the server 102, the server 102 may also have at least one database for storing vehicle passing video data, vehicle passing data, operating status information, and the like. A scheme flow diagram of an embodiment of the invention is shown in fig. 2.

As shown in fig. 3, a flowchart of a method for determining operating state information of a target intersection may include the following steps:

in step 301, a vehicle passing video of each entrance lane of the target intersection is obtained.

The schematic diagram of the goal crossing is shown in fig. 4, and the goal crossing may include a plurality of entrance lanes. Taking the crossroad of FIG. 4 as an example, the target intersection C₁There may be 4 directional inlet passages, east inlet passage 1, west inlet passage 2, south inlet passage 3 and north inlet passage 4. Each approach may have multiple lanes, such as a straight lane, a left-turn lane, and a mixed straight and right-turn lane. Each entrance lane may also be connected to an adjacent intersection, respectively an east adjacent intersection C_1,1West adjacent intersection C_1,2South adjacent intersection C_1,3And north adjacent intersection C_1,4. The camera equipment can be arranged above each entrance lane of the intersection and can shoot the view of the vehicles entering the intersection from the entrance laneAnd (5) image acquisition, namely acquiring a vehicle passing video at the intersection.

In implementation, the camera device can collect the passing video of the target intersection, monitor the traffic running condition of the target intersection, and upload the collected passing video to the server. Optionally, the passing videos of the adjacent intersections can also be uploaded to the server.

In step 302, traffic flow parameters of the target intersection are determined based on the vehicle passing video of each entrance lane of the target intersection.

The traffic flow parameters may include one or more of average vehicle speed, vehicle flow rate corresponding to each entrance lane, vehicle proportion in each driving direction corresponding to each entrance lane and large vehicle proportion corresponding to each entrance lane.

Alternatively, the server may determine the vehicle passing data of each vehicle in the vehicle passing video based on the vehicle passing video of each entrance lane of the target intersection, and then determine the traffic flow parameters of the target intersection based on the vehicle passing data of each vehicle at the target intersection.

In implementation, after the server receives the vehicle-passing video, each image frame of the vehicle-passing video can be identified, and vehicle-passing data of each vehicle in the vehicle-passing video is detected. The passing data at least comprises one or more data of license plate number, vehicle type information, lane information, vehicle speed and arrival time, and is structured data.

Optionally, some camera devices have a data processing function, and if the camera devices detect a video image of a vehicle in the process of collecting a vehicle passing video at the target intersection, the video image of the vehicle can be identified, and a piece of vehicle passing data corresponding to the vehicle is detected. Further, the image pickup apparatus may upload the detected vehicle passing data to the server.

The image recognition technology involved in the above process of detecting vehicle data is not described here. When the server acquires the passing data of the target intersection, the passing data can be stored in the database, and meanwhile, the intersection identification and the entrance lane identification of each piece of passing data can be correspondingly stored. Optionally, the vehicle passing data of adjacent intersections may also be determined by the same or similar method, and stored in the database of the server, which is not described herein again.

When a user needs to evaluate the running state of the target intersection at a certain time period, the data of passing vehicles at the time period at the target intersection can be read from the database through the server. Optionally, more than one camera device may be installed above the entrance of the target intersection, so that when the same vehicle passes through the target intersection, the video images may be simultaneously captured by the multiple camera devices, and when the vehicle data is obtained through detection, the vehicle may correspond to multiple vehicle passing data, that is, there is repeated vehicle passing data. After the vehicle data are read out by the server, the vehicle data can be subjected to data cleaning, that is, repeated vehicle data are removed, and subsequent processing is performed based on the vehicle data after the data cleaning. The rule for cleaning the data may be that the license plate numbers of any two pieces of vehicle passing data are the same, and the difference between the arrival times of the two pieces of vehicle passing data is smaller than a preset threshold, or may be other rules for judging repetition, and is not limited here.

After the server acquires the vehicle passing data, the server can respectively count the vehicle passing data of each entrance lane of the target intersection according to each parameter in the vehicle passing data to obtain the traffic flow parameter of the target intersection. The schematic diagram of the traffic flow parameters of the target intersection as shown in fig. 5 shows the traffic flow parameters of the east entry lane of the target intersection 8:00-9: 00.

The following describes the acquisition of each traffic flow parameter:

first, if the average speed of the vehicles is included in the traffic flow parameters, the speed of the vehicles may be included in the passing data, and the relevant process of determining the average speed of the vehicles at the target intersection may be as follows: an average speed of the vehicles at the targeted intersection is determined based on the vehicle speed of each vehicle at the targeted intersection.

The vehicle speed is easily influenced by factors such as weather, road line type and signal timing, and in order to enable the subsequent simulation process to be more suitable for the actual running process of the target intersection, the embodiment of the invention can calibrate and set the vehicle speed of the simulated vehicle in the simulation model, which runs through the target intersection. The server may acquire the vehicle speeds of all the vehicles from all the vehicle passing data, and further, the server may calculate the average vehicle speeds of all the vehicles, and optionally, the server may sort the vehicle speeds of each vehicle at the intersection and determine the median of all the vehicle speeds as the average vehicle speed at the intersection. If the number of all vehicle speeds is odd, the median may be the vehicle speed at the middle position in the sorting queue; if the number of all vehicle speeds is even, the median may be the average of the two vehicle speeds at the very middle of the sequencing queue. The median may divide all the vehicle speeds into two parts that are greater than the median and less than the median, and the two parts are equal in number of vehicle speeds.

Secondly, if the traffic flow parameter includes the vehicle flow corresponding to each entrance lane, the correlation process of determining the vehicle flow corresponding to each entrance lane of the target intersection may be as follows: and determining the traffic flow corresponding to each entrance lane of the target intersection based on the number of the traffic passing data corresponding to each entrance lane of the target intersection.

When the server reads the vehicle passing data from the database, the number of the vehicle passing data corresponding to each entrance lane can be determined. The server reads the passing data in a certain time period, so that the number can be divided by the time length of the time period to obtain the traffic flow V corresponding to each entrance lane of the target intersection_i,kWherein i is the number of the target intersection, and k is the number of the entrance lane. For example, V_1,1Is a target intersection C₁East entryway 1 traffic flow.

Thirdly, if the traffic flow parameters include the vehicle proportion of each driving direction corresponding to each entrance lane, the vehicle passing data may include lane information, and the relevant processing for determining the vehicle proportion of each driving direction corresponding to each entrance lane at the target intersection is as follows: determining the driving direction of each vehicle corresponding to each entrance way of the target intersection based on the lane information of each vehicle corresponding to each entrance way of the target intersection and the corresponding relationship between the lane information of each entrance way and the driving direction, which is stored in advance; and determining the vehicle proportion in each driving direction corresponding to each entrance lane of the target intersection based on the number of the vehicles in different driving directions corresponding to each entrance lane.

For the vehicle proportion of each driving direction corresponding to each entrance lane, the passing data may further include a license plate number, and the related processing for determining the vehicle proportion of each driving direction corresponding to each entrance lane at the target intersection may further be as follows: for each entrance lane of the target intersection, searching all target passing data with the same license plate number as the passing data of the entrance lane in the passing data of each adjacent intersection of the target intersection, and determining the vehicle proportion in each driving direction corresponding to the entrance lane according to the number of the searched target passing data of each adjacent intersection.

Each lane has its own prescribed direction of travel, e.g., a left turn lane specifies a left turn, and the other lanes are similar. The server may store in advance a correspondence relationship between the lane information and the driving direction of each entrance lane, which may be in the form of a list. As shown in the flowchart of determining the vehicle driving direction at the target intersection shown in fig. 6, the server may traverse each piece of vehicle passing data, and search for the driving direction corresponding to the lane information in the correspondence between the lane information of each entrance lane and the driving direction according to the lane information in each piece of vehicle passing data. If the found driving direction is unique, the driving direction can be determined as the driving direction corresponding to the vehicle and stored in the corresponding parameters.

If the found driving direction is not unique, namely the lane is a mixed lane, the server can find target passing data with the same license plate number as the passing data in the passing data corresponding to the connected entrance of the adjacent intersection. If the target vehicle passing data is found, whether the target vehicle passing data and the vehicle passing data meet time logic can be judged, namely whether the arrival time of the target vehicle passing data is behind the arrival time of the vehicle passing data is judged. If so, the server may targetAnd searching the driving direction corresponding to the vehicle in the driving direction matrix and storing the driving direction in corresponding parameters. The driving direction matrix is obtained by a technician in advance according to the position relation of the connected lane entrances of each entrance lane and the adjacent intersection of the target intersection, and is summarized and stored in the server. For example, for the goal intersection shown in fig. 4, if a certain piece of passing data for the east entry lane 1 of the goal intersection is present, the intersection C is adjacent to the north_1,4And searching target passing data matched with the license plate number in the south entrance way 3, and searching the position (1,3) in the driving direction matrix as the right turn, so that the driving direction corresponding to the vehicle passing data can be determined as the right turn.

By circulating the above processes, after the server determines the driving direction of each vehicle at the target intersection, the number of vehicles in each driving direction can be obtained through statistics for each entrance lane. Then, dividing the number of vehicles in each driving direction by the number of vehicles in the corresponding entrance lane to obtain the vehicle proportion P in each driving direction corresponding to each entrance lane_i,k,mWherein m is a running direction number. For example, the number of the left turn is 1, the number of the straight line is 2, the number of the right turn is 3, the number of the turn around is 4, and for the goal intersection shown in fig. 4, P_1,1,2Namely the target intersection C₁ East entry lane 1 straight going vehicle ratio.

In the above process, when the number of vehicles in each driving direction of each entrance lane is obtained through statistics, the traffic flow V in each driving direction corresponding to each entrance lane can be determined_i,k,mThe method for determining the traffic flow in each driving direction is the same as or similar to the method for determining the traffic flow, and is not described herein again. For an entrance lane, the traffic flow is equal to the sum of the traffic flows in the driving directions, and the sum of the vehicle proportions in the driving directions is 1, i.e. there is a functional relationship

Optionally, when there is camera equipment missing or detection at a certain adjacent intersectionWhen the traffic flow parameters (such as the traffic flow or the vehicle proportion in the driving direction) corresponding to the driving direction cannot be obtained by the method of matching the license plate number in the case of abnormal data, etc., the missing traffic flow parameters in the driving direction may be derived, and the corresponding processing may be as follows: and if the traffic flow parameters of the missing driving directions exist, determining the traffic flow parameters of the missing driving directions based on the functional relation of the traffic flow parameters of the rest driving directions and the traffic flow parameters of all driving directions. For example, for the goal intersection shown in FIG. 4, if the north-adjacent intersection C is_1,4If the camera equipment is lost, the target intersection C is₁The proportion of vehicles turning right on the east entry lane 1 may be given by the formula P_1,1,3＝1-(P_1,1,1-P_1,1,2-P_1,1,4) Get, target intersection C₁The flow of vehicles turning right at east entry lane 1 can be represented by formula V_1,1,3＝V_1,1·[1-(P_1,1,1-P_1,1,2-P_1,1,4)]Thus obtaining the product.

It should be noted that, the above method of matching license plate numbers can be used to determine the driving direction of each vehicle regardless of whether the driving direction specified by the lane is unique, but the determination of the driving direction by combining the two methods can reduce the calculation amount of the server and improve the calculation efficiency. If the vehicle passing data of each entrance lane adopts a method of matching license plate numbers, the number of the searched target vehicle passing data of each adjacent intersection can be counted, then the number of the vehicles in each driving direction is obtained through the driving direction matrix, and the vehicle proportion in each driving direction corresponding to each entrance lane is determined, which is similar to the above process and is not repeated here.

Thirdly, if the traffic flow parameters include the proportion of the large vehicles corresponding to each entrance lane, the vehicle passing data may include vehicle type information, and the relevant processing for determining the proportion of the large vehicles corresponding to each entrance lane at the target intersection is as follows: and determining the proportion of the large vehicles corresponding to each entrance lane of the target intersection based on the number of the vehicle passing data of the large vehicles corresponding to each entrance lane and the number of the vehicle passing data corresponding to each entrance lane.

The server can acquire the vehicle type information of the vehicle from the vehicle passing data of each entrance lane, and further, the server can count the number of the vehicle type information as the vehicle passing data of the large-scale vehicle, and divide the number by the number of the vehicle passing data of the corresponding entrance lane, so that the proportion of the large-scale vehicle corresponding to each entrance lane of the target intersection can be obtained.

In step 303, the vehicle running process of the target intersection is simulated based on the traffic flow parameters of the target intersection, and the running state information of the target intersection is determined based on the vehicle running process obtained by the simulation.

The running state information may include one or more of the average delay time of the vehicle, the average stop number of the vehicle, the average queuing length and the average speed of the simulated vehicle. The simulated vehicle average speed is the average speed of the simulated vehicle passing through the target intersection, and the delay condition of the simulated vehicle at the target intersection is considered.

In implementation, the server may simulate the vehicle running state of the target intersection based on simulation software, where the simulation software may be VISSIM micro traffic simulation software or the like. Technicians can pre-establish simulated traffic scenes including lanes, signal lamp groups and the like of the target intersection in simulation software according to the actual layout of the target intersection. The server may set the traffic flow parameter obtained in the above process as a parameter for simulation operation, and the flow chart for inputting the traffic flow parameter may be as shown in fig. 7, and drive the simulation operation after the setting is completed. Furthermore, the simulation software may add a simulated vehicle to the simulated traffic scene so that the simulated vehicle travels in the simulated traffic scene and the distribution of the simulated vehicle at each entrance lane, the vehicle speed, and the like conform to the set traffic flow parameters. In the process of simulation operation, various operation indexes of the target intersection, namely operation state information, can be obtained through various detectors, such as a travel time detector, a queuing length detector and the like, arranged in a simulation model for simulating a traffic scene. The running process of the vehicle at the target intersection is simulated through the simulation software, so that relatively comprehensive running state information can be obtained.

Meanwhile, the service level of the target intersection may be determined with reference to a road traffic capacity manual (HCM 2000), as shown in table 1 below, and intersection improvement advice may be derived based thereon.

Signal controlled intersection service level division in table 1 HCM manual

Optionally, for the requirement of monitoring the running state of the traffic network in real time, the server may obtain the vehicle passing video of each entrance lane of the target intersection, which is acquired by the camera device in the current detection period, every time a preset detection period is reached, that is, update the traffic flow parameters of the target intersection at regular intervals, simulate the vehicle running process of the current detection period of the target intersection based on the traffic flow parameters of the target intersection, and determine the running state information of the target intersection in the current detection period based on the vehicle running process of the current detection period obtained through simulation. A schematic diagram of the simulation loop process can be shown in fig. 8.

In the process shown in fig. 8, the update period is a preset detection period, which may be 15 minutes, and the simulation period may be 24 hours. When the simulation period is reached, the simulation model can be initialized, the traffic flow parameters of the next simulation period are input, and the vehicle running process of the next simulation period is simulated. However, each time the update period is reached, the simulation model may not be initialized, but rather keep the current simulated vehicles in the simulated traffic scene of the target intersection running and add new simulated vehicles in the simulated traffic scene based on the updated traffic flow parameters of the target intersection. The current simulated vehicle is a simulated vehicle which is added to the simulated traffic scene and does not leave the simulated traffic scene in the vehicle running process of the target intersection simulated in the last detection period. Therefore, the simulation of the vehicle running process between the adjacent updating periods is continuous, the complex traffic flow change characteristics can be reflected, and the running state of the target intersection can be dynamically evaluated.

The method for determining the running state information of the target intersection provided by the embodiment of the invention can be part of a road traffic network monitoring system, and the road traffic network monitoring system is shown in fig. 9. The technicians can optimize the signal timing scheme and the like of the target intersection according to the running state information obtained in the process to obtain an optimized scheme so as to improve the service level of the target intersection. The optimization scheme can be correspondingly set in a simulated traffic scene of simulation software, and then traffic flow parameters used before optimization can be input into the optimized simulated traffic scene for simulation to obtain optimized running state information, the specific process is the same as or similar to the process, and the detailed description is omitted here. Then, whether the optimization scheme meets the optimization requirement can be judged according to the running state information before and after optimization, and if the optimization scheme meets the optimization requirement, the optimization scheme can be stored in an expert database of a server for subsequent analysis and optimized use of an actual road traffic network.

Taking the delay variation of vehicles at the target intersection as an example, the delay time of the vehicles at the east entry road and the west entry road is relatively high, and the peak time period exceeds 60 s; the south and north directions are main roads, the traffic priority is high, so the delay time of all vehicles is maintained at about 40s, the delay time of the whole vehicle at the intersection is between 35s and 50s, and the service level is grade D, which belongs to the range with large delay but acceptable. In order to reduce the delay time of the target intersection, the timing scheme of the target intersection can be optimized for the above situations to obtain an optimized scheme: the duration of green lamps in the east and west directions is properly prolonged, and the overlapping phase positions are adopted in the south and north directions, so that the duration of green lamps in the south-inlet straight-going direction is shortened. And after optimizing the simulated traffic scene based on the optimization scheme, simulating to obtain optimized running state information. As shown in the schematic diagram of the simulation analysis result of the optimization scheme shown in fig. 10, each index of the optimized intersection is improved, wherein the delay time of each vehicle is reduced by 13%, the number of times of each vehicle is reduced by 11.7%, the simulated average vehicle speed is improved by 34%, and the optimization scheme can be stored in an expert database.

When the road traffic network monitoring system detects the actual running state of an intersection in the actual road traffic network, a proper optimization scheme can be selected from the expert database to optimize the actual road traffic network so as to improve the service level of the actual road traffic network. The method for selecting the optimization scheme may be a linear correspondence method or a method using machine learning, and is not limited herein.

Based on the same technical concept, the embodiment of the invention also provides a device for determining the running state information of the target intersection, and the device can be a server in the embodiment of the invention. As shown in fig. 11, the apparatus includes:

an obtaining module 1110, configured to obtain a vehicle passing video of each entrance lane of the target intersection, where the video is acquired by a camera;

a determining module 1120, configured to determine traffic flow parameters of the target intersection based on the vehicle passing video of each entrance lane of the target intersection;

the simulation module 1130 is configured to simulate a vehicle running process of the target intersection based on the traffic flow parameter of the target intersection, and determine running state information of the target intersection based on the vehicle running process obtained through simulation.

Optionally, each entrance lane comprises at least one lane, the determining module 1120 is configured to:

Optionally, if the traffic flow parameter includes an average vehicle speed, the vehicle passing data includes a vehicle speed, and the determining module 1120 is configured to:

Optionally, the determining module 1120 is configured to:

Optionally, if the traffic flow parameter includes a vehicle flow corresponding to each entrance lane, the determining module 1120 is configured to:

Optionally, if the traffic flow parameter includes a vehicle ratio in each driving direction corresponding to each entrance lane, the vehicle passing data includes lane information, and the determining module 1120 is configured to:

Optionally, if the traffic flow parameter includes a vehicle ratio in each driving direction corresponding to each entrance lane, the passing data includes a license plate number, and the determining module 1120 is configured to:

Optionally, if the traffic flow parameter includes a ratio of large vehicles corresponding to each entrance lane, the vehicle passing data includes vehicle type information, and the determining module 1120 is configured to:

Optionally, the obtaining module 1110 is configured to:

the simulation module is to:

Optionally, the simulation module is configured to 1130:

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

It should be noted that: the device for determining the operation state information of the intersection is only illustrated by dividing the functional modules when determining the operation state information of the intersection, and in practical application, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the server is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the apparatus for determining the operation state information of the target intersection and the method for determining the operation state information of the target intersection provided by the embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

Fig. 12 is a schematic structural diagram of a server according to an embodiment of the present invention. The server 1200 may vary widely in configuration or performance and may include one or more Central Processing Units (CPUs) 1222 (e.g., one or more processors) and memory 1232, one or more storage media 1230 (e.g., one or more mass storage devices) storing applications 1242 or data 1244. Memory 1232 and storage media 1230 can be, among other things, transient storage or persistent storage. The program stored in the storage medium 1230 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 1222 may be configured to communicate with the storage medium 1230, to execute a series of instruction operations in the storage medium 1230 on the server 1200.

The server 1200 may also include one or more power supplies 1226, one or more wired or wireless network interfaces 1250, one or more input-output interfaces 1258, one or more keyboards 1256, and/or one or more operating systems 1241, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

The server 1200 may include a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the method of determining operating status information for an intersection as described in the various embodiments above:

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. A method of determining operational status information for an intersection, the intersection including a plurality of entrance lanes, the method comprising:

identifying each image frame in the vehicle passing video of each entrance lane of the target intersection to obtain vehicle passing data of each vehicle in the vehicle passing video, wherein the vehicle passing data comprises license plate numbers, vehicle type information, lane information and vehicle speed;

determining traffic flow parameters of the target intersection based on vehicle passing data of each vehicle at the target intersection, wherein the traffic flow parameters comprise vehicle average speed, vehicle flow corresponding to each entrance lane, vehicle proportion in each driving direction corresponding to each entrance lane and large vehicle proportion corresponding to each entrance lane;

simulating the vehicle running process of the target intersection based on the traffic flow parameters of the target intersection, and determining running state information of the target intersection based on the vehicle running process obtained by simulation, wherein the running state information comprises vehicle average delay time, vehicle average stopping times, average queuing length and simulated vehicle average speed;

determining traffic flow parameters of the target intersection based on the vehicle passing data of each vehicle at the target intersection, including:

for each piece of vehicle passing data in the vehicle passing data of the target intersection, reading each piece of vehicle passing data, and searching a driving direction corresponding to the lane information in each piece of vehicle passing data in a pre-stored corresponding relationship between the lane information of each entrance lane and the driving direction according to the lane information in each piece of vehicle passing data, wherein the lane information of each entrance lane corresponds to one or more driving directions;

if the driving direction corresponding to the searched lane information is unique, determining the driving direction corresponding to the searched lane information as the driving direction of the vehicle corresponding to each piece of passing data;

if the driving direction corresponding to the searched lane information is not unique, searching target passing data with the same license plate number as each piece of passing data in passing data corresponding to an entrance lane connected to an adjacent intersection of the target intersection, and judging whether the arrival time of the target passing data is behind the arrival time of each piece of passing data or not when the target passing data is searched; if the arrival time of the target vehicle passing data is behind the arrival time of each piece of vehicle passing data, determining the driving direction of the vehicle corresponding to each piece of vehicle passing data according to the entrance lane corresponding to the target vehicle passing data and the entrance lane corresponding to each piece of vehicle passing data;

2. The method according to claim 1, wherein determining traffic flow parameters for the targeted intersection based on the vehicle passing data for each vehicle at the targeted intersection comprises:

3. The method of claim 2, wherein determining the average vehicle speed at the intersection based on the vehicle speed of each vehicle at the intersection comprises:

4. The method according to claim 1, wherein determining traffic flow parameters for the targeted intersection based on the vehicle passing data for each vehicle at the targeted intersection comprises:

5. The method according to claim 1, wherein determining traffic flow parameters for the targeted intersection based on the vehicle passing data for each vehicle at the targeted intersection comprises:

6. The method according to claim 1, wherein the acquiring of the vehicle passing video of each entrance lane of the intersection, which is acquired by the camera device, comprises:

7. The method according to claim 6, wherein simulating vehicle operation at the current detection cycle of the target intersection based on the traffic flow parameters of the target intersection comprises:

8. An apparatus for determining operational status information for an intersection, the intersection including a plurality of entrance lanes, the apparatus comprising:

the determining module is used for identifying each image frame in the vehicle passing video of each entrance lane of the target intersection to obtain vehicle passing data of each vehicle in the vehicle passing video, wherein the vehicle passing data comprises license plate numbers, vehicle type information, lane information and vehicle speed, and traffic flow parameters of the target intersection are determined based on the vehicle passing data of each vehicle at the target intersection, and the traffic flow parameters comprise vehicle average speed, vehicle flow corresponding to each entrance lane, vehicle proportion of each driving direction corresponding to each entrance lane and large vehicle proportion corresponding to each entrance lane;

the simulation module is used for simulating the vehicle running process of the target intersection based on the traffic flow parameters of the target intersection, and determining running state information of the target intersection based on the vehicle running process obtained by simulation, wherein the running state information comprises vehicle average delay time, vehicle average parking times, average queuing length and simulated vehicle average speed;

the determining module is specifically configured to read each piece of vehicle passing data in the vehicle passing data of the target intersection, search a driving direction corresponding to the lane information in each piece of vehicle passing data in a pre-stored corresponding relationship between the lane information of each entrance lane and the driving direction according to the lane information in each piece of vehicle passing data, where the lane information of each entrance lane corresponds to one or more driving directions;

if the driving direction corresponding to the searched lane information is not unique, searching target passing data with the same license plate number as each piece of passing data in passing data corresponding to an entrance lane connected to an adjacent intersection of the target intersection, judging whether the arrival time of the target passing data is behind the arrival time of each piece of passing data or not when the target passing data is searched, and if the arrival time of the target passing data is behind the arrival time of each piece of passing data, determining the driving direction of the vehicle corresponding to each piece of passing data according to the entrance lane corresponding to the target passing data and the entrance lane corresponding to each piece of passing data;

9. A terminal comprising a processor and a memory having stored therein at least one instruction that is loaded and executed by the processor to implement a method of determining operational status information for a target intersection as claimed in any one of claims 1 to 7.

10. A computer readable storage medium having stored therein at least one instruction which is loaded and executed by a processor to implement a method of determining operational status information for a goal intersection as claimed in any one of claims 1 to 7.