CN1737578A - Road vehicle speed measuring method realized only by video - Google Patents
Road vehicle speed measuring method realized only by video Download PDFInfo
- Publication number
- CN1737578A CN1737578A CN 200410059169 CN200410059169A CN1737578A CN 1737578 A CN1737578 A CN 1737578A CN 200410059169 CN200410059169 CN 200410059169 CN 200410059169 A CN200410059169 A CN 200410059169A CN 1737578 A CN1737578 A CN 1737578A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- speed
- video
- measuring method
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
This invention relates to one pure visual road auto speed measurement method, which adopts two light axis parallel vidicon and alternately collects auto series images and analyzes auto OCR optical characters as matching conditions to get auto displacement values and time gap to compute auto movement speed. The invention is applied in high speed road measurement and flow velocity system, city traffic organization.
Description
Technical field
The present invention relates to the pure video road vehicle speed-measuring method of the harmless binocular vision technology of a kind of noncontact, belong to field of machine vision.
Background technology
The binocular vision clue is human perceived distance, one of main method of the depth information of acquisition scenery.The vision physiological function construction computer vision system of anthropomorphic dummy and some animal, the difference that analyzes wherein from the taken sequence image of two or more camera chains is tried to achieve three-dimensional spatial information, stereoscopic analytical approach that Here it is.Such stereo visual system does not need special device, constructs easyly, is suitable for the three-dimensional surface analysis of convex polyhedron.In the binocular tri-dimensional vision system, the optical axis of two video cameras can intersect, and also can be parallel to each other, and the geometrical principle of imaging is similar.
Adopt two optical axises video camera parallel to each other, alternately the collection vehicle image series is analyzed vehicle OCR optical character feature as matching condition, obtains the vehicle movement numerical value and the time interval, can calculate vehicle movement speed.Simultaneously can also obtain the vehicle distances parameter by binocular parallax.
Along with growing continuously and fast and the continuous increase of vehicle owning amount of Domestic Automotive Industry, vehicle in accordance with regulations speed on road is travelled, ensure The coast is clear, punishment hypervelocity violator, and provide traffic flow data etc. to traffic programme department, all identification and the speed monitoring to vehicle proposes higher requirement; " road vehicle intelligent monitoring and recording system general technical specifications " (draft for deliberation) of " People's Republic of China's industry standards of public safety " then explicitly calls for functions such as having vehicle image record, number plate identification in road vehicle intelligent monitoring and recording system.Vehicle image comprises vehicle characteristics image (feature image) and overview image (panorama image).
The present invention proposes the motor vehicles that travel on the specific lane to be monitored automatically the analysis-by-synthesis information of vehicles based on the pure video road vehicle speed-measuring method of the harmless binocular vision technology of a kind of noncontact.When the travel speed that detects road motor vehicle exceeds setting range (Maximum speed limit or minimum speed limit), triggering control system by video gives video camera with trigger pip, video camera is just captured vehicle image to vehicles peccancy, transfers to timely and is installed in charge station or near the management control center of bayonet socket by will break rules and regulations image (compressed image file) and violation data of communication system.When vehicle arrives charge station's outlet or during the bayonet socket of the place ahead, the license plate recognition system that is installed in the exit is discerned license plate number automatically, by comparing with license plate information violating the regulations storehouse, the information of vehicles storehouse of deploying to ensure effective monitoring and control of illegal activities, exeed the regulation speed as finding, the vehicle alarm indication at once of deploying to ensure effective monitoring and control of illegal activities, the policeman just can tackle punishment, also use as evidence obtaining speed that all general information data can be comprised place, date, time, vehicle or the like storage card (PC-card) lining of all being deposited in high power capacity, also can manage operation to information of vehicles in the terminal management control system certainly.
Summary of the invention
The object of the present invention is to provide the pure video road vehicle speed-measuring method of the harmless binocular vision technology of a kind of noncontact to be mainly used in fields such as vehicle on highway speed, flow quantity detecting system, public security bayonet socket, Urban Traffic Planning.Knotmeter by this method design is made up of hardware components and software section.The application of this method and knotmeter has improved Traffic control for express highways efficient greatly, has alleviated highway patrol police's working strength, has reduced danger coefficient, has improved the science and the accuracy of patrol police's law enforcement.
The pure video frequency speed-measuring method of the harmless binocular vision technology of a kind of noncontact of the present invention and the technical scheme of knotmeter are: at the need of appointment the speed of a motor vehicle is carried out speed limit high-grade highway the roadside or above portal frame on the mounting vehicle knotmeter.The vehicle speed measuring instrument is made up of hardware components and software section.Hardware components comprises video device, processor, image pick-up card and light filling luminaire.Software section comprises modules such as image acquisition, calculating, identification, coupling, comparison, storage, compression, communication, alarm.Kernel software " mobile Sign Recognition " adopts the Kunming general machine vision of profit company " mobile Sign Recognition V1.0, computer software copyright registration certificate registration number: 2002SR3044 copyright owner: the Kunming general machine vision of profit company ".
The pure video frequency speed-measuring method of the harmless binocular vision technology of a kind of noncontact of the present invention, implementation step is as follows:
1. vehicle is by road, and video detection triggers;
2. the video device is set electronic shutter and exposure intensity according to ambient light, opens controlled light filling illuminating lamp automatically at night;
3. the video device receives the video detection trigger pip, catches several vehicle images;
4. image series is discerned and analyzed to knotmeter automatically by identification module;
5. adopt image Segmentation Technology that vehicle and background are separated;
6. the geometric properties on the extraction vehicle image comprises the optical character feature;
7. adopt accurate measuring vehicle displacement of image measurement technology and running time;
8. calculating Vehicle Speed;
9. recording information of vehicles comprises: speed, place, image, time, travel direction, license number etc.;
10. if the speed of travels down vehicle surpasses fixing speed scope (top speed or minimum speed) or reverse driving, knotmeter onsite alarming and remote alarms immediately then, the police can tackle punishment on the spot; Or
11. knotmeter is transferred to charge station or bayonet socket with the vehicles peccancy related data by (or nothing) line communication interface is arranged, the police tackles punishment; Or
12. knotmeter is transferred to the road management center with the vehicles peccancy related data by (or nothing) line communication interface is arranged, the police punishes afterwards.
Compared with prior art, the present invention has the following advantages;
Noncontact, harmless road surface; Can be Incident Management visual image is provided; A large amount of traffic management informations can be provided; Separate unit binocular video device and processor can detect multilane; System's long service life, maintenance workload are extremely low; The system change adjustment is easy; Rate accuracy up to: ± 1 km/hour; Has more excellent cost performance than laser velocimeter and radar meter commonly used.Vehicle image acquisition mode of the present invention is that the mode with video triggers, and needn't excavate the pre-buried vehicle detection coil of highway pavement, has both protected the road surface of high-grade highway, guarantees that again equipment maintenance service from now on is convenient.While can obstruction when installation and maintenance service.
Description of drawings
Fig. 1 is the workflow diagram of the pure video road vehicle speed-measuring method of the harmless binocular vision technology of noncontact of the present invention.
Embodiment
Be further described below in conjunction with the pure video frequency speed-measuring method and the knotmeter of the drawings and specific embodiments the harmless binocular vision technology of noncontact of the present invention.
1. vehicle is by road, and video detection triggers;
2. the video device is set electronic shutter and exposure intensity according to ambient light, opens controlled light filling luminaire automatically at night;
3. the video device receives the video detection trigger pip, catches several vehicle images;
4. image series is discerned and analyzed to knotmeter automatically by identification module;
5. adopt image Segmentation Technology that vehicle and background are separated;
6. the geometric properties on the extraction vehicle image comprises the optical character feature;
7. adopt accurate measuring vehicle displacement of image measurement technology and running time;
8. calculating Vehicle Speed;
9. recording information of vehicles comprises: speed, place, image, time, travel direction, license number etc.;
10. if the speed of travels down vehicle surpasses fixing speed scope (top speed or minimum speed) or reverse driving, knotmeter onsite alarming and remote alarms immediately then, the police can tackle punishment on the spot; Or
11. knotmeter is transferred to charge station or bayonet socket with the vehicles peccancy related data by (or nothing) line communication interface is arranged, the police tackles punishment; Or
12. knotmeter is transferred to the road management center with the vehicles peccancy related data by (or nothing) line communication interface is arranged, the police punishes afterwards.
The pure video road vehicle speed-measuring method and the knotmeter of the harmless binocular vision technology of noncontact of the present invention also can be applicable in the supervisory system of urban public security 110 bayonet sockets, to realize that networking deploys to ensure effective monitoring and control of illegal activities, find, intercept, arrest overspeed violation, escape, robber and rob vehicle.
Each main public security 110 bayonet socket in the city are installed pure video road vehicle knotmeter, and this knotmeter is round-the-clock full-automatic in real time according to the number-plate number that collects and the number-plate number on the blacklist in vehicle image and the database and the vehicle image coupling of comparing; As find the matching result unanimity, and then device calls alarm module and sends the sound and light alarm cue, and police on duty receives the report for police service and can the scene intercepts, arrests overspeed violation, escape, robber and rob vehicle.This device also can be realized the measurement to vehicle flowrate, average speed, roadway occupancy, vehicle classification, vehicle density, following distance, for traffic administration and planning department provide real-time accurate data.
The pure video road vehicle speed-measuring method and the knotmeter of the harmless binocular vision technology of above-mentioned noncontact are made up of hardware components and software section.Hardware components comprises video device, processor, image pick-up card and light filling luminaire.What this knotmeter adopted is open hardware architecture, can both buy ripe product on market.Software section comprises modules such as image acquisition, identification, coupling, comparison, storage, compression, communication, alarm.Image pick-up card, communication module and alarm module can both buy ripe product equally on market.Kernel software " mobile Sign Recognition " adopts the Kunming general machine vision of profit company " mobile Sign Recognition V1.0, computer software copyright registration certificate registration number: 2002SR3044 copyright owner: the Kunming general machine vision of profit company ".Especially being noted that vehicle image acquisition mode of the present invention, is to adopt pure video to trigger.Crucial a bit is the technical requirement that this knotmeter has satisfied field engineering, under in all weather conditions, rate accuracy up to: ± 1 km/hour; Greater than 90%, reject rate is less than 5 ‰ to discrimination for matching ratio, and recognition time has more excellent cost performance less than 300 milliseconds than laser velocimeter and radar meter commonly used.
The pure video road vehicle speed-measuring method of the harmless binocular vision technology of noncontact of the present invention and knotmeter are in application, and the data of its image recognition and knotmeter output have:
(1) vehicle image data: 8 BMP, 768*576/4=110592 ≈ 108K; JPEG is more than 10～40 about K.
(2) vehicle image characteristic: be the data that comprise the vehicle image principal character, JPEG, 8K altogether.
For highroad toll collection system, Vehicle Speed, number-plate number data and vehicle image data are sent to road information administrative center by computer network; Road information administrative center can link to each other with the highway Information Network of the whole nation or the whole province.
For the supervisory system of urban public security 110 bayonet sockets, Vehicle Speed, number-plate number data and vehicle image data are sent in the vehicle image automatic identification equipment of public security department vehicle information management center, each bayonet socket by computer network; The vehicle information management center can link to each other with the public security Information Network of the whole nation or the whole province.
Need to prove; particular case of the present invention is described in detail pure video road vehicle speed-measuring method and the knotmeter based on the harmless binocular vision technology of noncontact of the present invention; for a person skilled in the art, the various conspicuous change of under the situation of the spirit and scope that do not deviate from the method for the invention it being carried out is all within protection scope of the present invention.
Claims (6)
1. the pure video road vehicle speed-measuring method of the harmless binocular vision technology of a kind of noncontact of the present invention, adopt two optical axises video camera parallel to each other, replace the collection vehicle image series, analyze vehicle OCR optical character feature as matching condition, obtain the vehicle movement numerical value and the time interval, can calculate vehicle movement speed.Knotmeter by this method design is made up of hardware components and software section.Hardware components comprises video device, processor, image pick-up card and light filling luminaire.Software section comprises modules such as image acquisition, calculating, identification, coupling, comparison, storage, compression, communication, alarm, and the performing step of its method is as follows:
(1) vehicle is by road, and video detection triggers;
(2) the video device is set electronic shutter and exposure intensity according to ambient light, opens controlled light filling illuminating lamp automatically at night;
(3) the video device receives the video detection trigger pip, catches several vehicle images;
(4) image series is discerned and analyzed to knotmeter automatically by identification module;
(5) adopt image Segmentation Technology that vehicle and background are separated;
(6) geometric properties that extracts on the vehicle image comprises the optical character feature;
(7) adopt accurate measuring vehicle displacement of image measurement technology and running time;
(8) calculate Vehicle Speed;
(9) recording information of vehicles comprises: speed, place, image, time, travel direction, license number etc.;
(10) if the speed of travels down vehicle surpasses the fixing speed scope, i.e. top speed and minimum speed and reverse driving, knotmeter onsite alarming and remote alarms immediately then, the police can tackle punishment on the spot.
2. pure video road vehicle speed-measuring method according to claim 1 is characterized by: knotmeter is transferred to charge station or bayonet socket with the vehicles peccancy related data by (or nothing) line communication interface is arranged, and the police tackles punishment.
3. pure video road vehicle speed-measuring method according to claim 1 is characterized by: knotmeter is transferred to the road management center with the vehicles peccancy related data by (or nothing) line communication interface is arranged, and the police punishes afterwards.
4. pure video road vehicle speed-measuring method according to claim 1, it is characterized by: described video device is a binocular camera.
5. pure video road vehicle speed-measuring method according to claim 1, it is characterized by: described vehicle image is the characteristic image of vehicle.
6. pure video road vehicle speed-measuring method according to claim 1, it is characterized by: described vehicle image is the overview image of vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200410059169 CN1737578A (en) | 2004-08-19 | 2004-08-19 | Road vehicle speed measuring method realized only by video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200410059169 CN1737578A (en) | 2004-08-19 | 2004-08-19 | Road vehicle speed measuring method realized only by video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1737578A true CN1737578A (en) | 2006-02-22 |
Family
ID=36080444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200410059169 Pending CN1737578A (en) | 2004-08-19 | 2004-08-19 | Road vehicle speed measuring method realized only by video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1737578A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100452110C (en) * | 2006-07-14 | 2009-01-14 | 沈阳江龙软件开发科技有限公司 | Automobile video frequency discrimination speed-testing method |
| CN101187671B (en) * | 2007-12-27 | 2010-06-02 | 北京中星微电子有限公司 | Method and device for determining automobile driving speed |
| CN101206229B (en) * | 2007-12-11 | 2010-12-08 | 长安大学 | Method for matching vehicle speed based on linear array CCD image |
| CN101553852B (en) * | 2006-11-10 | 2011-02-02 | 器械（股份）责任有限公司 | System and method for detection of average speed of vehicles for traffic control |
| CN102194132A (en) * | 2011-04-07 | 2011-09-21 | 国通道路交通管理工程技术研究中心有限公司 | Detection and identification system and method for accompanying vehicle |
| CN102289659A (en) * | 2011-06-23 | 2011-12-21 | 杭州诚道科技有限公司 | Companion vehicle detection method |
| CN102819951A (en) * | 2011-06-09 | 2012-12-12 | 无锡物联网产业研究院 | Road target detection system, road target detection method and road target detection device |
| CN101907701B (en) * | 2009-06-08 | 2013-05-29 | 英华达股份有限公司 | Navigation assistant speed computing method |
| CN103208183A (en) * | 2013-04-03 | 2013-07-17 | 昆明联诚科技有限公司 | Vehicle video data mining method for traffic violation evidence obtaining |
| CN109949583A (en) * | 2019-04-15 | 2019-06-28 | 南京信息工程大学 | A kind of charge station's active safety protection alarming device and method |
-
2004
- 2004-08-19 CN CN 200410059169 patent/CN1737578A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100452110C (en) * | 2006-07-14 | 2009-01-14 | 沈阳江龙软件开发科技有限公司 | Automobile video frequency discrimination speed-testing method |
| CN101553852B (en) * | 2006-11-10 | 2011-02-02 | 器械（股份）责任有限公司 | System and method for detection of average speed of vehicles for traffic control |
| CN101206229B (en) * | 2007-12-11 | 2010-12-08 | 长安大学 | Method for matching vehicle speed based on linear array CCD image |
| CN101187671B (en) * | 2007-12-27 | 2010-06-02 | 北京中星微电子有限公司 | Method and device for determining automobile driving speed |
| CN101907701B (en) * | 2009-06-08 | 2013-05-29 | 英华达股份有限公司 | Navigation assistant speed computing method |
| CN102194132A (en) * | 2011-04-07 | 2011-09-21 | 国通道路交通管理工程技术研究中心有限公司 | Detection and identification system and method for accompanying vehicle |
| CN102819951A (en) * | 2011-06-09 | 2012-12-12 | 无锡物联网产业研究院 | Road target detection system, road target detection method and road target detection device |
| CN102819951B (en) * | 2011-06-09 | 2016-05-11 | 无锡物联网产业研究院 | A kind of road target detection system, method and device |
| CN102289659A (en) * | 2011-06-23 | 2011-12-21 | 杭州诚道科技有限公司 | Companion vehicle detection method |
| CN103208183A (en) * | 2013-04-03 | 2013-07-17 | 昆明联诚科技有限公司 | Vehicle video data mining method for traffic violation evidence obtaining |
| CN109949583A (en) * | 2019-04-15 | 2019-06-28 | 南京信息工程大学 | A kind of charge station's active safety protection alarming device and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN201594319U (en) | Multifunctional electronic police system with high-definition snapshot | |
| CN102945603B (en) | Method for detecting traffic event and electronic police device | |
| KR101786923B1 (en) | CCTV system integrated multi operations | |
| CN204856896U (en) | Radar traffic incident automatic check out system | |
| CN1725266A (en) | Vehicle intelligent monitoring recording syste mand method based on video trigger and speed measuring | |
| CN1851777A (en) | Vehicle video data digging system and method for obtaining evidence about drive against traffic regulations | |
| CN111340003B (en) | Evidence obtaining method and system for illegal lane change behavior in electronic police blind area | |
| CN103676829A (en) | An intelligent urban integrated management system based on videos and a method thereof | |
| CN201397576Y (en) | Device for automatically shooting picture of the illegal turning of vehicles at crossings | |
| JPH07210795A (en) | Method and instrument for image type traffic flow measurement | |
| CN1737578A (en) | Road vehicle speed measuring method realized only by video | |
| CN109348179A (en) | A kind of road monitoring detection system and method based on artificial intelligence | |
| Haghighat et al. | A computer vision‐based deep learning model to detect wrong‐way driving using pan–tilt–zoom traffic cameras | |
| TW201919017A (en) | System and method for automatically proving traffic violation vehicles | |
| CN1120782C (en) | Automatic method for indentification of number plate of vehicle | |
| CN112435478A (en) | Off-site illegal management method and system based on roadside parking high-order video equipment | |
| CN112071058A (en) | Road traffic monitoring and vehicle abnormity, contraband and fire detection method and system based on deep learning | |
| CN112749630A (en) | Intelligent video monitoring method and system for road conditions | |
| CN1133138C (en) | Automatic traffic video image treating system | |
| CN111899522A (en) | Monitoring system for road traffic public security bayonet | |
| CN113870551B (en) | Road side monitoring system capable of identifying dangerous and non-dangerous driving behaviors | |
| CN117894187A (en) | Highway intellectual detection system early warning system | |
| CN101303798A (en) | Novel bayonet | |
| CN101533558A (en) | Fixed intersection monitoring system | |
| CN2718699Y (en) | Intelligent monitoring and recording system based on video trigger and velocity measurement for vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |