CN106448179A - Intelligent expressway traffic analyzing system - Google Patents
Intelligent expressway traffic analyzing system Download PDFInfo
- Publication number
- CN106448179A CN106448179A CN201610817566.2A CN201610817566A CN106448179A CN 106448179 A CN106448179 A CN 106448179A CN 201610817566 A CN201610817566 A CN 201610817566A CN 106448179 A CN106448179 A CN 106448179A
- Authority
- CN
- China
- Prior art keywords
- real
- video stream
- data
- coil
- time
- 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.)
- Pending
Links
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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- 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
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Abstract
The invention discloses an intelligent expressway traffic video analyzing system. Expressway lane line detection, video sight line and lane line included angle measurement, real-time and average speed measurement and analysis, large and small vehicle recognition and analysis, traffic flow statistics and real-time road network comprehensive running index statistics are the main achieved functions. In the vehicle speed measuring and large and small vehicle recognition and analysis achieving process, a method based on a virtual coil is adopted, and the manner that coil parameter drawing adjustment in which a user participates and automatic system coil drawing are combined is achieved. During the specific large and small vehicle traffic flow statistics, judgment on the size of vehicles and statistics on traffic flow are achieved by calculating pixel points in the virtual coil. According to the intelligent expressway traffic video analyzing system, manual and automatic double calibration on early-stage parameter is achieved, and the later road network comprehensive running indexes are back displayed through a telescopic broken line graph in which the user participates; meanwhile, multiple abundant analyzing and monitoring functions are achieved, and very high practicability and analysis accuracy are achieved while the user experience is improved.
Description
Technical field
The present invention relates to a kind of freeway traffic intelligent analysis system, belong to the transport information intellectual analysis based on video
Technical field.
Background technology
At present in the freeway traffic intellectual analysis software aspects based on conventional video, it is nearly all machine-made shape
Formula and analysis method, Consumer's Experience sense shortage, precision and accuracy are inadequate, analysis causes user couple with statistical result data is mechanical
Cognitive not grade of the depth of result data is all current urgently improved place.
Content of the invention
Goal of the invention:For problems of the prior art, a kind of present invention feature richness of offer is perfect, Consumer's Experience
Sense is strong, precision is high, the freeway traffic intelligent analysis system of analytic statisticss result datas tool visualization characteristic.
Technical scheme:A kind of freeway traffic intelligent analysis system, including:
Read in video stream data module, after its first frame data is read into, user will be carried out described video stream data
Self-defining virtual coil parameter is drawn and is set, the coil parameter that virtual coil parameter after setting completed will be carried out with backstage
Automatically calculate mutually calibration (including lane detection and video sight line during it to measure with lane line angle), comprehensively must test the speed
Virtual coil parameter used, implements module subsequently into each analytic function.
It is test the speed analysis module and the identification of big dolly and vehicle flowrate module first, will in real time while background process
Data (include the section real-time speed of point up-downgoing, the real-time traffic flow amount of point up-downgoing, point up-downgoing big dolly vehicle flowrate real
When identification and statistics etc.) Dynamic Announce, on the GUI of front end, realizes and the real-time analysis of video stream synchronization or monitoring, finally whole
Individual video flow processing carries out COMPREHENSIVE CALCULATING and show that real-time road network of each time period is comprehensive to all analyses and statistics the data obtained after finishing
Close and run index, and echoed on GUI with broken line graph.
Video stream data in described video stream data module includes the video stream data of remote server real-time Transmission
With locally stored video stream data.
Described self-defining virtual coil parameter is drawn and is set the virtual sensing of testing the speed including each track is drawn respectively
Coil and upper and lower track carry out the drafting of virtual induction coil and the setting of big dolly identification respectively.
Described test the speed analysis module and big dolly identification with vehicle flowrate module in, all employ based on the virtual line of induction
The method of circle, and achieve the mode that the coil parameter drafting adjustment coil drafting automatic with system of user's participation combines,
And then target vehicle velocity can be accurately measured with a number, wherein big dolly identification division, we take a kind of innovation
Being differentiated, the cart that more than 6 meters of normal length 99% is all large and medium-sized lorry and visitor generally on road to area differentiating approach
Car, and less than 6 meters of dolly is all medium and small car, offroad vehicle, minicar etc..In conjunction with 6 meters of this length of practical situation with
On vehicle generally all more than 4 meters of overall height, wide 3 meters about, elemental area in the gray-scale maps of background extracting for such vehicle
Size is by the projected area of 2.4 meters * 6 meters * 2 meters that are far longer than a standard of vehicle, and the vehicle perspective plane of this standard
Amass and will be much higher than dolly in road again.So 2.5 meters * 6 meters * 2 meters of a standard of vehicle is modeled analyzing by we,
It is designed in conjunction with our the actual parameters that can be obtained with, obtained following algorithm and distinguished threshold value come the area to arrange big dolly:
S=Width2·cos(theta)
Wherein:S:The area of big dolly distinguishes threshold values, Width:Pixel in video corresponding to each track live width
Value, theta:Lane line and the angle of video.In view of the time complexity reducing algorithm further, this part of function mould
Block can only could be triggered by the virtual induction coil of Article 2 by vehicle above every time, triggers the work(of big dolly identification each time
After energy module, vehicle flowrate is carried out to it simultaneously.
The described result data in front end GUI echo includes the dynamic echo of real time data and calculates institute based on synthetic data
The broken line chart echo of the real-time road network integrated operation index of each time period obtaining, described broken line chart has details and drags amplification point
Analysis function, can make the analysis personnel analytical data with meticulously understanding gained more directly perceived.
Using technique scheme, the invention has the beneficial effects as follows:There is the manual of front period parameters and dual calibration automatically,
The telescopic broken line chart echo that later stage road network integrated operation index is participated in user, also has abundant analysis monitoring work(simultaneously
Can be (as traditional video frequency vehicle real-time speed mensure, vehicle flowrate, the analysis of big dolly and statistics and other such as vehicle surpass
The sound prompt function of speed, over-speed vehicles carry out license plate number identification output etc.), while improving Consumer's Experience, there is very high reality
With property and accuracy.
Brief description
Fig. 1 is the general frame figure of the embodiment of the present invention;
Fig. 2 is the flow chart automatically drawing virtual induction coil in the embodiment of the present invention.
Specific embodiment
With reference to specific embodiment, it is further elucidated with the present invention it should be understood that these embodiments are merely to illustrate the present invention
Rather than restriction the scope of the present invention, after having read the present invention, the various equivalences to the present invention for the those skilled in the art
The modification of form all falls within the application claims limited range.
As shown in figure 1, freeway traffic intelligent analysis system, including:
Read in video stream data module, after its first frame data is read into, user will carry out self-defined video stream data
Virtual coil parameter draw and set, calculating automatic with the coil parameter that backstage is carried out mutually calibrated by parameter after setting completed
(including lane detection and video sight line during it to measure with lane line angle), comprehensively must test the speed virtual coil ginseng used
Number, implements module subsequently into each analytic function.
It is test the speed analysis module and the identification of big dolly and vehicle flowrate module first, will in real time while background process
Data (include the section real-time speed of point up-downgoing, the real-time traffic flow amount of point up-downgoing, point up-downgoing big dolly vehicle flowrate real
When identification and statistics etc.) Dynamic Announce, on the GUI of front end, realizes and the real-time analysis of video stream synchronization or monitoring, finally whole
Individual video flow processing carries out COMPREHENSIVE CALCULATING and show that real-time road network of each time period is comprehensive to all analyses and statistics the data obtained after finishing
Close and run index, and echo on GUI with the broken line graph of time segment, specifically the folding of real-time road network integrated operation index
Line diagram output will be described below to be talked about.
Video stream data in video stream data module includes video stream data and the basis of remote server real-time Transmission
The video stream data of ground storage, with adapt to the local analyzing and processing of existing history video data and real time video data point
Analysis is processed, and improves the demand suitability.
Self-defining virtual coil parameter is drawn and is set the virtual induction coil that tests the speed including each track is drawn respectively
Drafting with the virtual induction coil that upper and lower track carries out big dolly identification respectively and setting.
Described test the speed analysis module and big dolly identification with vehicle flowrate module in, all employ based on the virtual line of induction
The method of circle, and achieve the mode that the coil parameter drafting adjustment coil drafting automatic with system of user's participation combines,
And then target vehicle velocity can be accurately measured with a number, wherein big dolly identification division, we take a kind of innovation
Being differentiated, usual more than 6 meters of cart 99% is all large and medium-sized lorry and passenger vehicle generally on road to area differentiating approach,
And less than 6 meters of dolly is all medium and small car, offroad vehicle, minicar etc..In conjunction with this more than 6 meters of car of practical situation
Generally all more than 4 meters of overall height, wide 3 meters about, elemental area size in the gray-scale maps of background extracting for such vehicle will
It is far longer than the projected area of 2.4 meters * 6 meters * 2 meters of vehicle of a standard, and the vehicle area of this standard will
It is much higher than dolly in road.So 2.5 meters * 6 meters * 2 meters of a standard of vehicle is modeled analyzing by we, in conjunction with me
The actual parameter that can be obtained be designed, obtained following algorithm come to arrange big dolly area distinguish threshold value:
S=Width2·cos(theta)
Wherein:S:The area of big dolly distinguishes threshold values, Width:Pixel in video corresponding to each track live width
Value, theta:Lane line and the angle of video.In view of the time complexity reducing algorithm further, this part of function mould
Block can only could be triggered by the virtual induction coil of Article 2 by vehicle above every time, triggers the work(of big dolly identification each time
After energy module, vehicle flowrate is carried out to it simultaneously.
