CN100435160C - Video image processing method and system for real-time sampling of traffic information - Google Patents
Video image processing method and system for real-time sampling of traffic information Download PDFInfo
- Publication number
- CN100435160C CN100435160C CNB2005100285721A CN200510028572A CN100435160C CN 100435160 C CN100435160 C CN 100435160C CN B2005100285721 A CNB2005100285721 A CN B2005100285721A CN 200510028572 A CN200510028572 A CN 200510028572A CN 100435160 C CN100435160 C CN 100435160C
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- traffic information
- real
- label
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The provided new detection technology with visual image for vehicle matching and traffic information acquisition comprises: pre-preparing image with background difference method, dynamic projecting to detect vehicle and extract vehicle feature information for vehicle matching by last and current frames of image and the corresponding traffic information. This invention can reduce computation quantity and improves reliability of result.
Description
Technical field
The invention belongs to the intelligent transport technology field, relate to the traffic information collection technology.
Background technology
The technology of gathering transport information has multiple, compare with other detection techniques, video detection technology has clear superiority at aspects such as coverage, detected parameters, maintainability and installation simplifications, and it is perspective good, the development trend of energy that represent traffic information detector.
Utilize the principle of video image acquisition transport information roughly can divide two classes at present: virtual coil method and tracing.Most of product belongs to this class of virtual coil method on the market, and its ultimate principle is exactly to judge according to the situation whether road Fixed Sections position pixel gray scale on the image changes to have or not the vehicle process, thus the statistics magnitude of traffic flow, computing velocity.The advantage of such detecting device is that principle is simple, and data processing time is short, is satisfying the detection of finishing flow, speed under the prerequisite that requires in real time.But because such detecting device only obtains sampling time and has or not vehicle to pass through this unique information of sample line position, and lost features such as comprising vehicle length, width and movement locus, so the vehicle matching precision of front and back two field picture is lower, overtake other vehicles and the situation of lane change under, the vehicle matching error causes speed to detect failure.
Following the tracks of ratio juris is the pixel that meets vehicle characteristics in the traffic scene image by identifying, calculating vehicle quantity, and frame vehicle before and after mating according to the feature that extracts, thereby computing velocity.In theory, tracing is more more rigorous than virtual coil method, so more can represent the trend of development.The difficulty of this method is: the tracking of Feature Extraction and feature.At first feature must be representative, and the vehicle in the image all possesses this feature and has nothing in common with each other; Secondly same vehicle feature in the different frame image should have correlativity, and good corresponding relationship can be arranged.The tracing shortcoming that present document is reported is that the vehicle detection calculated amount is excessive, and the result is inaccurate.
Obtain the complicacy that video image obtains transport information owing to utilize, during the video acquisition technology still is in and constantly improves.
Summary of the invention
At big, the insecure problem of result of existing tracing vehicle detection technique computes amount, the invention provides a kind of new vehicle detection technology, and based on this detection technique, the vehicle coupling before and after carrying out in the two field picture, thus realize information acquisition.
Treatment scheme of the present invention as shown in Figure 3, concrete parameter (comprising brightness, contrast, all kinds of threshold value) is being set afterwards, obtain a frame video image, adopt the dynamic projection method to detect vehicle, and then obtain the information such as length, width and shape of each car on this two field picture, mate by information of vehicles, realize gathering the function of telecommunication flow information with last two field picture.
Vehicle detection i.e. whether attribute vehicle or background of the pixel on the resolution image how, and needs the different vehicle pixel of identification whether belong to same vehicle.Present technique has adopted the dynamic projection method to detect vehicle, and the flow process of this method is: at first carry out difference with background image and handle, carry out horizontal projection then, eliminate interference of noise, carry out image recognition, extract the characteristic information of vehicle.
The vehicle matching process utilizes the dynamic projection method to handle the information of vehicles (comprising vehicle length, width and shape facility etc.) that the back obtains, and mates with last frame image information.
Comprise the steps:
(1) threshold value and image acquisition parameter in the testing process are set;
(2) set surveyed area by control device, but multilane concurrent operation simultaneously;
(3) application background difference method is with the surveyed area binaryzation, and pixel and background gray scale difference are then thought target pixel greater than a certain threshold value, and its gray-scale value is composed to certain is worth certain look, obtains binary map;
(4) with the projection in the horizontal direction of this binary map, obtain perspective view;
(5) Fig. 2 being carried out label and handle, is the continuous rower of this look pixel same numbering;
(6) calculate each and number the quantity of this certain look pixel, the spacing of adjacent label, set threshold value when target pixel quantity is lower than, perhaps the spacing of adjacent label is lower than setting threshold, thinks that then noise gets rid of, and adjusts label;
(7) with the total vehicle number of last label as this two field picture;
(8) extract the feature of each label pixel block, comprise length, width and shape facility etc., as vehicle characteristics;
(9) vehicle feature with last two field picture mates; Fail as a certain vehicle of this two field picture that the match is successful, then total flow increases by 1; As the match is successful, then calculate vehicle displacement, calculate car speed, and calculate other traffic parameters;
(10) read down two field picture, forward step (3) to.
The system that a kind of video image that is used for real-time sampling of traffic information is handled, it has the structure that realizes above arbitrary described method.Can be: the stylus that is used for acquired signal links to each other with video tape recorder or image recorder, is connected with computing machine by image collection card, D again, is provided with traffic information collection software in this computing machine; This video tape recorder or image recorder can link to each other with the image monitoring device simultaneously.
Description of drawings
Fig. 1 is a binary map of the present invention.
Fig. 2 is a perspective view of the present invention.
Fig. 3 is the system handles schematic flow sheet.
Fig. 4 is the parameter interface that is provided with of the present invention.
Fig. 5 is that surveyed area of the present invention is provided with the interface synoptic diagram.
Fig. 6 is calibrating length of the present invention interface (being used for computed range).
Fig. 7 is a detection runnable interface of the present invention.
Fig. 8 is a hardware connection diagram of the present invention.
Embodiment
Sciagraphy and background subtraction method are a kind of technological means of frequent single image identification of using in the Flame Image Process engineering, sciagraphy carries out horizontal direction or vertical direction projection to image pixel (being generally 0-1 value image), and the background subtraction method will comprise the image of target and subtract each other with the pixel value that does not comprise the image of target.The present invention adopts new vehicle detection thinking---dynamic projection method.This method synthesis uses sciagraphy and background subtraction method, multiple image is carried out continuous dynamic process, by the image after the projection process is discerned the vehicle that detects single image, and the coupling of vehicle on the two field picture before and after finishing according to the feature of vehicle perspective view, thereby realize information acquisition.
Its ultimate principle is (white is represented target pixel among the figure) as depicted in figs. 1 and 2, and concrete steps are as follows:
1. threshold value and image acquisition parameter (brightness and contrast) in the testing process are set;
2. set surveyed area by control device (for example mouse), but multilane concurrent operation simultaneously;
3. application background difference method obtains Fig. 1 with surveyed area binaryzation (pixel and background gray scale difference are then thought target pixel greater than a certain threshold value, and it is 255 that its gray-scale value is composed, i.e. white);
4. with Fig. 1 projection in the horizontal direction, obtain Fig. 2;
5. Fig. 2 being carried out label and handle, is the continuous rower of white pixel same numbering;
6. calculate quantity, the spacing of adjacent label of each numbering white pixel, set threshold value when target pixel quantity is lower than, perhaps the spacing of adjacent label is lower than setting threshold, thinks that then noise gets rid of, and adjusts label;
7. with the total vehicle number of last label as this two field picture;
8. extract the feature of each label pixel block, comprise length, width and shape facility etc., as vehicle characteristics;
9. the vehicle feature with last two field picture mates.Fail as a certain vehicle of this two field picture that the match is successful, then total flow increases by 1; As the match is successful, then calculate vehicle displacement, calculate car speed, and calculate other traffic parameters;
10. read down two field picture, forward step 3 to;
Fig. 4-the 7th, the interface synoptic diagram of specific embodiment; Fig. 8 is the hardware connection diagram of an embodiment of the present invention: the stylus 1 that is used for acquired signal links to each other with video tape recorder or image recorder 2, be connected with computing machine 5 by image collection card 3, D 4 again, be provided with traffic information collection software 6 in this computing machine 5; This video tape recorder or image recorder 2 can link to each other with image monitoring device 7 simultaneously.
Claims (5)
1, a kind of method of video image processing that is used for real-time sampling of traffic information, it is characterized in that: carry out the pre-service of image with the background subtraction method after, adopt the dynamic projection method to carry out vehicle detection, extract vehicle characteristics information on this basis, the vehicle of two field picture coupling realizes the collection of transport information before and after carrying out.
2, the method for video image processing that is used for real-time sampling of traffic information according to claim 1, it is characterized in that: the flow process of described vehicle detection is: at first carry out difference with background image and handle, carry out horizontal projection then, eliminate interference of noise, carry out image recognition, extract the characteristic information of vehicle;
This vehicle matching process is to utilize the dynamic projection method to handle the information of vehicles that the back obtains, and mates with last frame image information.
3, the method for video image processing that is used for real-time sampling of traffic information according to claim 1 and 2 is characterized in that comprising the steps: that (1) is provided with threshold value and the image acquisition parameter in the testing process;
(2) set surveyed area by control device, but multilane concurrent operation simultaneously;
(3) application background difference method is with the surveyed area binaryzation, and pixel and background gray scale difference are then thought target pixel greater than a certain threshold value, and its gray-scale value is composed to certain is worth certain look, obtains binary map;
(4) with the projection in the horizontal direction of this binary map, obtain perspective view;
(5) this perspective view being carried out label and handle, is the continuous rower of this look pixel same numbering;
(6) calculate each and number the quantity of this certain look pixel, the spacing of adjacent label, set threshold value when target pixel quantity is lower than, perhaps the spacing of adjacent label is lower than setting threshold, thinks that then noise gets rid of, and adjusts label;
(7) with the total vehicle number of last label as this two field picture;
(8) extract the feature of each label pixel block, comprise length, width and shape facility, as vehicle characteristics;
(9) vehicle feature with last two field picture mates; Fail as a certain vehicle of this two field picture that the match is successful, then total flow increases by 1; As the match is successful, then calculate vehicle displacement, calculate car speed, and calculate other traffic parameters;
(10) read down two field picture, forward step (3) to.
4, the method for video image processing that is used for real-time sampling of traffic information according to claim 3 is characterized in that step (3), and it is 255 that its gray-scale value is composed, i.e. white.
5, a kind of system that is used for the video image processing of real-time sampling of traffic information, it is characterized in that: it has the structure that realizes arbitrary described method among the claim 1-4: the stylus that is used for acquired signal links to each other with video tape recorder or image recorder, be connected with computing machine by image collection card, D again, be provided with traffic information collection software in this computing machine; This video tape recorder or image recorder can link to each other with the image monitoring device simultaneously.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2005100285721A CN100435160C (en) | 2005-08-05 | 2005-08-05 | Video image processing method and system for real-time sampling of traffic information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2005100285721A CN100435160C (en) | 2005-08-05 | 2005-08-05 | Video image processing method and system for real-time sampling of traffic information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1909012A CN1909012A (en) | 2007-02-07 |
CN100435160C true CN100435160C (en) | 2008-11-19 |
Family
ID=37700116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2005100285721A Expired - Fee Related CN100435160C (en) | 2005-08-05 | 2005-08-05 | Video image processing method and system for real-time sampling of traffic information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100435160C (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510356B (en) * | 2009-02-24 | 2011-07-20 | 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 |
CN101714296B (en) * | 2009-11-13 | 2011-05-25 | 北京工业大学 | Telescopic window-based real-time dynamic traffic jam detection method |
CN102622575A (en) * | 2011-01-31 | 2012-08-01 | 日电(中国)有限公司 | Baseline band video monitoring system and monitoring method |
CN102779412B (en) * | 2011-05-13 | 2014-11-05 | 深圳市新创中天信息科技发展有限公司 | Integrated video traffic information detection method and system |
CN102509457B (en) * | 2011-10-09 | 2014-03-26 | 青岛海信网络科技股份有限公司 | Vehicle tracking method and device |
CN102810250B (en) * | 2012-07-31 | 2014-07-02 | 长安大学 | Video based multi-vehicle traffic information detection method |
CN102930719B (en) * | 2012-10-09 | 2014-12-10 | 北京航空航天大学 | Video image foreground detection method for traffic intersection scene and based on network physical system |
CN103021177B (en) * | 2012-11-05 | 2014-05-07 | 北京理工大学 | Method and system for processing traffic monitoring video image in foggy day |
CN103295403B (en) * | 2013-06-17 | 2016-02-10 | 湘潭大学 | A kind of traffic flow visual inspection method |
CN104751627B (en) * | 2013-12-31 | 2017-12-08 | 西门子公司 | A kind of traffic determination method for parameter and device |
CN108460968A (en) * | 2017-02-22 | 2018-08-28 | 中兴通讯股份有限公司 | A kind of method and device obtaining traffic information based on car networking |
CN113538891A (en) * | 2020-04-17 | 2021-10-22 | 无锡锦铖人工智能科技有限公司 | Intelligent vehicle counting system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07210795A (en) * | 1994-01-24 | 1995-08-11 | Babcock Hitachi Kk | Method and instrument for image type traffic flow measurement |
CN1145127A (en) * | 1994-04-08 | 1997-03-12 | 特拉菲肯公司 | A traffic monitoring device and method |
CN1197255A (en) * | 1997-04-18 | 1998-10-28 | 三星电子株式会社 | Apparatus for determining vehicle class and method therefor |
CN1350941A (en) * | 2000-10-27 | 2002-05-29 | 新鼎系统股份有限公司 | Method and equipment for tracking image of moving vehicle |
CN1464487A (en) * | 2002-06-03 | 2003-12-31 | 昆明利普机器视觉工程有限公司 | A traffic flow detection system based on visual vehicle optical characteristic recognition and matching |
JP2004005726A (en) * | 2003-07-24 | 2004-01-08 | Fujitsu Ltd | Traffic flow monitoring system for moving-body |
US20040131233A1 (en) * | 2002-06-17 | 2004-07-08 | Dorin Comaniciu | System and method for vehicle detection and tracking |
-
2005
- 2005-08-05 CN CNB2005100285721A patent/CN100435160C/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07210795A (en) * | 1994-01-24 | 1995-08-11 | Babcock Hitachi Kk | Method and instrument for image type traffic flow measurement |
CN1145127A (en) * | 1994-04-08 | 1997-03-12 | 特拉菲肯公司 | A traffic monitoring device and method |
CN1197255A (en) * | 1997-04-18 | 1998-10-28 | 三星电子株式会社 | Apparatus for determining vehicle class and method therefor |
CN1350941A (en) * | 2000-10-27 | 2002-05-29 | 新鼎系统股份有限公司 | Method and equipment for tracking image of moving vehicle |
CN1464487A (en) * | 2002-06-03 | 2003-12-31 | 昆明利普机器视觉工程有限公司 | A traffic flow detection system based on visual vehicle optical characteristic recognition and matching |
US20040131233A1 (en) * | 2002-06-17 | 2004-07-08 | Dorin Comaniciu | System and method for vehicle detection and tracking |
JP2004005726A (en) * | 2003-07-24 | 2004-01-08 | Fujitsu Ltd | Traffic flow monitoring system for moving-body |
Also Published As
Publication number | Publication date |
---|---|
CN1909012A (en) | 2007-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100435160C (en) | Video image processing method and system for real-time sampling of traffic information | |
CN106935035B (en) | Parking offense vehicle real-time detection method based on SSD neural network | |
CN108320510B (en) | Traffic information statistical method and system based on aerial video shot by unmanned aerial vehicle | |
Nieto et al. | Road environment modeling using robust perspective analysis and recursive Bayesian segmentation | |
US8538082B2 (en) | System and method for detecting and tracking an object of interest in spatio-temporal space | |
CN101030256B (en) | Method and apparatus for cutting vehicle image | |
CN104183127A (en) | Traffic surveillance video detection method and device | |
CN111753797B (en) | Vehicle speed measuring method based on video analysis | |
CN103310444B (en) | A kind of method of the monitoring people counting based on overhead camera head | |
CN104978567B (en) | Vehicle checking method based on scene classification | |
CN112800860B (en) | High-speed object scattering detection method and system with coordination of event camera and visual camera | |
JPH05244596A (en) | Video image processor and vehicle detection method | |
Pan et al. | Traffic surveillance system for vehicle flow detection | |
CN104134222A (en) | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion | |
CN105513342A (en) | Video-tracking-based vehicle queuing length calculating method | |
CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
CN110633678B (en) | Quick and efficient vehicle flow calculation method based on video image | |
Rodríguez et al. | An adaptive, real-time, traffic monitoring system | |
CN112270310A (en) | Cross-camera pedestrian multi-target tracking method and device based on deep learning | |
CN102393901A (en) | Traffic flow information perception method based on hybrid characteristic and system thereof | |
CN105243354B (en) | A kind of vehicle checking method based on target feature point | |
CN101320477B (en) | Human body tracing method and equipment thereof | |
CN102749034A (en) | Railway switch gap offset detection method based on image processing | |
CN114530042A (en) | Urban traffic brain monitoring system based on internet of things technology | |
CN113591643A (en) | Underground vehicle station entering and exiting detection system and method based on computer vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20081119 Termination date: 20150805 |
|
EXPY | Termination of patent right or utility model |