CN108550262B - Urban traffic sensing system based on millimeter wave radar - Google Patents
Urban traffic sensing system based on millimeter wave radar Download PDFInfo
- Publication number
- CN108550262B CN108550262B CN201810554906.6A CN201810554906A CN108550262B CN 108550262 B CN108550262 B CN 108550262B CN 201810554906 A CN201810554906 A CN 201810554906A CN 108550262 B CN108550262 B CN 108550262B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- detection
- traffic
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/91—Radar or analogous systems specially adapted for specific applications for traffic control
Abstract
The invention discloses an urban traffic sensing system based on a millimeter wave radar, belongs to the technical field of road traffic state detection, and solves the problem that a traditional traffic information detection system cannot meet the information requirement of the front section of modern traffic. The intelligent traffic sensing system mainly comprises a data detection module, a data transmission module, a data receiving module, a data processing module, a data analysis module and a data sharing module, and a simple and efficient data processing method and an analysis method, firstly provides the detection of urban traffic data and the estimation of information by means of a military millimeter wave radar technology, and provides a whole set of functional modules and an implementation method of the traffic sensing system, so that the accurate positioning of accidents is realized, the estimation of accident condition information required by other traffic management and control is also realized, the intelligent traffic sensing system has strong economic benefits and social benefits, and has important significance in the technical field of intelligent traffic.
Description
Technical Field
The invention belongs to the technical field of road traffic states, and particularly relates to an urban traffic sensing system based on a millimeter wave radar.
Background
With the continuous improvement of urbanization and economic level in China, the quantity of motor vehicles in cities and the travel demand of residents are rapidly increased, and increasingly intensified traffic jam, traffic accidents, tail gas emission and energy consumption become important obstacles influencing urban development and modern ecological civilization construction. Through the powerful development of new technologies such as cloud computing, big data, internet, mobile internet and the like, an intelligent traffic system taking data perception as a core foundation is further developed, and particularly, the intelligent traffic system is implemented and applied to ground in the aspects of traffic planning and design, intelligent signal control, traffic guidance, intelligent public transportation and the like, so that urban traffic jam is remarkably relieved, and urban traffic operation efficiency is improved. Urban traffic data detection is the basic guarantee for the construction of intelligent traffic systems and is also the basis for implementing all traffic planning, design, management, control, operation and evaluation. Therefore, the construction of a comprehensive, accurate, real-time and shared data detection system is an important direction for modern traffic development.
Generally, traffic data detection refers to the quantitative or qualitative detection of one or more traffic volumes by one or more types of detectors, and commonly used detectors include coil detectors, geomagnetic detectors, ultrasonic detectors, microwave detectors, infrared detectors, video detectors, satellite mobile positioning detectors, and the like. The traffic data that each type of detector can detect includes one or more of flow, speed, occupancy, travel time, queue length, license plate, headway, vehicle trajectory, etc., but none of the types of detectors can cover all traffic parameters. Moreover, with the continuous change of urban traffic management and control demands, the detection of traffic volume has been far from meeting the demands of system planners, managers and designers, and more detection demands are proposed for daily traffic management and control, such as traffic accidents, congestion degrees, illegal parking, and the like. Therefore, the simple traffic data detection cannot meet the front-end information requirement of modern traffic.
Disclosure of Invention
The invention aims to provide a millimeter wave radar-based urban traffic sensing system aiming at the defects in the prior art.
The invention is realized by the following technical scheme:
the utility model provides a city traffic perception system based on millimeter wave radar which characterized in that: the device comprises a data detection module, a data transmission module, a data receiving module, a data processing module, a data analysis module and a data sharing module;
the data detection module detects vehicle information on a road in real time through a millimeter wave radar detector;
the data transmission module is used for transmitting the data detected by the data detection module to the data receiving module according to a fixed transmission time interval;
the data receiving module is responsible for receiving the detection information transmitted by the data transmission module and storing the detected data into a database according to a set data format;
the data processing module preprocesses the detection data in the database to obtain accurate detection data, and the preprocessed detection data is also called 'direct information';
the data analysis module judges other required traffic condition information by using the direct information through an algorithm, namely judges 'indirect information';
the data sharing module establishes a standard and a uniform data storage and access mode, and shares the direct information and the indirect information with other business systems.
Preferably, the millimeter wave radar detector is used for single-lane or multi-lane detection and is arranged right above a detection lane, and the height from the ground is 4.5-7 m.
Preferably, the vehicle information includes a vehicle type, a number of passing vehicles, an instantaneous speed of the vehicle, a detection time, and a location of the vehicle; the identification method of the position of the vehicle is that a coordinate system is established by taking a projection point of the millimeter wave radar detector on a lane as an origin, taking the direction along the road as the positive direction of an x axis and taking the direction perpendicular to the road as a y axis, and the (x, y) position in the coordinate system is the position of the vehicle.
Preferably, the data transmission module realizes the regular uploading of the vehicle target traffic detection data by adopting two 4G communication technologies of TD-LTE and FDD-LTE, and the transmission time interval is 0.5s-2 s.
Preferably, the set data format includes nine fields of a data unique representation number, a detection place, a detection time, a vehicle number, a vehicle position, a vehicle time, a vehicle speed, a corrected vehicle speed, and a data abnormality flag.
Preferably, the preprocessing of the detection data by the data processing module includes error data processing, repeated data processing and lost data processing;
the error data processing comprises vehicle position error data correction and vehicle speed error data correction; the method for correcting the vehicle position error data comprises the steps of correcting all vehicle positions exceeding the range of a detection area into vehicle positions on the boundary of the detection area by taking the detection area as the boundary, and updating the corrected data to corresponding fields of a database; the method for correcting the vehicle speed error data comprises the steps of taking alpha times of the maximum speed limit allowed by a detected road as a screening condition, correcting the data of the detected data to be alpha times of the speed limit value when the detected data exceed the value, and updating the corrected data to corresponding fields of a database;
when records with the same detection place, detection time and vehicle number exist in the database, the method for processing the repeated data is that arithmetic mean values of all vehicle positions, vehicle time and vehicle speeds are taken according to the detection place, the detection time and the vehicle number, and the mean values are taken as data of the current detection place, the detection time and the vehicle number;
the method for processing the lost data comprises the steps of sequencing original data according to the same detection place and the same vehicle number, judging whether the detection time is continuous, and indicating that the data is lost if discontinuous data appears in the middle in front and back adjacent N minutes; if the number of the lost records exceeds 3, the vehicle is considered to be lost in the vehicle detection process, and two adjacent data are marked as abnormal; if the number of the lost records is less than 3, the data in the adjacent detection intervals are supplemented by adopting a linear interpolation method.
Preferably, the indirect information includes traffic running state, road accident, and illegal parking on road side.
Preferably, the state judgment condition of the traffic running state is:
Preferably, the method for judging the road accident comprises the following steps:
a. dividing a detection area into a plurality of equidistant strip-shaped areas by using a cutting line perpendicular to the traffic flow driving direction along the traffic flow driving direction, wherein the strip-shaped areas are divided into a plurality of block-shaped areas by different lanes, namely, the detection area forms a matrix taking the lanes as a row vector and the cutting line as a column vector under the lane and cutting line division;
b. calculating the interval T according to the accident for any block area (i, j)AThe average speed v of all vehicles passing through the area is countedijIf no vehicle is detected, directly according to the free flow speed;
c. for each block area (i, j) the average vehicle speed vijAll the following conditions were determined:
vij＜v0,vi+1j≥v0,vi-1j≥v0(2) wherein v is0Critical speed, v, representing sporadic traffic congestioni+1jIndicating the average speed of the vehicle, v, at the same time in the right lane with respect to i lanei-1jRepresents the average speed of the vehicle at the same time of the left lane with respect to the j lane; if the condition is satisfied, it indicates that there is a high possibility that an accident occurs in the modified block area, and marks the time as tsij；
d. When the vehicle average speed no longer satisfies the condition (2), the recording end time teij；
e. If teij-tsij>TA, which indicates that a traffic accident has occurred in the area, wherein TA represents a minimum time threshold for which a typical accident lasts; the traffic accident is also divided into a single-vehicle accident and a multi-vehicle accident, when the accident condition of two adjacent block-shaped areas does not exist, the accident belongs to isolated time and is classified as the single-vehicle accident; when two or more adjacent block areas have accidents, the accidents belong to related events and are classified as multi-vehicle accidents.
Preferably, the roadside illegal parking determination method is as follows:
a. when a vehicle enters a detection area where the roadside is detected to be prohibited from parking, the speed of the vehicle is lower than that of the detection areavsWhen, record its current time as ts1 and the vehicle's location, where vsRepresenting a critical speed at which the vehicle is decelerating close to standstill;
b. by TSFor detecting an illegal parking time interval, if the vehicle is in a succession of a number of TSIn the time period, there is a proportion of 50% or more than 50% that the vehicle speed is less than vsAnd judging the illegal parking, and reporting the detected illegal parking information to the data center.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention provides the detection of urban traffic data and the estimation of information by means of military millimeter wave radar technology for the first time, and provides a whole set of functional modules and an implementation method of a traffic perception system, which can provide favorable information guarantee and decision support for the strategy design and evaluation of an intelligent traffic system;
2. according to the invention, data analysis is carried out on detection data acquired by the millimeter wave radar detector, indirect information which can not be directly detected, such as traffic running conditions, accidents and illegal parking, is estimated, and a road segment segmentation method is introduced to realize accurate positioning of the accidents, so that the problem that the traditional method can not be used for accurate detection is solved, and the urban traffic manager and a decision maker can master real-time, accurate and reliable urban traffic conditions;
3. the data processing method and the analysis method are simple and efficient, can detect that the traditional detector obtains the traffic parameters, can estimate the accident condition information required by other traffic management and control, can provide beneficial help for traffic management and control, traffic guidance and travel planning, have strong economic and social benefits, and have important significance in the technical field of intelligent traffic.
Drawings
Fig. 1 is a schematic view of the inventive segment division.
In the figure: 1. a data detection module; 2. a data transmission module; 3. a data receiving module; 4. a data processing module; 5. a data analysis module; 6. a data sharing module; 7. a road boundary; 8. cutting a line i; 9. a cutting line n.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
a city traffic perception system based on millimeter wave radar comprises a data detection module, a data transmission module, a data receiving module, a data processing module, a data analysis module and a data sharing module;
the data detection module detects vehicle information on a road in real time through a millimeter wave radar detector;
the data transmission module is used for transmitting the data detected by the data detection module to the data receiving module according to a fixed transmission time interval;
the data receiving module is responsible for receiving the detection information transmitted by the data transmission module and storing the detected data into a database according to a set data format;
the data processing module preprocesses the detection data in the database to obtain accurate detection data, and the preprocessed detection data is also called 'direct information';
the data analysis module judges other required traffic condition information by using the direct information through an algorithm, namely judges 'indirect information';
the data sharing module establishes a standard and a uniform data storage and access mode, and shares the direct information and the indirect information with other business systems.
Preferably, the millimeter wave radar detector is used for single-lane or multi-lane detection and is arranged right above a detection lane, and the height from the ground is 4.5-7 m.
Preferably, the vehicle information includes a vehicle type, a number of passing vehicles, an instantaneous speed of the vehicle, a detection time, and a location of the vehicle; the identification method of the position of the vehicle is that a coordinate system is established by taking a projection point of the millimeter wave radar detector on a lane as an origin, taking the direction along the road as the positive direction of an x axis and taking the direction perpendicular to the road as a y axis, and the (x, y) position in the coordinate system is the position of the vehicle.
Preferably, the data transmission module realizes the regular uploading of the vehicle target traffic detection data by adopting two 4G communication technologies of TD-LTE and FDD-LTE, and the transmission time interval is 0.5s-2 s.
Preferably, the set data format includes nine fields of a data unique representation number, a detection place, a detection time, a vehicle number, a vehicle position, a vehicle time, a vehicle speed, a corrected vehicle speed, and a data abnormality flag.
Preferably, the preprocessing of the detection data by the data processing module includes error data processing, repeated data processing and lost data processing;
the error data processing comprises vehicle position error data correction and vehicle speed error data correction; the method for correcting the vehicle position error data comprises the steps of correcting all vehicle positions exceeding the range of a detection area into vehicle positions on the boundary of the detection area by taking the detection area as the boundary, and updating the corrected data to corresponding fields of a database; the method for correcting the vehicle speed error data comprises the steps of taking alpha times of the maximum speed limit allowed by a detected road as a screening condition, correcting the data of the detected data to be alpha times of the speed limit value when the detected data exceed the value, and updating the corrected data to corresponding fields of a database;
when records with the same detection place, detection time and vehicle number exist in the database, the method for processing the repeated data is that arithmetic mean values of all vehicle positions, vehicle time and vehicle speeds are taken according to the detection place, the detection time and the vehicle number, and the mean values are taken as data of the current detection place, the detection time and the vehicle number;
the method for processing the lost data comprises the steps of sequencing original data according to the same detection place and the same vehicle number, judging whether the detection time is continuous, and indicating that the data is lost if discontinuous data appears in the middle in front and back adjacent N minutes; if the number of the lost records exceeds 3, the vehicle is considered to be lost in the vehicle detection process, and two adjacent data are marked as abnormal; if the number of the lost records is less than 3, the data in the adjacent detection intervals are supplemented by adopting a linear interpolation method.
Preferably, the indirect information includes traffic running state, road accident, and illegal parking on road side.
Preferably, the state judgment condition of the traffic running state is:
Preferably, the method for judging the road accident comprises the following steps:
a. dividing a detection area into a plurality of equidistant strip-shaped areas by using a cutting line perpendicular to the traffic flow driving direction along the traffic flow driving direction, wherein the strip-shaped areas are divided into a plurality of block-shaped areas by different lanes, namely, the detection area forms a matrix taking the lanes as a row vector and the cutting line as a column vector under the lane and cutting line division;
b. calculating the interval T according to the accident for any block area (i, j)AThe average speed v of all vehicles passing through the area is countedijIf no vehicle is detected, directly according to the free flow speed;
c. for each block area (i, j) the average vehicle speed vijAll the following conditions were determined:
vij＜v0,vi+1j≥v0,vi-1j≥v0(2) wherein v is0Critical speed, v, representing sporadic traffic congestioni+1jIndicating the average speed of the vehicle, v, at the same time in the right lane with respect to i lanei-1jRepresents the average speed of the vehicle at the same time of the left lane with respect to the j lane; if the condition is satisfied, it indicates that there is a high possibility that an accident occurs in the modified block area, and marks the time as tsij；
d. When the vehicle average speed no longer satisfies the condition (2), the recording end time teij；
e. If teij-tsij>TA, which indicates that a traffic accident has occurred in the area, wherein TA represents a minimum time threshold for which a typical accident lasts; the traffic accident is also divided into a single-vehicle accident and a multi-vehicle accident, when the accident condition of two adjacent block-shaped areas does not exist, the accident belongs to isolated time and is classified as the single-vehicle accident; when two or more adjacent block areas have accidents, the accidents belong to related events and are classified as multi-vehicle accidents.
Preferably, the roadside illegal parking determination method is as follows:
a. when a vehicle enters a detection area where the roadside is detected to be prohibited from parking, the speed of the vehicle is less than vsWhen, record its current time as ts1 and the vehicle's location, where vsRepresenting a critical speed at which the vehicle is decelerating close to standstill;
b. by TSFor detecting an illegal parking time interval, if the vehicle is in a succession of a number of TSIn the time period, there is a proportion of 50% or more than 50% that the vehicle speed is less than vsAnd judging the illegal parking, and reporting the detected illegal parking information to the data center.
The invention mainly utilizes the millimeter wave radar technology to realize the detection of the target object parameters of the short-and-medium distance; the data are transmitted to a data center through a wireless communication technology, the data center analyzes the traffic flow, the vehicle position, the detection time and the vehicle speed acquired by the detector, estimates the real-time traffic conditions such as traffic accidents, roadside parking, traffic jam and the like on roads on the road surface, and shares the traffic conditions to other signal control, service management, police dispatch, traffic guidance, traffic planning, design and the like.
The system mainly comprises a data detection module 1, a data transmission module 2, a data receiving module 3, a data processing module 4, a data analysis module 5 and a data sharing module 6. The millimeter wave radar detector detects the vehicle information on the road in real time, wherein the vehicle information comprises the type of the vehicle (large-sized vehicle and small-sized vehicle), the number of passing vehicles, the instantaneous speed of the vehicle, the detection time and the position of the vehicle; after the millimeter wave radar detector detects the data, the data communication module is responsible for transmitting the detected data to the data center through a wireless communication technology according to a fixed transmission time interval. The background data center is provided with a data receiving module 3 specially used for receiving data, and is responsible for receiving the detection information transmitted by wireless, analyzing the data one by one according to a predetermined communication protocol and storing the data in a database. The information directly detected by the millimeter wave radar detector is not subjected to data processing, but the detected information may have certain errors due to factors such as actual road scenes, vehicle sheltering, environment, climate and the like, so that the data processing module 4 is required to preprocess the detected data to obtain basically accurate detected data. The traffic data (i.e. direct data) directly obtained by the millimeter wave radar detector is very limited, and the data analysis module 5 mainly estimates other required traffic condition information (i.e. indirect information) by using a certain algorithm by means of the directly obtained data. The data sharing module 6 mainly makes a standard and uniform data storage and access mode, and is used for other business systems to access direct data and indirect information concisely and efficiently.
The millimeter wave radar detector is used for single-lane or multi-lane detection and is arranged right above a detection lane, and the height from the ground is 4.5-7 m. Namely, if the detection is single lane detection, the detection is directly installed above the lane, and if the detection is multi-lane detection, the detection is installed directly above the central line of the area formed by all lanes. The millimeter wave radar detector is not influenced by factors such as light, visibility and bad weather, can realize all-weather detection for 7 × 24 hours, can track 32 targets simultaneously, has the maximum detection distance of 110 meters, and directly detects data including the position, the speed and the detection time of each target. The method for identifying the position of the vehicle comprises the following steps: and establishing a coordinate system by taking the projection point of the millimeter wave radar detector on the lane as an origin, the direction along the road as the positive direction of the x axis and the direction perpendicular to the road as the y axis, wherein the (x, y) position in the coordinate system is the position of the vehicle. The data transmission module 2 can adopt two 4G communication systems of TD-LTE and FDD-LTE to realize the regular uploading of the traffic detection data of 32 targets, and the transmission interval can be generally set to be 0.5s-2s according to the requirement of rear-end data combing. The data receiving module 3 receives the detection data sent by the transmission module in a fixed time interval and stores the detected data into a database according to a defined format. The well-defined data format in the data receiving module 3 includes nine fields of a data unique representation number, a detection place, a detection time, a vehicle number, a vehicle position, a vehicle time, a vehicle speed, a corrected vehicle speed, and a data abnormality flag.
The preprocessing of the detection data by the data processing module 4 includes error data processing, repeated data processing and lost data processing. The error data processing is based on the parameter maximum boundary and mainly comprises the correction of vehicle position error data and the correction of vehicle speed error data; the method for correcting the vehicle position error data comprises the steps of correcting all vehicle positions exceeding the range of a detection area into vehicle positions on the boundary of the detection area by taking the detection area as the boundary, and updating the corrected data to corresponding fields of a database; the method for correcting the vehicle speed error data is characterized in that alpha times of the maximum speed limit allowed by a detected road is taken as a screening condition, the minimum speed of the vehicle is 0km/h, the maximum speed is theoretically the road speed limit value, but the maximum speed allowed by a driver on the road is set to be alpha times of the speed limit value in consideration of the fact that the actual driving speed of the driver is slightly higher than the limit value, so that the data of the detected data exceeds the value, the data of the detected data is corrected to be alpha times of the speed limit value, and the corrected data is updated to a corresponding field of a database. The method for processing the lost data comprises the steps of sequencing original data according to the same detection place and the same vehicle number, judging whether the detection time is continuous, and indicating that the data is lost if discontinuous data appears in the middle in front and back adjacent N minutes; if the number of the lost records exceeds 3, the vehicle is considered to be lost in the vehicle detection process, and two adjacent data are marked as abnormal; if the number of the lost records is less than 3, the data in the adjacent detection intervals are supplemented by adopting a linear interpolation method.
The data analysis in the data analysis module 5 mainly performs data analysis according to the direct data, further estimates indirect information, namely the current traffic state or abnormal condition, and can provide decision support for traffic management and control. According to the method, the estimated indirect information is divided into three categories of traffic running states (unblocked, basically unblocked, slightly congested, moderately congested and severely congested), unexpected events in roads and illegal parking on the road sides according to the requirements of actual urban traffic management and control. The method for estimating the traffic running state in a statistical time period is represented as follows:
the step of estimating the road accident in the data analysis module 5 within a statistical event section comprises:
a. as shown in fig. 1 of the accompanying drawings, a detection area is divided into a plurality of equidistant strip-shaped areas along a traffic flow driving direction by cutting lines 1, ·.. cutting lines i,. and.. and cutting lines n, wherein the cutting lines are perpendicular to the traffic flow driving direction, and the strip-shaped areas are further divided into a plurality of block-shaped areas by different lanes (namely lanes 1,... the lanes j,. the.. and lanes m), that is, the detection area forms a matrix with lanes as a row vector and the cutting lines as a column vector under lane and cutting line division;
b. calculating the interval T according to the accident for any block area (i, j)AThe average speed v of all vehicles passing through the area is countedijIf no vehicle is detected, directly according to the free flow speed;
c. for each block area (i, j) the average vehicle speed vijAll the following conditions were determined:
vij＜v0,vi+1j≥v0,vi-1j≥v0(2) wherein v is0Critical speed, v, representing sporadic traffic congestioni+1jIndicating the same time of the vehicle in the right lane with respect to the i laneAverage velocity, vi-1jRepresents the average speed of the vehicle at the same time of the left lane with respect to the j lane; if the condition is satisfied, it indicates that there is a high possibility that an accident occurs in the modified block area, and marks the time as tsij；
d. When the vehicle average speed no longer satisfies the condition (2), the recording end time teij；
e. If teij-tsij>TA, which indicates that a traffic accident has occurred in the area, wherein TA represents a minimum time threshold for which a typical accident lasts; the traffic accidents are also divided into single-vehicle accidents and multi-vehicle accidents, and when the accidents of two adjacent block areas do not occur, the accidents belong to isolated time and are classified into the single-vehicle accidents, such as single-vehicle breakdown; when two or more adjacent block areas have accidents, the accidents belong to related events, and are classified into multiple vehicle accidents, such as rear-end collision and side scraping.
The method for judging illegal parking on the road side in the data analysis module 5 comprises the following steps:
a. when a vehicle enters a detection area where the roadside is detected to be prohibited from parking, the speed of the vehicle is less than vsWhen, record its current time as ts1 and the vehicle's location, where vsIndicating that the vehicle is decelerating and approaching a critical speed at rest;
b. by TSFor detecting an illegal parking time interval, if the vehicle is in a succession of a number of TSIn the time period, there is a proportion of 50% or more than 50% that the vehicle speed is less than vsAnd judging the illegal parking, and reporting the detected illegal parking information to the data center.
The data sharing in the data sharing module 6 is direct data and indirect information which are convenient for other intelligent transportation systems to call a sensing system, and is used for designing and evaluating strategies. The data fields for the external system to uniformly call comprise: the detection location, the detection time, the number of passing vehicles, the average speed of the vehicles, the variance of the speed of the vehicles, the minimum speed, the maximum speed, the traffic running condition, the accident condition and the illegal parking condition.
The invention adopts traffic perception to replace traffic data detection, comprises two functions of data detection and data mining, not only obtains the detection of traditional traffic parameters, but also obtains other necessary traffic information such as traffic accidents, congestion degree, illegal parking and the like by utilizing the detection data to carry out data analysis and mining, and the information is difficult to directly detect; the method processes the detected traffic data based on the millimeter wave radar detection technology to obtain the information such as traffic jam, traffic accident and roadside parking which cannot be obtained by the conventional detection equipment, and provides powerful support for the services such as urban traffic signal control, traffic guidance, road traffic police configuration, illegal parking treatment, real-time response and treatment of traffic accidents and the like; the data processing method and the data analysis method are simple and efficient, the comprehensiveness and the accuracy of data information obtained by an original data detection system can be improved, and non-detection information can be obtained through data analysis to provide decision information support for traffic management and control; the invention has strong economic benefit and social benefit and has important significance in the technical field of intelligent traffic.
In summary, the present invention is only a preferred embodiment, and not intended to limit the scope of the invention, and all equivalent changes and modifications in the shape, structure, characteristics and spirit of the present invention described in the claims should be included in the scope of the present invention.
Claims (4)
1. The utility model provides a city traffic perception system based on millimeter wave radar which characterized in that: the device comprises a data detection module, a data transmission module, a data receiving module, a data processing module, a data analysis module and a data sharing module;
the data detection module detects vehicle information on a road in real time through a millimeter wave radar detector;
the data transmission module transmits the data detected by the data detection module to the data receiving module according to a fixed transmission time interval, the data transmission module realizes the regular uploading of the vehicle target traffic detection data by adopting two 4G communication technologies of TD-LTE and FDD-LTE, and the transmission time interval is 0.5s-2 s;
the data receiving module is responsible for receiving the detection information transmitted by the data transmission module and storing the detected data into a database according to a set data format, wherein the set data format comprises nine fields of a data unique representation number, a detection place, detection time, a vehicle number, a vehicle position, vehicle time, vehicle speed, corrected vehicle speed and a data abnormal mark;
the data processing module preprocesses the detection data in the database to obtain accurate detection data, and the preprocessed detection data is also called 'direct information';
the data analysis module judges other required traffic condition information by using the direct information through an algorithm, namely judges indirect information, wherein the indirect information comprises a traffic running state, an accident in a road and illegal parking on the road side;
the state judgment condition of the traffic running state is as follows:
the method for judging the road accident comprises the following steps:
a. dividing a detection area into a plurality of equidistant strip-shaped areas by using a cutting line perpendicular to the traffic flow driving direction along the traffic flow driving direction, wherein the strip-shaped areas are divided into a plurality of block-shaped areas by different lanes, namely, the detection area forms a matrix taking the lanes as a row vector and the cutting line as a column vector under the lane and cutting line division;
b. calculating the interval T according to the accident for any block area (i, j)AThe average speed v of all vehicles passing through the area is countedijIf no vehicle is detected, directly according to the free flow speed;
c. for each block area (i, j) the average vehicle speed vijAll the following conditions were determined:
vij＜v0,vi+1j≥v0,vi-1j≥v0(2) wherein v is0Critical speed, v, representing sporadic traffic congestioni+1jIndicating the average speed of the vehicle, v, at the same time in the right lane with respect to i lanei-1jRepresents the average speed of the vehicle at the same time of the left lane with respect to the j lane; if the condition is satisfied, it indicates that there is a high possibility that an accident occurs in the modified block area, and marks the time as tsij；
d. When the vehicle average speed no longer satisfies the condition (2), the recording end time teij；
e. If teij-tsij>TA, which indicates that a traffic accident has occurred in the area, wherein TA represents a minimum time threshold for which a typical accident lasts; the traffic accident is also divided into a single-vehicle accident and a multi-vehicle accident, when the accident condition of two adjacent block-shaped areas does not exist, the accident belongs to isolated time and is classified as the single-vehicle accident; when two or more adjacent block areas have accidents, the accidents belong to related events and are classified as multi-vehicle accidents;
the roadside illegal parking judgment method comprises the following steps:
a. when a vehicle enters a detection area where the roadside is detected to be prohibited from parking, the speed of the vehicle is less than vsWhen, record its current time as ts1 and the vehicle's location, where vsRepresenting a critical speed at which the vehicle is decelerating close to standstill;
b. by TSFor detecting an illegal parking time interval, if the vehicle is in a succession of a number of TSIn the time period, there is a proportion of 50% or more than 50% that the vehicle speed is less than vsJudging the illegal parking and reporting the detected illegal parking information to a data center;
the data sharing module establishes a standard and a uniform data storage and access mode, and shares the direct information and the indirect information with other business systems.
2. The millimeter wave radar-based urban traffic perception system according to claim 1, wherein: the millimeter wave radar detector is used for single-lane or multi-lane detection and is arranged right above a detection lane, and the height from the ground is 4.5-7 m.
3. The millimeter wave radar-based urban traffic perception system according to claim 1, wherein: the vehicle information comprises the type of the vehicle, the number of passing vehicles, the instantaneous speed of the vehicle, the detection time and the position of the vehicle; the identification method of the position of the vehicle is that a coordinate system is established by taking a projection point of the millimeter wave radar detector on a lane as an origin, taking the direction along the road as the positive direction of an x axis and taking the direction perpendicular to the road as a y axis, and the (x, y) position in the coordinate system is the position of the vehicle.
4. The millimeter wave radar-based urban traffic perception system according to claim 1, wherein: the data processing module carries out preprocessing on the detection data, including error data processing, repeated data processing and lost data processing;
the error data processing comprises vehicle position error data correction and vehicle speed error data correction; the method for correcting the vehicle position error data comprises the steps of correcting all vehicle positions exceeding the range of a detection area into vehicle positions on the boundary of the detection area by taking the detection area as the boundary, and updating the corrected data to corresponding fields of a database; the method for correcting the vehicle speed error data comprises the steps of taking alpha times of the maximum speed limit allowed by a detected road as a screening condition, correcting the data of the detected data to be alpha times of the maximum speed limit when the detected data exceeds the alpha times of the maximum speed limit, and updating the corrected data to corresponding fields of a database;
when records with the same detection place, detection time and vehicle number exist in the database, the method for processing the repeated data is that arithmetic mean values of all vehicle positions, vehicle time and vehicle speeds are taken according to the detection place, the detection time and the vehicle number, and the mean values are taken as data of the current detection place, the detection time and the vehicle number;
the method for processing the lost data comprises the steps of sequencing original data according to the same detection place and the same vehicle number, judging whether the detection time is continuous, and indicating that the data is lost if discontinuous data appears in the middle in front and back adjacent N minutes; if the number of the lost records exceeds 3, the vehicle is considered to be lost in the vehicle detection process, and two adjacent data are marked as abnormal; if the number of the lost records is less than 3, the data in the adjacent detection intervals are supplemented by adopting a linear interpolation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810554906.6A CN108550262B (en) | 2018-06-01 | 2018-06-01 | Urban traffic sensing system based on millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810554906.6A CN108550262B (en) | 2018-06-01 | 2018-06-01 | Urban traffic sensing system based on millimeter wave radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108550262A CN108550262A (en) | 2018-09-18 |
| CN108550262B true CN108550262B (en) | 2021-06-11 |
Family
ID=63511696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810554906.6A Active CN108550262B (en) | 2018-06-01 | 2018-06-01 | Urban traffic sensing system based on millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108550262B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191864A (en) * | 2018-11-12 | 2019-01-11 | 上海慧昌智能交通系统有限公司 | Method and apparatus for lines on highway identification |
| CN112150833B (en) * | 2019-06-28 | 2021-12-07 | 比亚迪股份有限公司 | Method and device for adjusting speed limit of road section, storage medium and electronic equipment |
| CN110782680B (en) * | 2019-11-01 | 2021-03-02 | 北京星云互联科技有限公司 | Slow vehicle detection method and device and computer readable storage medium |
| CN111681418A (en) * | 2020-05-26 | 2020-09-18 | 南京信息职业技术学院 | Road state monitoring system based on multiple millimeter wave radars and working method thereof |
| CN111696366A (en) * | 2020-06-04 | 2020-09-22 | 中国人民解放军战略支援部队信息工程大学 | Road accident perception and identification method and system |
| CN112147611A (en) * | 2020-08-18 | 2020-12-29 | 河北省交通规划设计院 | Long-distance traffic radar based on 77GHz millimeter wave radar |
| CN112068126A (en) * | 2020-08-25 | 2020-12-11 | 电子科技大学 | Active millimeter wave imaging system for human body whole-body security inspection |
| CN112433203B (en) * | 2020-10-29 | 2023-06-20 | 同济大学 | Lane linearity detection method based on millimeter wave radar data |
| CN112562329A (en) * | 2020-11-28 | 2021-03-26 | 山西省交通科技研发有限公司 | Traffic event sensing method based on millimeter wave radar data |
| CN112712697B (en) * | 2020-12-30 | 2022-04-12 | 上海智能交通有限公司 | Lane-level traffic state discrimination method oriented to vehicle-road cooperative application |
| CN113554876B (en) * | 2021-09-18 | 2021-11-30 | 苏州映赛智能科技有限公司 | Multi-millimeter wave radar domain control system |
| CN114267172A (en) * | 2021-11-19 | 2022-04-01 | 山西省交通运输安全应急保障技术中心(有限公司) | Road sectional traffic conflict risk early warning system and method thereof |
| CN114858214B (en) * | 2022-04-27 | 2023-08-25 | 中徽建技术有限公司 | Urban road performance monitoring system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093616A (en) * | 2006-06-23 | 2007-12-26 | 中国科学院上海微系统与信息技术研究所 | Non-linear correction method of voltage controlled oscillator in radar system for detecting flow rate of vehicle |
| CN101719315B (en) * | 2009-12-23 | 2011-06-01 | 山东大学 | Method for acquiring dynamic traffic information based on middleware |
| CN104715610B (en) * | 2015-04-09 | 2017-03-15 | 银江股份有限公司 | A kind of traffic index computational methods towards urban transportation |
| CN106530684B (en) * | 2015-09-11 | 2019-08-20 | 杭州海康威视系统技术有限公司 | Handle the method and device of traffic route information |
| CN105261215B (en) * | 2015-10-09 | 2017-10-10 | 南京慧尔视智能科技有限公司 | Intelligent transportation behavior cognitive method and system based on microwave |
| CN107895482A (en) * | 2017-11-24 | 2018-04-10 | 北京安航达科技有限公司 | Transport investigation device and method based on millimetre-wave radar and laser radar |
-
2018
- 2018-06-01 CN CN201810554906.6A patent/CN108550262B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108550262A (en) | 2018-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108550262B (en) | Urban traffic sensing system based on millimeter wave radar | |
| US11074813B2 (en) | Driver behavior monitoring | |
| CN109859500B (en) | High-speed confluence area safety early warning method based on vehicle-road cooperation | |
| EP3403219A1 (en) | Driver behavior monitoring | |
| CN109275121B (en) | Vehicle trajectory tracking method based on adaptive extended Kalman filtering | |
| CN104851295A (en) | Method and system for acquiring road condition information | |
| CN100589143C (en) | Method and appaatus for judging the traveling state of a floating vehicle | |
| CN110276973B (en) | Automatic intersection traffic rule identification method | |
| CN112712697B (en) | Lane-level traffic state discrimination method oriented to vehicle-road cooperative application | |
| CN108039046B (en) | Urban intersection pedestrian detection and identification system based on C-V2X | |
| CN110796862B (en) | Highway traffic condition detection system and method based on artificial intelligence | |
| CN112085950B (en) | Method and system for estimating traffic state discrimination index, storage medium and application | |
| CN109493606B (en) | Method and system for identifying illegal parking vehicles on expressway | |
| WO2022213542A1 (en) | Method and system for clearing information-controlled intersection on basis of lidar and trajectory prediction | |
| CN106448223B (en) | Expressway driving speed early warning device and method capable of automatically adapting to haze | |
| CN113470350B (en) | Traffic scheduling method for sidewalk | |
| Tak et al. | Development of AI-based vehicle detection and tracking system for C-ITS application | |
| CN114999181B (en) | Highway vehicle speed abnormality identification method based on ETC system data | |
| CN107564336B (en) | Signalized intersection left turn conflict early warning system and early warning method | |
| CN116434523A (en) | Vehicle active safety control method and device based on constraint degree in information perception scene | |
| Kaur et al. | RFID based Intelligent Transport System with RSU Communication for Emergency Vehicles in Urbanization | |
| CN114241764B (en) | Bus accurate data fusion center system and method based on bus-road cooperation technology | |
| CN114299719B (en) | Track-based lane temporary pointing identification method and system in end cloud system | |
| CN113053100B (en) | Method and device for estimating bus arrival time | |
| CN115909791A (en) | Traffic-based intelligent recognition detector and detection method for highway traffic information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 225000 5-storey Building B, Zhigu Science and Technology Building, 186 Yangtze River Middle Road, Yangzhou Economic and Technological Development Zone, Jiangsu Province Applicant after: China automotive electronics Yangzhou Co., Ltd. Address before: 225000 Zhigu Building B504, 186 Yangtze River Middle Road, Hangjiang District, Yangzhou City, Jiangsu Province Applicant before: China automotive electronics Yangzhou Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211009 Address after: 610000 No. 879 Ganghua Road, north area of modern industrial port, Pidu District, Chengdu, Sichuan Patentee after: Sichuan kunhong Yuanxiang Technology Co.,Ltd. Address before: 225000 5-storey Building B, Zhigu Science and Technology Building, 186 Yangtze River Middle Road, Yangzhou Economic and Technological Development Zone, Jiangsu Province Patentee before: YANGZHOU CAEP-AE Co.,Ltd. |