Again taking the Computational Method of Velocity Measurement based on virtual induction coil in the system as a example, the above side based on virtual induction coil
Method substantially can be described as:It is configured the position of virtual induction coil by the gray-scale maps after vehicle characteristics are extracted, calculate car
By time of 2 virtual induction zone coils, with the distance between virtual induction zone remove it is possible to obtain the accurate of vehicle
Real-time speed.
The described result data in front end GUI echo includes the dynamic echo of real time data and calculates institute based on synthetic data
The broken line chart echo of the real-time road network integrated operation index of each time period obtaining, described broken line chart has details and drags amplification point
Analysis function, can make the analysis personnel analytical data with meticulously understanding gained more directly perceived.And specifically road network is comprehensively transported in real time
The calculating of row index be then with《Network of highways operational monitoring and the provisional technical requirements of service》2012 editions as reference, inspection information institute
Design, as follows in conjunction with the computing formula of each reference variable and the road network aggregative index N value of weight distribution:
N=0.6* road network congestion index+0.4* road network environment index
The assignment table that the assignment reference of wherein road network congestion index is defined as below:
And road network environment index then has two kinds of situations according to our early stages to video lane detection result:Perfection detects
N/R lane line and its be then entered as 0 with video sight line angle, if detection detection lane line has exception with angle
Or inspection does not measure, then with 0 assignment, represent that now environmental condition is poor.
As shown in Fig. 2 for the embodiment of the present invention with regard to highway lane detection and video sight line and track wire clamp
Angle measures the process chart of part, and we read a two field picture and are processed first, every two field picture is filtered operate, such as
Here we use Canny operator and are filtered, and then carry out Threshold binary conversion treatment to filtering image again, next
We arrange the minima of HoughVote, so that we carry out virtual induction coil drafting the later stage, and then carry out Hough transform
To obtain independent track blank image, that is, the track lines having processed.
And for treated complete lines, we can obtain the blank image of track lines, to blank image picture
Traveled through, filtered out the white pixel coordinate points of all of white track lines, we take 2 points pixel coordinate (x1, y1)
With (x2, y2), using following mathematical formulae, position and the angle of lane line just can be drawn, to rule:
Wherein r is the angle (unit is " ° ") for lane line.
Claims (5)
1. a kind of freeway traffic intelligent analysis system is it is characterised in that include:Read in video stream data module, described
After its first frame data is read into, user will carry out self-defining virtual coil parameter and draw and set video stream data, if
Put to finish the coil parameter that follow-up reforwarding advanced and carried out with backstage and automatically calculate mutually calibration and (during it, include lane detection
And video sight line is measured with lane line angle), comprehensively must test the speed virtual coil parameter used, subsequently into each analytic function
Implement module, be test the speed analysis module and the identification of big dolly and vehicle flowrate module first, while background process
By real time data Dynamic Announce on the GUI of front end, realize the real-time analysis with video stream synchronization or monitoring, finally in whole video
Stream process carry out COMPREHENSIVE CALCULATING and draw real-time road network integrated operation of each time period to all analyses and statistics the data obtained after finishing
Index, and echoed on GUI with broken line graph.
2. freeway traffic intelligent analysis system as claimed in claim 1 is it is characterised in that described video stream data module
In video stream data include the video stream data of remote server real-time Transmission and locally stored video stream data.
3. freeway traffic intelligent analysis system as claimed in claim 1 is it is characterised in that described self-defining dummy line
Circle parameter draw with set include each track is drawn respectively test the speed virtual induction coil and upper and lower track carries out size respectively
The drafting of virtual induction coil of car identification and setting.
4. freeway traffic intelligent analysis system as claimed in claim 1 it is characterised in that described test the speed analysis module and
In big dolly identification and vehicle flowrate module, all employ the method based on virtual induction coil, and achieve user and participate in
Coil parameter draw the mode that adjustment coil automatic with system drafting combines, and then can be to target vehicle velocity and a number
Accurately measured.
5. freeway traffic intelligent analysis system as claimed in claim 1 is it is characterised in that described echo in front end GUI
Result data include real time data dynamic echo and based on synthetic data calculate gained real-time road network of each time period comprehensive
Run the broken line chart echo of index, described broken line chart has details and drags amplification analytic function, can make analysis personnel more
Analytical data with meticulously understanding gained directly perceived.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610817566.2A CN106448179A (en) | 2016-09-12 | 2016-09-12 | Intelligent expressway traffic analyzing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610817566.2A CN106448179A (en) | 2016-09-12 | 2016-09-12 | Intelligent expressway traffic analyzing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106448179A true CN106448179A (en) | 2017-02-22 |
Family
ID=58168578
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610817566.2A Pending CN106448179A (en) | 2016-09-12 | 2016-09-12 | Intelligent expressway traffic analyzing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106448179A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107895492A (en) * | 2017-10-24 | 2018-04-10 | 河海大学 | A kind of express highway intelligent analysis method based on conventional video |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510356A (en) * | 2009-02-24 | 2009-08-19 | 上海高德威智能交通系统有限公司 | Video detection system and data processing device thereof, video detection method |
CN202563521U (en) * | 2011-11-29 | 2012-11-28 | 冷明 | Vehicle characteristic identification device based on public security video image in skynet engineering |
CN103177246A (en) * | 2013-03-26 | 2013-06-26 | 北京理工大学 | Dual-model lane line identification method based on dynamic area division |
CN103295397A (en) * | 2013-05-13 | 2013-09-11 | 同济大学 | Method and system for self-service road condition information display for users |
JP2015060443A (en) * | 2013-09-19 | 2015-03-30 | 株式会社 日立産業制御ソリューションズ | Traffic volume grasping device and method |
-
2016
- 2016-09-12 CN CN201610817566.2A patent/CN106448179A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510356A (en) * | 2009-02-24 | 2009-08-19 | 上海高德威智能交通系统有限公司 | Video detection system and data processing device thereof, video detection method |
CN202563521U (en) * | 2011-11-29 | 2012-11-28 | 冷明 | Vehicle characteristic identification device based on public security video image in skynet engineering |
CN103177246A (en) * | 2013-03-26 | 2013-06-26 | 北京理工大学 | Dual-model lane line identification method based on dynamic area division |
CN103295397A (en) * | 2013-05-13 | 2013-09-11 | 同济大学 | Method and system for self-service road condition information display for users |
JP2015060443A (en) * | 2013-09-19 | 2015-03-30 | 株式会社 日立産業制御ソリューションズ | Traffic volume grasping device and method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107895492A (en) * | 2017-10-24 | 2018-04-10 | 河海大学 | A kind of express highway intelligent analysis method based on conventional video |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
CN102810250B (en) | Video based multi-vehicle traffic information detection method | |
CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
US8433099B2 (en) | Vehicle discrimination apparatus, method, and computer readable medium storing program thereof | |
CN105184872B (en) | Automobile insurance electronic price computing device based on machine vision | |
CN104021676A (en) | Vehicle positioning and speed measuring method based on dynamic video feature of vehicle | |
CN107256636A (en) | A kind of traffic flow acquisition methods for merging laser scanning and video technique | |
CN101660932A (en) | Automatic calibration method of pointer type automobile meter | |
CN101615342B (en) | Vehicle detection method | |
CN111402613B (en) | Method for selecting lane of toll station for automatically driving vehicle | |
DE102013211930A1 (en) | Binocular broad base line object comparison method using a minimal cost flownet | |
CN109285163B (en) | Laser point cloud based lane line left and right contour line interactive extraction method | |
CN103886597A (en) | Circle detection method based on edge detection and fitted curve clustering | |
CN103557792A (en) | Method for visual tracking and position measurement of drogue object | |
CN110232682B (en) | Image-based track foreign matter detection method | |
CN102252859A (en) | Road train straight-line running transverse stability automatic identification system | |
CN103413325A (en) | Vehicle speed identification method based on vehicle body feature point positioning | |
CN103514599B (en) | A kind of segmentation of the image optimum based on neighborhood total variation scale selection method | |
CN110733416B (en) | Lane departure early warning method based on inverse perspective transformation | |
CN115423824A (en) | Train carriage positioning and segmenting method based on point cloud voxel rectangular grid | |
CN106448179A (en) | Intelligent expressway traffic analyzing system | |
JP6929207B2 (en) | Road image processing device, road image processing method, road image processing program, and recording medium | |
CN109544607A (en) | A kind of cloud data registration method based on road mark line | |
CN109781023B (en) | Trailer contour dimension measuring method, device and system | |
CN114049306A (en) | Traffic anomaly detection system design based on image camera and high-performance display card |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |