CN113643534B

CN113643534B - Traffic control method and equipment

Info

Publication number: CN113643534B
Application number: CN202110864612.5A
Authority: CN
Inventors: 梁延禹; 关喜嘉; 王邓江; 邓永强
Original assignee: Beijing Wanji Technology Co Ltd
Current assignee: Beijing Wanji Technology Co Ltd
Priority date: 2021-07-29
Filing date: 2021-07-29
Publication date: 2023-04-18
Anticipated expiration: 2041-07-29
Also published as: CN113643534A

Abstract

The embodiment of the application provides a traffic control method and traffic control equipment, and belongs to the field of road traffic control. The method comprises the following steps: acquiring at least one lane-changing vehicle changing from a first lane to a second lane in a target detection area; determining a jammed vehicle of the second lane from the lane-change vehicles according to the position of the lane-change vehicle and the position of the vehicle in the second lane; and adjusting the traffic flow guidance of the first lane according to the number of the vehicles which are plugged in the second lane, so that the traffic flow guidance of the first lane is the same as the traffic flow guidance of the second lane. According to the method, the intelligent base station senses vehicle information on the road in real time, traffic flow states of all lanes are comprehensively analyzed, lane traffic flow guiding directions are flexibly regulated and controlled based on analysis results, and the congested traffic flow is dredged timely and efficiently.

Description

Traffic control method and equipment

Technical Field

The application belongs to the field of road traffic control, and particularly relates to a traffic control method and traffic control equipment.

Background

With the development of social life, the problem of ground traffic jam is increasingly prominent. For example, with the continuous transition of urban layouts, a pattern that work units are concentrated in urban central areas and residential areas are concentrated in urban peripheral areas is gradually formed, and the pattern can cause a tidal traffic flow phenomenon that bidirectional road traffic flow is unbalanced, so that the utilization rate of lane resources is low, and traffic jam is caused. In addition, the current road intersections generally adopt a fixed lane function division scheme, and the scheme cannot adjust lane functions according to the unevenness of the traffic flow, so that the traffic flow guiding direction of the lane cannot be flexibly adjusted to adapt to the actual traffic condition, thereby further aggravating the road traffic jam condition, especially the traffic jam condition at the road intersections.

Disclosure of Invention

The application provides a traffic control method and traffic control equipment, which flexibly adjust traffic flow guidance of a lane according to the actual condition of the traffic flow of the lane through an intelligent base station so as to solve the problems that traffic jam cannot be timely and efficiently dredged and the utilization rate of lane resources is low.

In a first aspect, a method for traffic control is provided, the method comprising: the method comprises the steps that vehicle information in a target detection area is obtained through an intelligent base station arranged in the target detection area; the vehicle information comprises a vehicle type and/or a vehicle behavior; acquiring distribution information in the target detection area according to the vehicle information; when the vehicle information comprises the vehicle type, the distribution information is vehicle distribution obtained based on statistics of the vehicle type; when the vehicle information includes the vehicle behavior, the distribution information is vehicle distribution obtained based on the vehicle behavior statistics; and carrying out traffic control on the target detection area according to the distribution information.

According to the traffic control method provided by the embodiment of the application, the roadside device analyzes the vehicle behaviors and/or the vehicle types based on the image data and the point cloud data to count and analyze the vehicle distribution condition, and performs traffic control based on the vehicle distribution condition, so that the road traffic jam can be effectively relieved, and the road driving safety is improved.

With reference to the first aspect, in certain implementations of the first aspect, when the vehicle type is a preset vehicle type, the method further includes: acquiring the historical driving state of the vehicle of the preset vehicle type; acquiring a predicted driving state of the vehicle of the preset vehicle type according to the historical driving state; acquiring a lane where the vehicle of the preset vehicle type is located based on the vehicle distribution; and carrying out traffic control on the lane where the vehicle of the preset vehicle type is located, so that the vehicle of the preset vehicle type meets the predicted running state.

According to the traffic control method provided by the embodiment of the application, the distribution state of the special vehicle executing the specific task (such as the emergency rescue task) is subjected to statistical analysis, and the traffic control is performed based on the analysis result, so that the smoothness of the special vehicle in running can be ensured.

With reference to the first aspect, in certain implementations of the first aspect, the preset vehicle type includes at least one of: ambulances, police cars, disaster relief cars and fire engines.

With reference to the first aspect, in certain implementations of the first aspect, when the vehicle behavior is a congestion behavior, the method includes: acquiring at least one lane-changing vehicle changing from a first lane to a second lane in a target detection area; determining a jammed vehicle of the second lane from the lane-change vehicles according to the position of the lane-change vehicle and the position of the vehicle in the second lane; and adjusting the traffic flow guidance of the first lane according to the number of the vehicles which are plugged in the second lane, so that the traffic flow guidance of the first lane is the same as the traffic flow guidance of the second lane.

According to the traffic control method provided by the application, the intelligent base station flexibly adjusts the traffic flow guidance of the other lanes with lower traffic resource utilization rate to be the same as the traffic flow guidance of the traffic jam lane according to the vehicle congestion number of the traffic jam lane, so that the vehicles in the traffic jam lane can be shunted by the other lanes, and the traffic jam condition of the traffic jam lane can be effectively relieved in real time.

With reference to the first aspect, in certain implementations of the first aspect, the determining a congested vehicle in the second lane from the lane-change vehicles according to the position of the lane-change vehicle and the position of the vehicle in the second lane specifically includes: determining a first vehicle in the second lane located in front of the lane-change vehicle side and a second vehicle in the second lane located behind the lane-change vehicle side according to the position of the lane-change vehicle and the position of the vehicle in the second lane; determining a distance length between the first vehicle and the second vehicle; and when the distance length is smaller than the length of the body of the lane-changing vehicle, determining that the lane-changing vehicle is a jammed vehicle of the second lane.

It should be understood that the first vehicle in the second lane in front of the lane-change vehicle refers to a vehicle in the second lane, which is adjacent to the lane-change vehicle and in front of the lane-change vehicle, that is, there is no other vehicle barrier between the vehicle in front of the lane-change vehicle and the lane-change vehicle; the second vehicle located behind the lane-change vehicle in the second lane is a vehicle located behind the lane-change vehicle and adjacent to the lane-change vehicle in the second lane, that is, no other vehicle is obstructed between the vehicle behind the lane-change vehicle and the lane-change vehicle.

It can be understood that, in the embodiment of the present application, the manner of determining whether the lane-changing vehicle is a congested vehicle is mainly determined by determining a relationship between a vehicle body length of the lane-changing vehicle and a distance length between adjacent vehicles in the lane-changing lane (that is, two vehicles in front of and behind the lane-changing lane), and if the distance between the two vehicles is large enough (greater than or equal to the vehicle body length of the lane-changing vehicle), the lane-changing vehicle is a normal lane-changing vehicle, and the lane-changing vehicle is not a congested vehicle; and if the distance between the front vehicle and the rear vehicle is less than the length of the vehicle body of the lane-changing vehicle, the lane-changing vehicle belongs to a plug vehicle.

According to the traffic control method provided by the embodiment of the application, whether the lane-changing vehicle is a jammed vehicle or not can be determined by comparing the length of the body of the lane-changing vehicle with the length of the gap in the lane-changing lane, and the jammed vehicle can be efficiently and accurately determined from the lane-changing vehicle.

With reference to the first aspect, in certain implementations of the first aspect, the adjusting the traffic flow guidance of the first lane according to the number of congested vehicles in the second lane specifically includes: when the number of the jammed vehicles in the second lane is larger than a first threshold value, adjusting the traffic flow guidance of the first lane; or calculating the average value of the number of the vehicles which are jammed in the second lane within first preset time according to the number of the vehicles which are jammed in the second lane; and when the average value is larger than a second threshold value, adjusting the traffic flow guidance of the first lane.

According to the traffic control method provided by the embodiment of the application, the intelligent base station senses the vehicle information and the lane information on the road in real time, comprehensively analyzes the number of the traffic jam of each lane, flexibly regulates and controls the traffic flow guiding direction of the lane based on the analysis result, and conducts timely and efficient dredging on the traffic jam. If more vehicles are jammed in a certain lane (such as the second lane), the traffic flow guidance of the adjacent lane (such as the first lane) can be adjusted, so that the adjacent lane can shunt traffic on the jammed lane.

With reference to the first aspect, in certain implementations of the first aspect, the adjusting the traffic flow guidance of the first lane according to the number of congested vehicles in the second lane specifically includes: acquiring the queuing length of the vehicles in the second lane; determining the congestion proportion of the second lane according to the number of the congested vehicles in the second lane and the queuing length; and when the jam proportion is larger than a third threshold value, adjusting the traffic flow guidance of the first lane.

According to the traffic control method provided by the embodiment of the application, the intelligent base station senses the vehicle information and the lane information on the road in real time, comprehensively analyzes the number of the traffic jam of each lane, flexibly regulates and controls the traffic flow guiding direction of the lane based on the analysis result, and conducts timely and efficient dredging on the traffic jam. If more vehicles are jammed in a certain lane (such as a second lane), the traffic flow guidance of the adjacent lane (such as a first lane) can be adjusted, so that the adjacent lane shunts the traffic on the jammed lane.

With reference to the first aspect, in certain implementations of the first aspect, the adjusting the traffic flow guidance of the first lane so that the traffic flow guidance of the first lane is the same as the traffic flow guidance of the second lane specifically includes: and indicating the signal lamp corresponding to the first lane to be adjusted to a target phase, wherein the target phase is the same as the phase of the signal lamp corresponding to the second lane.

According to the traffic control method provided by the embodiment of the application, if there are more congested vehicles in a certain lane (such as the second lane), the traffic flow guidance of the adjacent lane (such as the first lane) can be adjusted, so that the adjacent lane shunts traffic on the congested lane.

With reference to the first aspect, in certain implementations of the first aspect, the method further includes: collecting point cloud data and video data in the target detection area; and performing fusion processing on the point cloud data and the video data to acquire perception information of the target detection area, wherein the perception information is used for identifying the lane-changing vehicle and the jammed vehicle of the second lane.

With reference to the first aspect, in certain implementations of the first aspect, the determining a congested vehicle in the second lane from the lane change vehicles specifically includes: determining the offset and the offset direction of the course angle of the lane-changing vehicle according to the perception information; and determining the jammed vehicle of the second lane from the lane-changing vehicles according to the offset and the offset direction of the course angle of the lane-changing vehicles.

With reference to the first aspect, in certain implementations of the first aspect, the determining a congested vehicle in the second lane from the lane-change vehicles according to the position of the lane-change vehicle and the position of the vehicle in the second lane specifically includes: determining the position of the lane-changing vehicle and the position of the vehicle in the second lane according to the perception information; and determining a jammed vehicle of the second lane from the lane-change vehicles according to the position of the lane-change vehicle and the position of the vehicle in the second lane.

In a second aspect, there is provided a smart base station, comprising: the camera is used for collecting video data in a target detection area; the laser radar is used for acquiring point cloud data in the target detection area; a memory for storing computer readable instructions; a processor configured to execute the computer-readable instructions, which when executed, cause the smart base station to implement the method as described in any one of the implementations of the first aspect.

In a third aspect, a system for lane management is provided, which includes a smart base station for performing the method according to any one of the implementations of the first aspect, and a signal lamp for adjusting a phase according to an indication of the smart base station.

In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions that, when executed, cause a method as described in any of the implementations of the first aspect to be implemented.

In a fifth aspect, a computer product is provided, the computer product comprising computer instructions that, when executed in a computer, cause the method described in any of the implementations of the first aspect to be implemented.

In a sixth aspect, a chip is provided, which includes computer instructions that, when executed in a computer, cause the method described in any of the implementations of the first aspect to be implemented.

Drawings

Fig. 1 is a schematic diagram of a system architecture applicable to a traffic control method according to an embodiment of the present disclosure.

Fig. 2 is a schematic structural diagram of an intelligent base station according to an embodiment of the present disclosure.

Fig. 3 is a schematic application scenario diagram of a traffic control method according to an embodiment of the present application.

Fig. 4 is a schematic flowchart of a method for traffic control according to an embodiment of the present disclosure.

Fig. 5 is a schematic flow chart of another traffic control method according to an embodiment of the present disclosure.

Fig. 6 is a schematic flow chart of another traffic control method provided in an embodiment of the present application.

Fig. 7 is a schematic structural diagram of another intelligent base station according to an embodiment of the present disclosure.

Detailed Description

The embodiments of the present application will be described below with reference to the drawings.

It is to be understood that the terminology used in the description of the embodiments herein is for the purpose of describing particular embodiments only, and is not intended to be limiting of the application. In the description of the embodiments of the present application, "/" means "or" unless otherwise specified, for example, a/B may mean a or B; "and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more, and "at least one", "one or more" means one, two or more, unless otherwise specified.

In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a definition of "a first" or "a second" feature may explicitly or implicitly include one or more of the features.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather mean "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

As mentioned in the background, the ground road traffic (especially the road intersection traffic) often causes congestion due to factors such as tidal traffic flow, and the like, which seriously affects the convenience and safety of people. For the problem of traffic congestion, a method for controlling traffic flow by regularly determining road sections is mostly adopted at present, but on one hand, the existing method cannot respond in time when the traffic congestion condition appears (or suddenly appears) in real time; on the other hand, when facing tidal traffic flow, etc., bidirectional lane resources cannot be utilized in a balanced manner, for example, a lane guided by a certain direction is heavily congested, while lane vehicles guided by the opposite direction are sparse. In addition, the existing traffic control technology has inconsistent judgment basis, and the conversion between the phases of traffic control lacks safety control, so that the running risk can be caused.

In order to solve the above problems, embodiments of the present application provide a traffic control method, which includes sensing vehicle information in a road in real time by a smart base station disposed on a roadside, comprehensively analyzing traffic flow states of lanes, flexibly adjusting and controlling a traffic flow guidance direction (hereinafter referred to as traffic flow guidance) of the lanes based on an analysis result, and timely and efficiently dredging congested traffic flows. According to the traffic control method provided by the embodiment of the application, the adaptive regulation and control can be flexibly and efficiently carried out on the traffic flows of a plurality of lanes based on the real-time condition of traffic, the timely response to the traffic jam condition is achieved, the traffic flow guidance of the lane at the sparse side of the vehicle can be regulated and controlled, the lane at the sparse side of the vehicle is utilized to shunt the traffic flow on the jammed lane, and therefore the lane resources are fully utilized.

It should be understood that the traffic flow status of a lane as referred to herein may include the traffic status of a plurality of vehicles on the lane, such as whether a plurality of vehicles on the lane are in a congested state or a non-congested state; if the vehicle is in the congested state, the traffic flow state may further specifically include a queuing length of congested vehicles on the lane, a number of queued vehicles, a number of congested vehicles, and the like.

In order to facilitate understanding of the solutions described in the embodiments of the present application, some terms that may be referred to in the embodiments of the present application are explained below:

1. road, lane and intersection

In the embodiment of the present application, a road refers to a passage for a vehicle to travel and for communicating two places.

In the embodiment of the present application, the lane is a passage for a single tandem vehicle traveling in the same direction, and the common lanes include different types such as a straight lane, a left-turn lane, and a right-turn lane. A road includes one or more lanes, for example, a road may include 4 lanes, one left turn lane, 2 straight lanes, and 1 right turn lane. For the sake of simplicity, two adjacent lanes (e.g. a first lane and a second lane; or lane 1 and lane 2 shown in fig. 3) are taken as an example for the following description, but in practical applications, the invention is not limited thereto.

In the embodiment of the present application, an intersection (or called road intersection) refers to a junction of two or more roads, and is also a necessary place for collecting, turning and evacuating traffic of vehicles and pedestrians. Generally, the types of intersections may be divided according to the number of intersecting roads, and for example, may be divided into three-way, four-way, and multi-way. There are plane intersections and solid intersections in the intersecting manner, for example, the main forms of the plane intersections are crosses, X-shaped intersections, T-shaped intersections, Y-shaped intersections, staggered intersections, multiple intersections, and the like.

2. Laser radar (light laser detection and ranging, liDAR)

The laser radar is a target detection technology, a laser beam is emitted by a laser, the laser beam is subjected to diffuse reflection after encountering a target object, the reflected beam is received by a detector, and characteristic quantities such as the distance, the direction, the height, the speed, the posture, the shape and the like of the target object are determined according to the emitted beam and the reflected beam.

The wisdom basic station that this application embodiment provided can install laser radar, and this laser radar can scan the object in the target detection region through quick and repeatedly launch the laser beam, acquires the point cloud data that the target detection region corresponds. Specifically, the laser radar emits a laser beam into an environment within a target detection area, receives an echo beam of the laser beam reflected by each object (including a vehicle, a lane, and the like) in the environment, and determines the position, size, movement information, and the like of each object by calculating a time delay between an emission time point of the laser beam and a return time point of the echo beam. In addition, in practical applications, the lidar may also determine angular information describing the spatial orientation of the laser beam, combine the position of each object with the angular information of the laser beam, and generate a three-dimensional map of the described environment.

Exemplarily, as shown in fig. 1, a schematic diagram of a system architecture applicable to the traffic control method provided in the embodiment of the present application is shown. The system architecture includes an intelligent base station 100, at least one vehicle (e.g., vehicle 200), and at least one traffic flow guidance adjustment device 300.

In some embodiments, the smart base station 100 (or road side converged sensing system or road side base station) is an important infrastructure of the intelligent transportation vehicle road system, and has road sensing capability, computing capability, communication capability, and the like. For example, the smart base station 100 may collect point cloud data and video data in a target detection area through a laser radar and a camera, respectively; different types of information of the objects in the target detection area can be identified according to the point cloud data and the video data, such as first information (such as vehicle types, license plate numbers and the like) of vehicles can be identified according to the video data, and second information (such as vehicle positions, driving speeds, heading angles, vehicle lengths and the like) of the vehicles can be identified according to the point cloud data; then, different types of information of the same object may be fused to obtain perception information (or called fusion information) in the target detection area, where the perception information may include vehicle information and lane information in the target detection area, such as vehicle type, vehicle position, driving speed, heading angle, vehicle length, license plate number, lane line, lane position, and the like. Meanwhile, the intelligent base station 100 may also be configured with computing resources, and the intelligent base station may analyze traffic flow states of the respective lanes through the computing resources, for example, determine the number of queued vehicles on the lane, the number of congested vehicles, the vehicle queuing length, the congestion ratio, and the like. In addition, the intelligent base station can adjust the phase according to the number of the vehicles with the jam or the indication signal lamp of the jam proportion on the lane so as to adjust the traffic flow guidance on the corresponding lane and the like.

In some embodiments, the intelligent base station 100 may be disposed on the road side, and particularly, may be disposed in an area where traffic congestion is likely to occur, such as a road intersection. In practical applications, the intelligent base station 100 may establish communication connections with a plurality of vehicles and other intelligent roadside devices (such as the traffic flow guidance adjusting device 300) through a wireless network, so as to implement interconnection. The wireless network may be any wireless network based on communication technology standards, such as a Long Term Evolution (LTE) wireless network, a vehicle networking (V2X), and a fifth generation mobile communication technologyOperation (the 5) ^th generation, 5G), and the like. For example, the smart base station 100 may send a traffic prompt to the vehicle based on the sensed traffic information; alternatively, the smart base station 100 may instruct a signal lamp to change a phase, adjust traffic flow guidance, and the like based on the traffic flow status on each lane. The detailed structure and operation principle of the smart base station will be described with reference to the accompanying drawings, and will not be described in detail herein.

In some embodiments, the vehicle 200 may include an onboard communication device capable of communicatively coupling with the smart base station 100. For example, the vehicle 200 may receive traffic prompting information, such as signal light phase guidance, speed guidance, road condition prompting information, and the like, sent by the smart base station 100 through wireless communication. For example, the vehicle 200 in the embodiment of the present application may be a general-purpose vehicle, and may also be an autonomous vehicle (or an unmanned vehicle, a computer-driven vehicle, or a wheeled mobile robot), and the present application does not limit the specific type of the vehicle.

In some embodiments, the traffic guidance adjusting device 300 may be, for example, a traffic signal lamp (or called "signal lamp"), and is mainly responsible for adjusting the traffic guidance according to the indication of the intelligent base station 100, such as adjusting the phase to change the traffic guidance on the corresponding lane. For example, in the scene shown in fig. 3, if the signal lamp corresponding to the lane 1 is a red lamp and the signal lamp corresponding to the lane 2 is a green lamp, when it is recognized that the traffic congestion is caused by a serious traffic jam phenomenon in the lane 2, the signal lamp corresponding to the lane 1 may be switched to the green lamp, that is, adjusted to the same traffic flow guidance as the lane, and shunts the traffic flow in the lane 2, so as to alleviate the traffic congestion condition of the vehicle in the lane 2.

It should be understood that the traffic flow guidance adjusting device may also be other devices for indicating traffic flow guidance, such as an electronic road sign, etc., and the present application is only illustrated by way of example and not limited thereto.

For example, as shown in fig. 2, a schematic structural diagram of an intelligent base station according to an embodiment of the present application is provided. The smart base station 100 may correspond to the smart base station 100 in fig. 1. Illustratively, the smart base station 100 may include at least an information collecting system 1001, a computing system 1002, and a regulating system 1003.

In some embodiments, the information acquisition system 1001 is primarily responsible for information acquisition within a target detection area. The information collection system 100 may include a vision system sensor such as a camera (e.g., a high definition camera), and a radar system sensor such as a laser radar. The camera can be used for acquiring video data (such as video images including vehicles and lanes) in a certain area range; lidar may be used to acquire point cloud data (e.g., point cloud coordinates of a vehicle) over a range of areas. For example, the video image acquisition range of the camera may be greater than or less than the point cloud image acquisition range of the lidar, which is not limited in the embodiment of the present application. For example, the sampling rate of the camera and the sampling rate of the lidar may be the same or different, for example, the sampling rates of the camera and the lidar may be both 50Hz, which is not limited in this application. For convenience of understanding, in the embodiments of the present application, the detection areas of the high definition camera and the lidar (for example, both the detection areas of the target) are the same, and the sampling rates are also the same as an example, where the detection areas of the camera and the lidar may be both shown by dashed circle boxes in fig. 3.

In some embodiments, the computing system may identify vehicle information within the target detection area from the acquired video data. For example, the information collection system may transmit the collected video images including the vehicle to the computing system; and the operation system identifies the information of the vehicle type, the license plate and the like through a target detection algorithm according to the received video image. In addition, the computing system can also identify lane information in the target detection area according to the acquired video data, such as the position of each lane, lane lines and the like. In some embodiments, the computing system may also identify vehicle information from the point cloud data of the vehicle. For example, the information acquisition system may transmit the acquired point cloud image of the vehicle to the computing system; and the computing system calculates the information of the current position of the vehicle, the distance from the intelligent base station, the running speed of the vehicle, the course angle of the vehicle and the like according to the received three-dimensional point cloud coordinates of the vehicle in the point cloud image. The specific process of the computing system obtaining the vehicle and lane information according to the video data and the point cloud data can be referred to as the existing flow, and details of the process are not described in the application.

For example, in this embodiment of the application, the computing system may further perform fusion processing on the video data recognition result and the point cloud data recognition result of the same object to obtain more comprehensive perception information of the target detection area. For example, the computing system identifies first information of the vehicle according to the video data, and identifies second information of the vehicle according to the point cloud data; then, the computing system may perform fusion processing on the first information and the second information to obtain perception information of the vehicle. The video data identification result and the point cloud data identification result can be obtained by identifying the video data and the point cloud data which are acquired at the same time respectively.

Specifically, the following two methods can be adopted for the fusion processing process of the video data identification result and the point cloud data identification result: (1) The operation system can identify a two-dimensional coordinate corresponding to a certain vehicle (the two-dimensional coordinate is used for representing the position 1 of the vehicle in the video image) according to the collected video image corresponding to the first moment through a target detection algorithm, and can also determine a three-dimensional point cloud coordinate corresponding to the certain vehicle in the point cloud image (the three-dimensional point cloud coordinate is used for representing the position 2 of the vehicle in the point cloud image) according to the collected point cloud image corresponding to the first moment; then, the computing system can convert the two-dimensional coordinates according to a preset rotation and translation matrix and map the two-dimensional coordinates into three-dimensional point cloud coordinates (mapping coordinates) similar to those in the point cloud image; then, the computing system can compare the mapping coordinates with the three-dimensional point cloud coordinates corresponding to the point cloud image position 2, and if the mapping coordinates are registered with the three-dimensional point cloud coordinates corresponding to the point cloud image position 2, the vehicle at the position 1 in the video image and the vehicle at the position 2 in the point cloud image are the same vehicle; the information from the vehicle at location 1 and the information from the vehicle at location 2 may then be integrated to obtain more comprehensive sensory information about the vehicle 1. (2) The operation system can identify a two-dimensional coordinate corresponding to a certain vehicle (the two-dimensional coordinate is used for representing the position 1 of the vehicle in the video image) through a target detection algorithm according to the collected video image corresponding to the first moment; converting the two-dimensional coordinates corresponding to the vehicle at the position 1 through a rotation and translation matrix, and mapping the video image into a point cloud image; comparing the point cloud image obtained by mapping with the actually acquired point cloud image at the first moment, and if the positions of two vehicles are overlapped in the two point cloud images, indicating that the two vehicles are the same vehicle; the information identified from the video image of the vehicle may then be integrated with the information identified from the point cloud image to obtain more comprehensive perception of the vehicle.

It should be understood that through the above process, the smart base station may obtain the perception information of the vehicle in the target detection area, so as to determine the traffic conditions such as vehicle lane change more accurately in the following.

In addition, the operation system can also identify each lane and traffic flow states on each lane according to the point cloud data acquired by the laser radar and the video data acquired by the high-definition camera. For example, according to the video data, the intelligent base station can accurately obtain the positions of the lanes, such as dividing lines between the lanes, i.e. identify the boundaries of the lanes; according to the point cloud data, the intelligent base station can obtain the position of the vehicle; the number of vehicles included in each lane, the number of queued vehicles, the queuing length of the vehicles, the number of jammed vehicles, and the like can be obtained by integrating the lane positions and the positions of the vehicles. In other words, the computing system can enable the intelligent base station to accurately acquire more comprehensive state information such as traffic states (such as whether to change lanes, stop states or driving states and the like) of vehicles on each lane by comprehensively analyzing the point cloud data and the video data, so that the accuracy of subsequent traffic flow regulation and control is ensured. The computing system may also determine a lane management policy based on the vehicle status and the traffic flow status of the lane.

In some embodiments, the regulation system 1003 may be configured to regulate the associated signal lights according to the lane management policy indicated by the computing system 1002. The regulation and control system 1003 may have a communication capability, and may instruct the signal lamps to adjust the phase in a wired or wireless communication manner, thereby regulating and controlling the traffic flow direction and alleviating the traffic congestion.

It should be understood that the structure of the smart base station 100 shown in fig. 2 is merely an example, and in practical applications, the smart base station 100 may further include more systems or components than those shown in fig. 2. For example, the intelligent base station 100 may further include a storage system, which may be configured to store information of each vehicle and traffic flow status information (e.g., the number of vehicles jammed in the lane) in the lane, and the like, which is not limited in this embodiment.

According to the traffic control method provided by the embodiment of the application, the intelligent base station senses the vehicle information on the road in real time, the traffic state of each lane is comprehensively analyzed, lane traffic flow guidance is flexibly regulated and controlled based on the analysis result, and the congested traffic flow can be timely and efficiently dredged.

Fig. 3 is a schematic view of an application scenario of the traffic control method according to the embodiment of the present disclosure.

For example, the road intersection shown in fig. 3 may be provided with a smart base station (not shown in fig. 3), the smart base station includes a high-definition camera and a lidar, the high-definition camera may collect video data of an object in a target detection area in real time, the lidar may collect a point cloud image of the object in the target detection area in real time, and the target detection area of the high-definition camera and the lidar may be indicated by a circular dotted frame. For example, the target detection area may include a lane 1 and a lane 2, where the lane 1 may be a straight lane, and the vehicle in the lane 1 includes, for example: vehicle 1, vehicle 3, and vehicle 5; lane 2 may turn right the lane, the vehicles in lane 2 including, for example: vehicle 2, vehicle 4, and vehicle 6.

It should be understood that the embodiment of the present application mainly uses lane 1 and lane 2 to describe a method for traffic control, and in practical applications, other guiding lanes may also exist on the road, which is not limited in this application.

In some embodiments, the intelligent base station may acquire lane information of the target detection area in advance, such as lane position, lane guidance, and a boundary between lanes. For example, the intelligent base station acquires and stores in advance that lane 1 is a straight lane and lane 2 is a right-turn lane. For example, the method for acquiring the lane information by the smart base station may include the following two methods: (1) After the intelligent base station is installed, monitoring lane information in a detection area, for example, recognizing the lane information through video data collected by a high-definition camera and point cloud data collected by a laser radar; (2) The lane manager may input road information within the detection area into the intelligent base station. The intelligent base station can store the road information into a local storage system (such as a database) for later use in regulating traffic flow.

It should be understood that, since lane information such as lane positions and lane lines is generally fixed, when the lane information in the detection area is not changed, the intelligent base station may perform detection and recognition only once on the lane information in the target detection area, or the administrator may input the lane information to the intelligent base station only once, without updating the lane information each time traffic flow control is performed. Through the mode, on the basis of ensuring the accuracy of road information, the calculation resource and the storage resource of the intelligent base station can be saved, and the operation efficiency of the intelligent base station is improved.

In some embodiments, when a vehicle enters the target detection area, the high-definition camera may acquire a video image including the vehicle, and the smart base station may identify first information of the vehicle, such as a type of the vehicle, a license plate number, and the like, by performing calculation analysis on data of the video image. Meanwhile, the laser radar can acquire a point cloud image comprising the vehicle, and the intelligent base station can identify second information of the vehicle, such as the position of the vehicle, the running speed of the vehicle, the course angle of the vehicle, the length of the vehicle and the like, by calculating and analyzing the point cloud image data.

It should be understood that through the data of the object in the target detection area of high definition digtal camera and laser radar real-time collection, the wisdom basic station can in time high-efficiently perceive the vehicle state change in the target detection area.

In some embodiments, the smart base station may perform a fusion process on first information of the vehicle identified according to the video data and second information of the vehicle identified according to the point cloud data according to a fusion algorithm to obtain more three-dimensional and abundant perception information of the vehicle.

In some embodiments, the smart base station may also determine traffic flow status on each lane from the video data and the point cloud data, where the traffic flow status may include the number of vehicles jammed on the lane, the number of vehicles queued, the length of vehicles queued, and the like. The intelligent base station can store the traffic flow state on each lane in the database, and update the stored traffic flow state in real time according to the change of the traffic flow. For example, the smart base station may store traffic flow statuses in lane 1 and lane 2, respectively, examples of which may be as shown in table 1.

TABLE 1

Lane numbering	Number of vehicles/vehicles with plug	Number of vehicles in line/vehicle	length/Km of queued vehicles
				Lane
1	0	3	1
				Lane 2	1	3	1

It should be understood that the numerical values in table 1 are only examples, and the numerical values can be flexibly changed in practical applications, which is not limited in the present application.

In some embodiments, the smart base station may determine that the vehicle has changed lanes according to the offset and the offset direction of the heading angle of the vehicle. For example, taking the vehicle 1 in fig. 3 as an example, when the smart base station detects that the heading angle of the vehicle 1 is greatly deviated to the right (e.g., the heading angle deviation amount is greater than the fourth threshold), it is determined that the vehicle 1 changes lanes from lane 1 to lane 2, and the vehicle 1 is called a lane-change vehicle.

In some embodiments, after determining that the vehicle has changed lane, the smart base station may next determine whether the lane-change vehicle is a congested vehicle. Illustratively, still taking the vehicle 1 in fig. 3 as an example, the determination process may include: the intelligent base station determines a front vehicle on the side adjacent to the vehicle 1 and a rear vehicle on the side adjacent to the vehicle 1 in the lane 2 according to the position of the vehicle 1 and by combining point cloud data and video data, and calculates the distance length between the two vehicles; then, judging whether the vehicle 1 is jammed to the lane 2 according to the length of the vehicle body of the vehicle 1 and the distance length between the two vehicles at the front side and the rear side, wherein if the distance length is smaller than the length of the vehicle body of the vehicle 1, the jam of the vehicle 1 to the lane 2 is determined; and if the distance length is greater than or equal to the length of the vehicle body of the vehicle 1, determining that the vehicle 1 is in a normal lane change state, and not plugging the lane 2.

For example, as shown in fig. 3, when the smart base station detects that the heading angle of the vehicle 1 is deflected to the right and the amount of deflection is greater than 45 ° (fourth threshold), it may be determined that the vehicle 1 is a lane change vehicle, changing lanes from lane 1 to lane 2 on the right; the intelligent base station determines that a vehicle in front of the side adjacent to the vehicle 1 in the lane 2 is the vehicle 2 and a vehicle behind the side is the vehicle 4 according to the current position of the vehicle 1; then, the distance length between the vehicle 2 and the vehicle 4 is calculated (as noted as L1). After the vehicle 1 enters the target detection area, the intelligent base station already acquires and stores the vehicle body length (as denoted by L2) of the vehicle 1, so that the intelligent base station can call the vehicle body length L2 of the vehicle 1 to compare with the distance length L1, wherein if L2 < L1, it is determined that the vehicle 1 normally changes lane to the lane 2; and if the L2 is larger than or equal to the L1, determining that the vehicle 1 is a jammed vehicle of the lane 2.

In some embodiments, when vehicle 1 is determined to be a congested vehicle for lane 2, the intelligent base station may update the traffic flow status of the second lane stored in the database, such as increasing the total number of congested vehicles in lane 2 by 1.

In some embodiments, the intelligent base station may determine whether to dynamically manage the lanes based on the number of congested vehicles or the rate of congestion in the traffic flow state. The congestion ratio can be the ratio of the number of vehicles congested on the lane to the length of the vehicles queued on the lane; or, the congestion ratio may also be a ratio of the number of congested vehicles on the lane to the total number of queued vehicles on the lane; alternatively, the jam may be a ratio of the number of vehicles jammed within a predetermined time (e.g., within 10 minutes) to the number of all vehicles passing through the lane.

As one example, the intelligent base station may dynamically manage the lane when the number of congested vehicles in the lane is greater than a first threshold, or an average of the number of congested vehicles in the lane within a first preset time is greater than a second threshold.

As another example, the intelligent base station may dynamically manage the lane when the congestion ratio on the lane is greater than a third threshold. For example, when the congestion ratio in lane 2 is greater than the third threshold, the intelligent base station may instruct the signal light corresponding to lane 1 to change to the same phase as lane 2, that is, the signal light corresponding to lane 1 guides the traffic flow to turn right, so that the vehicles in lane 1 do not need to change to lane 2, and may divert part of the traffic flow of lane 2, thereby dredging the traffic congestion of lane 2.

According to the traffic control method provided by the embodiment of the application, the intelligent base station senses the vehicle information and lane information on the road in real time, the traffic flow state of each lane is comprehensively analyzed, the lane traffic flow guiding direction is flexibly regulated and controlled based on the analysis result, and the congested traffic flow is effectively dredged in time.

In the above embodiment, the traffic control method provided in the embodiment of the present application is introduced from a system architecture and an application scenario layer, and in order to better understand the traffic control method provided in the embodiment of the present application, the following embodiment introduces an internal implementation process thereof.

Exemplarily, as shown in fig. 4, a schematic flow chart of a method for traffic control according to an embodiment of the present application is provided. The process can be executed by the intelligent base station as a main body, and can include the following specific steps:

s401, at least one lane-changing vehicle changing from a first lane to a second lane in the target detection area is obtained.

For example, the target detection area may refer to a specific area at a road intersection.

For example, the first lane and the second lane may be two adjacent lanes on the same road, and the guidance of the first lane and the second lane may be different. For example, the first lane may be a straight lane (e.g., lane 1 in fig. 3), and the second lane may be a right-turn lane (e.g., lane 2 in fig. 3), which is not limited in this application.

In some embodiments, the smart base station may collect video data in the target detection area through the high definition camera and collect point cloud data in the target detection area through the laser radar; then, identifying first information of a target detection area according to the video data, and identifying second information of the target detection area according to the point cloud data; and then, the first information and the second information are subjected to fusion processing to obtain perception information of the target detection area, wherein the perception information can be used for identifying lane-changing vehicles and jammed vehicles of a second lane.

Wherein the first information refers to a recognition result obtained by using the video data. For example, the first information may include the vehicle type, the license plate number, and the like of the vehicle 1 as shown in table 2.

TABLE 2

Vehicle number	Vehicle	1
			Type of vehicle	Medium size car
License plate number	XXXXXX

The second information refers to a recognition result obtained by using the point cloud data. For example, the second information may include a body length of the vehicle 1, a vehicle position, a traveling speed of the vehicle, a heading angle of the vehicle, and the like, as shown in table 3.

TABLE 3

Vehicle number	Vehicle	1
			Length of car body	4m
Vehicle position	First position (latitude, longitude)
		Speed of travel	20Km/h
Course angle	45°

In some embodiments, the smart base station performs fusion processing on the first information and the second information, and may obtain perception information of the vehicle 1. Illustratively, the perception information may be as shown in table 4:

TABLE 4

Vehicle number	Vehicle	1
			Type of vehicle	Medium size car
License plate number	XXXXXX
		Length of car body	4m
Vehicle position	First position (latitude, longitude)
		Speed of travel	20Km/h
Course angle	45°

It should be understood that the information shown in tables 2 to 4 is only an example, and in practical applications, the first information, the second information, and the perception information may also include more other information, which is not limited in this application.

Through fusing the recognition result that will acquire according to the point cloud data with the recognition result that acquires according to video data, can acquire the more three-dimensional abundant perception information of vehicle in the target detection area to make the state of each vehicle in the target detection area can be known in real time to the wisdom basic station, so that regulate and control the traffic flow more accurately.

In some embodiments, the smart base station may determine lane-change vehicles based on the perception information of the vehicles. For example, the specific manner in which the smart base station may determine the lane-change vehicle according to the perception information may include: the intelligent base station can determine the offset and the offset direction of the course angle of at least one vehicle in the target detection area according to the perception information; and determining at least one lane-changing vehicle changing from the first lane to the second lane according to the offset and the offset direction of the heading angle of the at least one vehicle. For example, when the intelligent base station judges that the deviation of the heading angle of a certain vehicle between the preset values is larger than a fourth threshold value, or when the intelligent base station judges that the deviation of the heading angle of a certain vehicle is larger than the fourth threshold value according to two continuous frames of point cloud images, the vehicle can be determined to be a lane-changing vehicle.

S402, determining a jammed vehicle in a second lane from the lane-change vehicles according to the positions of the lane-change vehicles and the positions of the vehicles in the second lane.

In some embodiments, the smart base station may determine a location of the lane-change vehicle and a vehicle location in the second lane from the perception information; and then determining a jammed vehicle in the second lane from the lane-change vehicles according to the position of the lane-change vehicle and the position of the vehicle in the second lane.

In some embodiments, the manner of determining a congested vehicle in a second lane from lane-change vehicles may include: determining a first vehicle in the second lane in front of the lane-change vehicle and a second vehicle in the second lane behind the lane-change vehicle according to the position of the lane-change vehicle and the position of the vehicle in the second lane; determining a distance length between the first vehicle and the second vehicle; and when the distance length is smaller than the length of the vehicle body of the lane-changing vehicle, determining the lane-changing vehicle as a jammed vehicle of the second lane.

It should be understood that the first vehicle in the second lane located in front of the lane-changing vehicle side refers to a vehicle located in the second lane, which is adjacent to the lane-changing vehicle and located in front of the lane-changing vehicle side, that is, there is no other vehicle barrier between the vehicle in front of the lane-changing vehicle and the lane-changing vehicle; the second vehicle located behind the lane-change vehicle in the second lane is a vehicle located in the second lane, adjacent to the lane-change vehicle and located behind the lane-change vehicle, that is, no other vehicle barrier exists between the vehicle behind the lane-change vehicle and the lane-change vehicle.

In some embodiments, the smart base station may acquire and store traffic flow status information corresponding to lanes in the target detection area according to the perception information in the target detection area (as shown in table 1). For example, the traffic flow status information may include the total number of congested vehicles in the second lane, such as the total number of congested vehicles in the current second lane, the total number of congested vehicles in the second lane within a preset time period, and the like. Optionally, the traffic flow status information may further include one or more of the total number of passing vehicles in the second lane, the length of queued vehicles in the second lane, the number of queued vehicles in the second lane, and the like within a preset time period.

In some embodiments, after determining the congested vehicles in the second lane from the lane-change vehicles, the intelligent base station may update the number of congested vehicles in the traffic flow status information (e.g., table 1) of the second lane stored in the local database, such as increasing the number of congested vehicles in the second lane by 1, to obtain the latest total number of congested vehicles in the second lane.

And S403, adjusting the traffic flow guide of the first lane according to the number of the vehicles which are added with the traffic jam of the second lane, so that the traffic flow guide of the first lane is the same as the traffic flow guide of the second lane.

In some embodiments, the intelligent base station adjusting the traffic flow guidance of the first lane according to the number of congested vehicles in the second lane may include at least the following three situations:

situation 1, when the number of congested vehicles in the second lane is greater than a first threshold, adjusting traffic flow guidance of the first lane;

situation 2, calculating an average value of the number of the vehicles jammed in the second lane within a first preset time according to the number of the vehicles jammed in the second lane; when the average value is larger than a second threshold value, adjusting the traffic flow guidance of the first lane;

and 3, acquiring the traffic jam proportion of the vehicles in the second lane, and adjusting the traffic flow guidance of the first lane when the traffic jam proportion is greater than a third threshold value.

In case 3, the jam proportion of the second lane may be calculated and obtained in the following manners: (1) acquiring the queuing length of the vehicles in the second lane; determining the congestion proportion of the second lane according to the number of the congested vehicles in the second lane and the queuing length; (2) Calculating the ratio of the number of the jammed vehicles in the second lane to the number of the queued vehicles in the second lane to obtain a jamming ratio; (3) And calculating the ratio of the number of the vehicles which are jammed in the second lane within the preset time to the total number of the vehicles passing through the second lane within the preset time to obtain the jamming ratio.

In some implementations, the intelligent base station adjusting the traffic flow direction of the first lane such that the traffic flow direction of the first lane is the same as the traffic flow direction of the second lane may include: the wisdom basic station instructs the signal lamp adjustment that first lane corresponds to target phase place, and this target phase place is the same with the phase place of the signal lamp that the second lane corresponds. For example, the smart base station may send indication information to a signal lamp corresponding to the first lane, where the indication information is used to indicate that the signal lamp is adjusted to the target phase within a preset time period.

It should be understood that, in practical applications, each lane may be respectively corresponding to a signal lamp, the phase of the signal lamp may be used for guiding the flow direction of traffic flow in the lane, and by adjusting the signal lamp corresponding to the first lane to be in the same phase as the signal lamp corresponding to the second lane, the first lane and the second lane may have the same traffic flow guidance, so as to reduce the vehicle congestion degree of the second lane.

Optionally, the intelligent base station may further indicate lanes with low road resource utilization rate) to adjust the phase of the signal lamp corresponding to the lane with low lane resource utilization rate to the target phase, and adjust the traffic flow direction of the lane with low lane resource utilization rate to the same traffic flow direction as that of the lane with traffic congestion, so that the lane with low lane resource utilization rate may perform traffic diversion to relieve the pressure in the lane with traffic congestion, and thus, traffic congestion is timely dredged.

According to the traffic control method provided by the embodiment of the application, the intelligent base station senses the vehicle information and the lane information on the road in real time, the traffic flow state of each lane is comprehensively analyzed, the traffic flow direction of the lanes is flexibly regulated and controlled based on the analysis result, and the congested traffic flow can be efficiently dredged in time.

For example, as shown in fig. 5, a schematic flow chart of a method for more detailed traffic control provided in the embodiment of the present application is shown. The process may be performed by the smart base station as a subject. In this embodiment, after the vehicle (such as the lane-change vehicle or the vehicle 1) enters the target detection area, the process may specifically include the following steps:

s501, reading the video data and detecting first information of the vehicle.

In some embodiments, the computing system of the smart base station may read video data collected by a high-definition camera in the target detection area, where the video data may include video data corresponding to the vehicle, such as a video image of the vehicle. The operation system identifies first information of the vehicle by adopting a target detection algorithm according to video data corresponding to the vehicle, wherein the first information can comprise information such as vehicle type, license plate number and the like. For example, for a large vehicle, the computing system may identify the license plate information of the vehicle target using a license plate recognition algorithm, and determine the specific vehicle based on the license plate information.

In some embodiments, after the intelligent base station determines a specific vehicle, information transmission can be performed through the vehicle-mounted communication device of the vehicle. For example, the smart base station may send traffic guidance information, road condition prompting information, and the like to the vehicle.

It should be understood that through this step, the intelligent base station can acquire information of the specific type of the vehicle in each lane, the license plate, and the like.

And S502, reading the point cloud data and detecting second information of the vehicle.

In some embodiments, the computing system of the smart base station may read point cloud data within a target detection area acquired by the laser radar, which may include corresponding point cloud data of the vehicle. The computing system identifies first state information of the vehicle by using a target detection algorithm according to the point cloud data corresponding to the vehicle, wherein the first state information can comprise information such as the position, the speed and the course angle of the vehicle.

It should be understood that the smart base station may simultaneously acquire the video data and the point cloud data, and thus the steps S501 and S502 may be simultaneously performed by the smart base station.

And S503, fusing the perception information of the same vehicle through a fusion algorithm.

In some embodiments, the computing system of the smart base station may perform fusion processing on the first information and the second information of the same vehicle to obtain perception information of the same vehicle. The perception information may include, for example, vehicle position, speed, travel track, heading angle, vehicle length, etc. of the vehicle.

It should be understood that, through this step, the intelligent base station can acquire a more comprehensive state of the vehicle, so that the traffic flow state of each lane can be accurately known.

S504, lane information is obtained, and lane positions such as left turn, straight running, right turn and the like are determined.

In some embodiments, the computing system of the smart base station may obtain location information of each lane. Alternatively, the step S504 may be executed in advance before the flow of this embodiment is started.

In some embodiments, the manner in which the smart base station acquires the lane information may include: (1) judging the position of each lane according to the video data; (2) The road manager inputs the position of each lane, etc., but the present application is not limited thereto.

And S505, acquiring traffic flow state information in each lane, wherein the traffic flow state information comprises information such as the number of queued vehicles in the lane.

In some embodiments, traffic flow state information within the respective lanes may be obtained based on perceptual information of the vehicle. The traffic flow status information may further include a plurality of information such as vehicle positions in the lane, a spacing between vehicles, a heading angle of vehicles, a spacing between vehicles, and the like.

S506, judging whether the offset of the current vehicle heading angle of the continuous frames is larger than a fourth threshold value.

In some embodiments, the smart base station may determine the heading angle offset of the vehicle according to two consecutive frames of the point cloud images. If the offset of the course angle of the vehicle is smaller than or equal to the fourth threshold, indicating that the current vehicle has no lane changing behavior; if the offset of the heading angle of the vehicle is greater than the fourth threshold, it indicates that the lane change behavior of the vehicle occurs, and step S507 may be executed next.

The fourth threshold may be preset according to information such as a vehicle type and a vehicle length, and the fourth threshold may be, for example, a value in a range from 0 ° to 90 °, which is not limited in this application.

And S507, judging whether the distance between the front vehicle and the rear vehicle is less than or equal to the length of the vehicle body in the lane where the current vehicle is going to enter.

In some embodiments, the intelligent base station may determine a front vehicle and a rear vehicle adjacent to the current vehicle in the lane change lane according to the position of the current vehicle, and acquire a distance length between the front vehicle and the rear vehicle.

In some embodiments, the intelligent base station may determine whether the current vehicle is a congested vehicle in a lane change lane according to a length of a body of the current vehicle and a length of a space between two vehicles. If the distance between the front vehicle and the rear vehicle is greater than the length of the vehicle body, indicating that the current vehicle is in a normal lane changing behavior; if the distance between the front vehicle and the rear vehicle is less than or equal to the length of the vehicle body, it indicates that the current vehicle is a congested vehicle, and step S508 may be performed next.

And S508, judging the number of the vehicles with the jam in the lane change.

In some embodiments, when it is determined that the current vehicle is a congested vehicle in a lane change lane, the intelligent base station may update the database of the number of congested vehicles corresponding to the lane change lane plus 1.

S509, the vehicle queuing length of the lane change lane to be entered currently is calculated according to the position, the direction and the like of the vehicle.

In some embodiments, the intelligent base station may determine the queuing length of the vehicles based on traffic flow status information in each lane. For example, for a lane change lane, the intelligent base station may know the position and the driving direction of each vehicle according to the traffic flow state information of the lane change lane, and obtain the length of the queued vehicles of the lane change lane based on the position and the driving direction.

And S510, calculating the jamming proportion in the lane changing lane.

In some embodiments, the intelligent base station may calculate the proportion of congestion in the lane-change lane based on the number of congested vehicles in the lane-change lane and the length of queued vehicles. For a specific calculation manner, reference may be made to the above related descriptions, which are not described herein again.

And S511, judging whether the road changing lane jamming ratio is larger than a third threshold value.

For example, the third threshold value may be obtained according to a traffic flow state such as a traffic flow of the lane change lane at the current time.

In some embodiments, if the congestion ratio of the lane change lane is less than or equal to the third threshold, it indicates that there is no obvious congestion phenomenon in the lane change lane; if the congestion ratio of the lane-change lane is greater than the third threshold, it indicates that a significant congestion phenomenon (or traffic congestion phenomenon) occurs in the lane-change lane, and then step S512 may be executed.

And S512, adjusting the signal lamp at regular time, and changing the original lane direction of the vehicle into the lane changing direction.

In some embodiments, when the lane-changing lane jamming phenomenon is serious, the intelligent base station performs dynamic lane management. Specifically, the intelligent base station may instruct the signal lamp corresponding to the lane where the current vehicle is initially located to adjust to the same phase as the lane-changing signal lamp, that is, change the traffic flow guiding direction of the lane where the vehicle is initially located to the traffic flow guiding direction of the lane-changing lane, and increase the number of lanes in the traffic flow direction of the traffic congestion lane.

S513, the vehicle travels as indicated by the signal light.

According to the traffic control method provided by the embodiment of the application, fusion information of the laser radar and the multi-view video data is fused by the intelligent base station, so that multiple tasks such as vehicle target detection, tracking, license plate recognition and the like are carried out in real time, and the traffic conditions of all lanes at a traffic intersection are comprehensively sensed; judging the lane changing condition of the vehicle based on the vehicle position and the course angle information, and judging whether the lane changing behavior of the vehicle is jamming or not through the inter-vehicle distance of the lane changing; counting the proportion of the vehicles jammed in each lane to the number of the vehicles in the lane, and further judging the resource utilization rate of the lane in the road at the moment; through the timing dynamic lane management, the lane flow direction is regulated and controlled, and the road utilization rate is safely and efficiently improved.

The above is mainly specifically described for the traffic control process in the vehicle congestion behavior scene. However, the traffic control method provided by the embodiment of the application is not only suitable for the congestion scene, but also suitable for various other vehicle behaviors and vehicle type scenes. Generally speaking, the traffic control method provided by the embodiment of the application counts vehicle distribution according to vehicle behaviors and/or vehicle types (such as emergency rescue vehicle types), and correspondingly performs traffic control based on the vehicle distribution, so that traffic congestion is relieved, and traffic safety is improved.

Exemplarily, as shown in fig. 6, a schematic flow chart of a further traffic control method provided in the embodiment of the present application is shown. The intelligent base station can be used as an execution subject of the method, and the method comprises the following steps:

s601, vehicle information in the target detection area is obtained through an intelligent base station arranged in the target detection area, wherein the vehicle information comprises vehicle types and/or vehicle behaviors.

For example, the smart base station may identify a vehicle type and/or vehicle behavior based on point cloud data collected by the lidar and image data collected by the camera. The identification process or principle can be referred to the above related description, and is not described herein again to avoid repetition.

In some embodiments, the vehicle behavior may include lane change behavior, jamming behavior of the vehicle, for example. In addition, the vehicle behavior may specifically include vehicle braking, deceleration, hard braking, and the like.

S602, acquiring distribution information in a target detection area according to vehicle information; when the vehicle information includes the vehicle type, the distribution information is the vehicle distribution obtained based on the vehicle type statistics; when the vehicle information includes the vehicle behavior, the distribution information is a vehicle distribution obtained based on the vehicle behavior statistics.

In some embodiments, the smart base station may previously acquire and store a preset vehicle type, which may include a special vehicle performing a specific task (such as an emergency rescue task), and may include, for example: ambulances, police cars, disaster relief cars, fire trucks, and the like.

In some embodiments, the smart base station may perform processing analysis based on the point cloud data collected by the laser radar and the image data collected by the camera, and obtain a distribution of the vehicle of the preset vehicle type, for example, identify a lane where the vehicle of the preset vehicle type is located. The process of acquiring the distribution condition of the vehicle of the preset vehicle type by the intelligent base station may refer to the related description above, and is not described herein again.

For example, when the smart base station detects that there is an ambulance in the target detection area, it can further determine which lane the ambulance is distributed on according to the lane information and the location of the ambulance, and obtain the distribution of the specific vehicle.

Similarly, the intelligent base station can also determine the distribution of vehicles in the road according to the vehicle behaviors. For example, after the intelligent base station identifies a congested vehicle and identifies a lane where the congested vehicle is located, the intelligent base station may further statistically analyze the number and the positions of the congested vehicles distributed on each lane; or, the intelligent base station can further statistically analyze which lanes and positions all the jammed vehicles are distributed in the target detection area.

S603, carrying out traffic control on the target detection area according to the distribution information.

The traffic control may include regulating and controlling a traffic flow direction of a lane; alternatively, the traffic control may include management of maintenance, repair, and the like of the road or lane. The purpose of traffic control is to alleviate traffic congestion conditions, or to give priority to passage of vehicles performing specific tasks (such as emergency rescue tasks), and the like. The embodiment of the present application does not limit the specific type of traffic control.

Whereas the above embodiments of fig. 4 and 5 have been described in detail with respect to the traffic control process in the congestion scenario, the description is mainly made with respect to the traffic control process in the scenario where a special vehicle exists in the target detection area.

Illustratively, when the vehicle type of the target detection area is a preset vehicle type, the smart base station may perform traffic control through a process specifically including:

s6031, the history of the running state of the vehicle of the preset vehicle type is acquired.

In some embodiments, when the vehicle enters the target detection area, the smart base station may detect and recognize a driving state of the vehicle and store a history of the driving state of the vehicle. The driving state may include, for example, a driving speed, a heading angle, a position, and the like of the vehicle. Thereafter, the smart base station may predict a subsequent possible travel state of the vehicle based on the historical travel state of the vehicle. In addition, the intelligent base station can predict the lane which the vehicle may continue to travel according to the lane position.

S6032, the predicted travel state of the vehicle of the preset vehicle type is acquired from the history travel state.

The historical travel state may be, for example, travel information of the vehicle during a period from a time when the vehicle enters the target detection area to a current time. The historical driving state may also include information such as the location, heading angle, etc. of the vehicle. Based on this information, the intelligent base station can predict the next possible travel trajectory of the vehicle, in particular the travel trajectory of a vehicle of a preset vehicle type.

For example, the intelligent base station may predict whether the vehicle will change lanes next according to the position, the heading angle, and the like of a vehicle (such as an ambulance) of a preset vehicle type, and if so, may regulate and control traffic flow guidance of a lane after lane change, so that the vehicle can pass through as soon as possible after lane change; if not, the traffic flow guidance of the current lane of the vehicle can be regulated and controlled so that the vehicle can pass through as soon as possible.

And S6033, acquiring the lane where the vehicle of the preset vehicle type is located based on the vehicle distribution.

The intelligent base station can determine the lane where the vehicle is located according to the position of the vehicle, the position of the lane and the like. The manner of determining the lane where the vehicle is located may refer to the related description of the foregoing, and will not be described herein again.

And S6034, performing traffic control on the lane where the vehicle of the preset vehicle type is located, so that the vehicle of the preset vehicle type meets the predicted driving state.

In some embodiments, the intelligent base station may predict a lane in which a vehicle of a predetermined vehicle type may want to continue traveling based on the lane in which the vehicle is located. Referring to fig. 3, a process for predicting a vehicle of a preset type by a smart base station will be described by taking the preset vehicle type as an ambulance.

As an example, assuming that the vehicle 2 in the lane 2 shown in fig. 3 is an ambulance, the intelligent base station may determine that the vehicle 2 is currently in the lane 2 based on the position of the vehicle 2 within a history period (e.g., from the time of entering the target detection area to the current time) and the lane position; then, it is predicted that the vehicle 2 will continue to travel in the lane 2, based on the fact that the heading angle of the vehicle 2 has not changed by a large amount over the history period. Meanwhile, the intelligent base station is based on that the vehicle 2 is an ambulance and belongs to a preset vehicle type, and can control the traffic flow corresponding to the lane 2 to keep smooth, for example, a signal lamp is controlled to keep a green light until the vehicle 2 drives through an intersection.

As still another example, assuming that the vehicle 1 in the lane 1 shown in fig. 3 is an ambulance, the intelligent base station may determine that the vehicle 1 is currently in the lane 1 based on the position of the vehicle 1 within a history period (e.g., from the time of entering the target detection area to the current time) and the lane position; then, it is predicted that the vehicle 1 intends to change the lane to travel in the lane 2 based on the change of the heading angle of the vehicle 1 occurring in a large magnitude (e.g., the magnitude of the change is larger than the first threshold) within the history period. Meanwhile, the intelligent base station is based on that the vehicle 1 is an ambulance and belongs to a preset vehicle type, can control traffic flow guidance in the lane 2, enables traffic flow corresponding to the lane 2 to be kept smooth, and regulates signals corresponding to the lane 2 and the like to keep green light until the vehicle 1 drives through an intersection.

As yet another example, assuming that the vehicle 3 in the lane 1 shown in fig. 3 is an ambulance, the intelligent base station may determine that the vehicle 3 is currently in the lane 1 based on the position of the vehicle 3 within a history period (e.g., from the time of entering the target detection area to the current time) and the lane position; meanwhile, the vehicle 1 can be judged to be positioned in front of the vehicle 3 according to the position and the running state of the vehicle 1; moreover, the intelligent base station can also predict that the vehicle 1 wants to change lane to the lane 2 to drive according to the fact that the heading angle of the vehicle 1 changes greatly in the historical period (for example, the change amplitude is larger than the first threshold), and predict that the vehicle 3 still continues to drive in the lane 1 without the heading angle of the vehicle 3 changing greatly in the historical period. Based on the fact that the vehicle 3 is a preset vehicle type, in order to enable the vehicle 3 to preferentially pass through the lane and keep the smooth running process of the vehicle, the intelligent base station can control the traffic flow guidance in the lane 1, so that the traffic flow corresponding to the lane 1 is kept smooth, for example, signals corresponding to the lane 1 are controlled to keep green light until the vehicle 3 passes through the intersection. Meanwhile, considering that the vehicle 1 is located in front of the vehicle 3, in order to enable the vehicle 1 to change to the lane 2 as soon as possible and eliminate the blocking of the vehicle 3, the intelligent base station can also regulate and control the traffic flow guidance in the lane 2, so that the traffic flow corresponding to the lane 2 is kept smooth until the vehicle 1 smoothly changes to the lane 2, and the blocking effect of the vehicle 3 is eliminated.

It should be understood that the above cases are only examples, and in practical applications, other cases may be included. For example, the intelligent base station also counts the distribution of the vehicle in the lane according to the vehicle behavior, and performs traffic control based on the distribution.

For example, the intelligent base station may detect whether the vehicle has sudden braking, deceleration, and other behaviors according to the driving speed of the vehicle, and if it detects that more vehicles have sudden braking, deceleration, and other behaviors all at a certain position on the road, it means that the road condition at the position is possibly not good, and maintenance is required. At this moment, the wisdom basic station can carry out the suggestion to road management personnel, makes relevant personnel maintain the road to guarantee the road safety of vehicle.

The specific mode that the traffic control is carried out based on vehicle behavior and/or vehicle type to wisdom base station can set up according to actual conditions is nimble, and this application does not limit this.

For example, as shown in fig. 7, a schematic structural diagram of an intelligent base station according to an embodiment of the present application is provided. The smart base station 700 includes a laser radar 701, a camera 702, a processor 703, a memory 704, and a bus 705.

The camera 702 is configured to collect video data in a target detection area; the laser radar 701 is used for acquiring point cloud data in the target detection area; a memory 704 for storing computer readable instructions; the processor 701 is configured to execute the computer readable instructions, and when the computer readable instructions are executed, the smart base station is enabled to implement the traffic control method described above.

The embodiment of the application further provides a system for lane management, which comprises an intelligent base station and a signal lamp, wherein the intelligent base station is used for executing the traffic control method introduced in the application, and the signal lamp is used for adjusting the phase according to the indication of the intelligent base station.

Embodiments of the present application further provide a computer-readable storage medium, which includes computer instructions, and when the computer instructions are executed in a computer, the method for traffic control is implemented.

The embodiment of the present application further provides a computer product, which includes computer instructions, and when the computer instructions are executed in a computer, the method for traffic control is implemented.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer commands. The procedures or functions described in accordance with the embodiments of the present application are generated in whole or in part when the computer program commands are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer commands may be stored in or transmitted through a computer-readable storage medium. The computer commands may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optics, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.

One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program that can be executed by associated hardware, the computer program can be stored in a computer-readable storage medium, and the processes when executed can include the processes of the above method embodiments. And the aforementioned storage medium includes: various media capable of storing program codes, such as ROM or RAM, magnetic or optical disks, etc.

The above description is only a specific implementation of the embodiments of the present application, but the scope of the embodiments of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the embodiments of the present application should be covered by the scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of traffic management, the method comprising:

the method comprises the steps that vehicle information in a target detection area is obtained through an intelligent base station arranged in the target detection area, wherein the vehicle information comprises vehicle types and/or vehicle behaviors;

acquiring distribution information in the target detection area according to the vehicle information, wherein when the vehicle information comprises the vehicle type, the distribution information is vehicle distribution obtained through statistics based on the vehicle type; when the vehicle information includes the vehicle behavior, the distribution information is a vehicle distribution statistically derived based on the vehicle behavior; the distribution information comprises a lane where the corresponding vehicle is located and a position in the lane; the lane where the vehicle is located and the position in the lane are detected by the intelligent base station;

acquiring at least one lane-changing vehicle changing from a first lane to a second lane in the target detection area according to the distribution information;

determining a congested vehicle in the second lane from the lane-change vehicles according to the position of the lane-change vehicles and the position of the vehicle in the second lane;

acquiring the queuing length of the vehicles in the second lane;

determining the congestion proportion of the second lane according to the number of the congested vehicles in the second lane and the queuing length;

when the congestion ratio is larger than a third threshold value, adjusting the traffic flow guidance of the first lane so that the traffic flow guidance of the first lane is the same as the traffic flow guidance of the second lane.

2. The method of claim 1, wherein when the vehicle type is a preset vehicle type, the method further comprises:

acquiring the historical driving state of the vehicle of the preset vehicle type;

acquiring a predicted driving state of the vehicle of the preset vehicle type according to the historical driving state;

acquiring a lane where a vehicle of the preset vehicle type is located based on the vehicle distribution;

and carrying out traffic control on the lane where the vehicle of the preset vehicle type is located, so that the vehicle of the preset vehicle type meets the predicted running state.

3. The method of claim 2, wherein the preset vehicle type comprises at least one of:

ambulances, police cars, disaster relief cars and fire engines.

4. Method according to any of claims 1-3, wherein said determining from said lane-change vehicles a congested vehicle in said second lane according to a position of said lane-change vehicle and a vehicle position in said second lane, comprises in particular:

determining a first vehicle in the second lane located in front of the lane-change vehicle side and a second vehicle in the second lane located behind the lane-change vehicle side according to the position of the lane-change vehicle and the position of the vehicle in the second lane;

determining a length of a gap between the first vehicle and the second vehicle;

and when the distance length is smaller than the length of the body of the lane-changing vehicle, determining that the lane-changing vehicle is a jammed vehicle of the second lane.

5. The method according to claim 4, wherein adjusting the traffic flow guidance of the first lane according to the number of the jammed vehicles of the second lane specifically comprises:

when the number of the jammed vehicles of the second lane is larger than a first threshold value, adjusting traffic flow guidance of the first lane; or,

calculating the average value of the number of the vehicles which are jammed in the second lane within first preset time according to the number of the vehicles which are jammed in the second lane;

and when the average value is larger than a second threshold value, adjusting the traffic flow guidance of the first lane.

6. The method according to claim 1, wherein the adjusting the traffic flow guidance of the first lane such that the traffic flow guidance of the first lane is the same as the traffic flow guidance of the second lane comprises:

and indicating the signal lamp corresponding to the first lane to be adjusted to a target phase, wherein the target phase is the same as the phase of the signal lamp corresponding to the second lane.

7. The method of claim 6, further comprising:

collecting video data and point cloud data of the target detection area;

identifying first information of the target detection area according to the video data, and identifying second information of the target detection area according to the point cloud data;

and performing fusion processing on the first information and the second information to acquire perception information of the target detection area, wherein the perception information is used for identifying the lane-changing vehicle and the jammed vehicle of the second lane.

8. The method according to claim 7, wherein acquiring at least one lane-change vehicle changing from a first lane to a second lane in the target detection area specifically comprises:

determining the offset and the offset direction of the course angle of at least one vehicle in the target detection area according to the perception information;

and determining at least one lane-changing vehicle changing from the first lane to the second lane according to the offset and the offset direction of the heading angle of the at least one vehicle.

9. The method according to claim 7 or 8, wherein the determining of the congested vehicle in the second lane from the lane-change vehicles based on the position of the lane-change vehicle and the position of the vehicle in the second lane comprises:

determining the position of the lane-changing vehicle and the position of the vehicle in the second lane according to the perception information;

and determining a jammed vehicle of the second lane from the lane-change vehicles according to the position of the lane-change vehicles and the position of the vehicle in the second lane.

10. An intelligent base station, comprising:

the camera is used for collecting video data in a target detection area;

the laser radar is used for acquiring point cloud data in the target detection area;

a memory for storing computer readable instructions;

a processor for executing the computer readable instructions, which when executed, cause the smart base station to implement the method of any one of claims 1 to 9.

11. A system for lane management, comprising a smart base station for performing the method according to any one of claims 1 to 9, and a signal lamp for adjusting a phase according to an indication of the smart base station.

12. A computer-readable storage medium comprising computer instructions that, when executed, cause the method of any of claims 1-9 to be implemented.