CN102496281A - Vehicle red-light violation detection method based on combination of tracking and virtual loop - Google Patents
Vehicle red-light violation detection method based on combination of tracking and virtual loop Download PDFInfo
- Publication number
- CN102496281A CN102496281A CN2011104217108A CN201110421710A CN102496281A CN 102496281 A CN102496281 A CN 102496281A CN 2011104217108 A CN2011104217108 A CN 2011104217108A CN 201110421710 A CN201110421710 A CN 201110421710A CN 102496281 A CN102496281 A CN 102496281A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- red light
- dash
- detect
- state
- 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.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle tracking method and vehicle tracking system based on the video identification technology, wherein a fixed region is defined at the bottom of a video image so as to detect the appearance of vehicles. An inter-frame space number of system frame difference is determined according to vehicle length and vehicle speed. When the vehicle appears, the running speed stage of the vehicle is judged according to a frame difference value and a special threshold, if the vehicle frame difference value is more than the set threshold, the violation state of the vehicle is detected by a virtual loop method, if the vehicle frame difference value is not more than the set threshold, the violation state of the vehicle is detected by a background difference subtraction tracking method. The system relates to vehicle detection and tracking methods and systems for the same based on machine vision; and the method comprises the following steps of: capturing images, establishing and updating background, detecting vehicle appearance, judging the running state of the vehicles, and respectively selecting the virtual loop method or the tracking method to detect the red-light violation behaviors of vehicles according to the running state of the vehicles.
Description
Technical field
The present invention designs field of traffic, particularly relates to a kind of traffic lights recognition system and method.
Background technology
Intelligent transportation system is a big focus of researching and developing at present.Intelligent transportation system is to apply to whole traffic management system with advanced person's infotech, data communication transmission technology, electronic sensor technology, electron controls technology and Computer Processing technology etc. are integrated effectively; And a kind of interior on a large scale, the full position of setting up plays a role, comprehensively transport in real time, accurately and efficiently and management system.
Wherein, in intelligent transportation system, vehicle detection and tracking are most basic parts; It requires from the resulting image sequence of video camera; Detection has or not the examination hall of moving vehicle entering video camera, and the position of setting movement vehicle, and it belongs to the research range of computer vision.
At present, have powerful connections poor method, frame difference method and optical flow method of commonly used vehicle checking method.Wherein, the background subtraction method is a kind of method the most frequently used during present moving vehicle is cut apart, and it is to utilize the difference of present image and image to detect a kind of technology of moving region.
Frame difference method is to do to extract the detection that moving vehicle is realized in the moving region based on the time difference and the thresholding of pixel between two frames fixing in the continuous images sequence or the multiframe partition image.
Moving vehicle to detecting will be followed the tracks of, and vehicle tracking algorithm at present commonly used mainly contains: based on the track algorithm of characteristic, based on the track algorithm of 3-D, based on the track algorithm of distorted pattern with based on the track algorithm in zone.Wherein, based on the track algorithm of characteristic, be exactly that 1 car is extracted some characteristics such as diacritic straight line or turning etc., or these characteristics combination are represented a vehicle, even the outstanding advantage of this type algorithm is to have partial occlusion, some characteristics are still visible.But when vehicle each other too near the time, the problem that exists characteristic too closely can't cut apart.Based on the track algorithm of 3-D is through using the geometry knowledge of video camera and scene, has the three-dimensional model of precise geometry to project into image with one, follows the tracks of according to the change in location in the image.The advantage of this type algorithm is that accuracy rate is high when type of vehicle of confirming and geometric model details, and shortcoming is that the mountain is big in the last work amount of calculating, and real-time is poor.Track algorithm based on distorted pattern is tracing object with the vehicle ' s contour, extracts contour feature through the snake active contour model.This method is blocked sensitivity to noise, has profile initialization problem.Based on the track algorithm in zone at first join domain extract and according to circumstances merged or cut apart.The most serious weakness of this method is that the zone merges and cut apart the inaccurate situation that exists in vehicle detection.
More than multiple vehicle detection with to follow the tracks of efficient not high, be badly in need of addressing this problem.
Summary of the invention
The object of the present invention is to provide a kind of effective crossing vehicle detection method of making a dash across the red light.For realizing its purpose, the present invention proposes a kind of based on following the tracks of the vehicle that combines with the virtual coil detection method system of making a dash across the red light, and it is characterized in that it comprises: obtain the current video two field picture, the generation background image; Delimit surveyed area in the video bottom; Extract information of vehicles, adopt frame difference method to estimate state of motion of vehicle; If frame difference limen value is greater than setting threshold, then adopt the virtual coil method to detect the vehicle state that makes a dash across the red light; If frame difference limen value is greater than setting threshold, then adopt tracing to detect the vehicle state that makes a dash across the red light.
1) system obtains current video frame through camera, obtains the frame of video in the some cycles, dynamically generates the background image at current crossing.
2) system adopts regional area to detect the vehicle appearance, is unified in the video bottom section and trigger condition is set and detects type of vehicle, judges that situation appears in vehicle; Analyze the characteristics of vehicle,, confirm the interFrameGap number of frame difference in conjunction with length of wagon, frame of video frame per second and speed of a motor vehicle relation through the crossing; If vehicle appears in this zone, then correspondence is set up a detection or tracing object; In FX, do background and subtract, when vehicle occurred, grey scale pixel value was considered to the foreground moving target greater than the pixel region of a certain threshold value in the difference diagram that obtains; These foreground pixel points are for further processing, can obtain information such as moving vehicle position, size, shape; With the lane width is unified object of reference, obtains vehicle length and width information, when reaching certain condition, triggers a detected object.
3) system selects for use the virtual coil method to detect vehicle and makes a dash across the red light according to the detected object characteristic that triggers, and is reference with the stop line, in the track, delimits first virtual coil in the stop line anteposition, behind stop line, delimits second coil; In red light cycle, judge traveling state of vehicle according to the logic state that vehicle in two coils triggers, the coil state can be divided into suspicious state, candid photograph state, blocked state, idle condition; Make a dash across the red light if vehicle takes place, then trigger capture machine and capture corresponding picture.
4), select for use the tracing that combines background to subtract difference to detect the vehicle peccancy state according to the detected object characteristic that triggers; Subtract each other back absolute value addition to the RGB triple channel of background and current video respectively, the probability density figure of this difference as the iteration tracking; Analyze vehicle driving trace, in red light cycle, judge vehicle driving trace and relation, make a dash across the red light, then trigger capture machine and capture corresponding picture if vehicle takes place for the track stop line.
Shown in Figure 1 is the process flow diagram of embodiment of the invention journey.
Embodiment
In order more to understand technology contents of the present invention, the spy lifts preferred embodiment, and cooperates appended graphic explanation following.
Be illustrated in figure 1 as the process flow diagram of the present invention's one preferred embodiment, the present invention---a kind ofly comprise the following steps based on following the tracks of the vehicle combine with the virtual coil detection method of making a dash across the red light.
Step 100: obtain the current video two field picture through camera, manually on image, draw surveyed area, in surveyed area, occur earlier when vehicle is through the crossing usually, set interactive information such as track, stop line simultaneously.
Step 110: the foundation of background and renewal.Obtain the video image of getting three minutes approximately in advance and set up background; (as 30 seconds) are carried out context update one time at regular intervals in testing process.
Step 120: the frame of video generation background image in 3 green light cycles.After obtaining background image, manually delimit surveyed area, detect vehicle and occur in the video bottom.
Step 130: under the situation of cruising; Vehicle occurs from the frame of video bottom usually; Drive towards in the middle of the video back from the top or the left and right sides disappear; When vehicle arrives the video bottom, this zone visual information is changed, as long as can judging, detection video bottom section has or not emerging vehicle.
The method that adopts regional area to detect is unified in this zone and trigger condition is set and detects type of vehicle; If vehicle appears in this zone, then correspondence is set up a detection or tracing object and need not the whole video zone is detected.
Be more accurately localizing objects vehicle, the present invention also combines the result of frame difference, further confirms the result of background in subtracting.
Because different crossings video camera sets up height maybe be different with video camera phase road pavement angle; Vehicle presents big or small disunity in the image at different crossings; Vehicle size information is difficult to judge; So the present invention is unified object of reference with the lane width, different vehicle dimension information width is all with reference to vehicle width.
The interFrameGap of processing video frames is counted the parameter that N is a key; The N value is too little, can't effectively detect, internal color consistent reach the slowly target of motion big such as size, and the N value is too big; The moving region of detecting is inaccurate; Therefore, analyze actual crossing length of wagon and frame of video frame per second relation, to confirm the N value.
Different vehicle is with the asynchronism(-nization) of the different speed of a motor vehicle through same segment distance, and the distance of same section effluxion is also different, analyzes the moving of car situation of friction speed through the crossing, the variation of every frame traveling-position, thus confirm the N value.
Because the camera installation site is different, the crossing actual conditions are different, so with dolly length of wagon standard as a reference, analysis time period is also with a dolly length of wagon of vehicle ' elapsed time standard as a reference.Usually the length of wagon of dolly is 4.40 meters, and following table has compared the time of friction speed through length of wagon, as calculating, has obtained the distance of every frame vehicle process with per second 25 frames.
The speed of a motor vehicle be the speed of a motor vehicle of 10km/h, 20km/h, 40km/h, 60km/h through the crossing, the vehicle movement of every frame is respectively 11.11 cm, 22.22 cm, 44.44 cm, 66.67 cm.
The speed of a motor vehicle was in the 40km/h when usually vehicle was through the crossing, so that motion detection frame of video interbody spacer is set to 2 frames is comparatively suitable, promptly per 3 frames are got a frame.
The speed of vehicle at the crossing is 40km/h, per 3 frames 3/10 of dolly length of wagon of going approximately, so the N value is set to 2 among the present invention.
The threshold decision crossing ambient condition and the vehicle speed state that obtain according to the frame difference.
Find that through the multitude of video checking there is general phenomenon in traffic intersection, when the speed of a motor vehicle is fast, is generally green light cycle and crossing car and disturbs few less; When vehicle was slow, normally the vehicle religion was blocked up or the red light situation.
Find that according to multitude of video checking during through the crossing, the frame difference is very obvious with the very fast speed of a motor vehicle for vehicle; But vehicle location and characteristic also change obviously; Be unfavorable for the realization of tracking, and the speed of a motor vehicle is when slow, the frame difference is not obvious; But it is not obvious that vehicle location and characteristic also change, and helps the realization of tracking.
Therefore the present invention designs frame difference method judgement state of motion of vehicle, selects the corresponding processing strategy for use according to different frame difference intensity.As frame difference result during, select for use the virtual coil method to detect, otherwise select for use tracing to detect greater than threshold value.
Step 140: according to the detected object characteristic that triggers, selecting for use the virtual coil method to detect vehicle and make a dash across the red light, is reference with the stop line, in the track, delimits first virtual coil in the stop line anteposition, behind stop line, delimits second coil; In red light cycle, judge traveling state of vehicle according to the logic state that vehicle in two coils triggers, the coil state can be divided into suspicious state, candid photograph state, blocked state, idle condition; Under red light lighted situation, putting coil 1 was idle condition with coil 2, when coil 1 has been judged as the car state, captures a pictures in advance; When coil 1 and coil 2 are captured second photo, last the 3rd photo of set time internal trigger for there being car to trigger simultaneously; When coil 1 has car, during the no car of coil 2, coil 1 is in blocked state; The complete procedure that vehicle makes a dash across the red light has been reacted in this design.
Step 150:, select for use the tracing that combines background to subtract difference to detect the vehicle peccancy state according to the detected object characteristic that triggers; Subtract each other back absolute value addition to the RGB triple channel of background and current video respectively; The image difference of vehicle region is to be the mountain peak shape; The zone, track then is tangible level land shape, and the probability density figure this difference is followed the tracks of as iteration can very stable iteration obtain vehicle location; Analyze vehicle driving trace, in red light cycle, judge vehicle driving trace and relation, make a dash across the red light, then trigger capture machine and capture corresponding picture if vehicle takes place for the track stop line.
It should be noted last that above embodiment is only unrestricted in order to technical scheme of the present invention to be described.Although the present invention is specified with reference to embodiment; Those of ordinary skill in the art is to be understood that; Technical scheme of the present invention is made amendment or is equal to replacement, the spirit and the scope of all little disengaging technical scheme of the present invention, it all should be encompassed in the middle of the claim scope of the present invention.
Claims (5)
1. one kind based on the vehicle of following the tracks of to combine with the virtual coil detection method of making a dash across the red light, and it is characterized in that it comprises:
1) obtains the current video two field picture, the generation background image;
2) delimit surveyed area in the video bottom;
3) extract information of vehicles, adopt frame difference method to estimate state of motion of vehicle;
4) if frame difference limen value greater than setting threshold, then adopts the virtual coil method to detect the vehicle state that makes a dash across the red light;
5) if frame difference limen value not greater than setting threshold, then adopts tracing to detect the vehicle state that makes a dash across the red light.
2. according to claim 1 a kind of based on following the tracks of the vehicle combine with the virtual coil detection method service system that makes a dash across the red light, it is characterized in that:
1) obtains current video frame through camera;
2) obtain the interior frame of video of some cycles, dynamically generate the background image at current crossing.
3. according to claim 1 a kind of based on following the tracks of the vehicle combine with the virtual coil detection method service system that makes a dash across the red light, it is characterized in that:
1) adopts regional area to detect vehicle and occur, be unified in the video bottom section and trigger condition be set and detect type of vehicle, judge that situation appears in vehicle;
2) analyze the characteristics of vehicle,, confirm the interFrameGap number of frame difference in conjunction with length of wagon and speed of a motor vehicle relation through the crossing;
3) if vehicle appears in this zone, then correspondence is set up a detection or tracing object;
4) in FX, do background and subtract, when vehicle occurred, grey scale pixel value was considered to the foreground moving target greater than the pixel region of a certain threshold value in the difference diagram that obtains;
5) these foreground pixel points are for further processing, can obtain information such as moving vehicle position, size, shape;
6) be unified object of reference with the lane width, obtain vehicle length and width information, when reaching certain condition, trigger a detected object.
4. according to claim 3 a kind of based on following the tracks of the vehicle combine with the virtual coil detection method system of making a dash across the red light, it is characterized in that:
1) according to the detected object characteristic that triggers, select for use the virtual coil method to detect vehicle and make a dash across the red light, with the stop line reference, in the track, delimit first virtual coil in the stop line anteposition, behind stop line, delimit second coil;
2) in red light cycle, judge traveling state of vehicle according to the logic state that vehicle in two coils triggers;
3) if vehicle takes place to make a dash across the red light, then trigger capture machine and capture corresponding picture.
5. according to claim 3 a kind of based on following the tracks of the vehicle combine with the virtual coil detection method system of making a dash across the red light, it is characterized in that:
1), select for use the tracing that combines background to subtract difference to detect the vehicle peccancy state according to the detected object characteristic that triggers;
2) adopt the probability density figure of the difference of background subtraction as the iteration tracking;
3) analyze vehicle driving trace, in red light cycle, judge vehicle driving trace and relation, make a dash across the red light, then trigger capture machine and capture corresponding picture if vehicle takes place for the track stop line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104217108A CN102496281B (en) | 2011-12-16 | 2011-12-16 | Vehicle red-light violation detection method based on combination of tracking and virtual loop |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104217108A CN102496281B (en) | 2011-12-16 | 2011-12-16 | Vehicle red-light violation detection method based on combination of tracking and virtual loop |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102496281A true CN102496281A (en) | 2012-06-13 |
| CN102496281B CN102496281B (en) | 2013-11-27 |
Family
ID=46188100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104217108A Active CN102496281B (en) | 2011-12-16 | 2011-12-16 | Vehicle red-light violation detection method based on combination of tracking and virtual loop |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102496281B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218916A (en) * | 2013-04-07 | 2013-07-24 | 布法罗机器人科技（苏州）有限公司 | Method and system for detecting red light running based on complex high-dynamic environmental modeling |
| CN104134353A (en) * | 2014-08-24 | 2014-11-05 | 无锡北斗星通信息科技有限公司 | Vehicle red light jaywalking detecting system |
| CN106056926A (en) * | 2016-07-18 | 2016-10-26 | 华南理工大学 | Video vehicle speed detection method based on dynamic virtual coil |
| CN106778540A (en) * | 2013-03-28 | 2017-05-31 | 南通大学 | Parking detection is accurately based on the parking event detecting method of background double layer |
| CN108765976A (en) * | 2018-06-21 | 2018-11-06 | 智慧互通科技有限公司 | The parallel parking information of trackside manages system and method |
| CN111145551A (en) * | 2020-01-03 | 2020-05-12 | 南京邮电大学 | Intersection traffic planning system based on CNN detection follows chapter rate |
| CN111275977A (en) * | 2019-08-23 | 2020-06-12 | 上海烜融信息技术服务有限公司 | System and method for monitoring red light running of vehicle |
| CN111523385A (en) * | 2020-03-20 | 2020-08-11 | 北京航空航天大学合肥创新研究院 | Stationary vehicle detection method and system based on frame difference method |
| CN112255536A (en) * | 2020-09-21 | 2021-01-22 | 山东产研鲲云人工智能研究院有限公司 | Switch fault detection method and device, electronic equipment and storage medium |
| CN112632426A (en) * | 2020-12-22 | 2021-04-09 | 新华三大数据技术有限公司 | Webpage processing method and device |
| CN113746903A (en) * | 2021-08-04 | 2021-12-03 | 广西科技师范学院 | Internet of vehicles system and method applying visible light communication |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6064319A (en) * | 1998-10-22 | 2000-05-16 | Matta; David M. | Method and system for regulating switching of a traffic light |
| WO2007112284A2 (en) * | 2006-03-24 | 2007-10-04 | Wavetronix Llc | Monitoring signalized traffic flow |
| TWI298857B (en) * | 2006-06-16 | 2008-07-11 | Chunghwa Telecom Co Ltd | |
| US7786855B2 (en) * | 2005-08-08 | 2010-08-31 | University Of Washington Through Its Center For Commercialization | Mobile system and method for traffic detector simulations |
| CN102136193A (en) * | 2011-03-10 | 2011-07-27 | 北京大学深圳研究生院 | Image feature-based virtual coil snapshot system |
| CN102142194A (en) * | 2010-12-30 | 2011-08-03 | 杭州海康威视数字技术股份有限公司 | Video detection method and system |
-
2011
- 2011-12-16 CN CN2011104217108A patent/CN102496281B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6064319A (en) * | 1998-10-22 | 2000-05-16 | Matta; David M. | Method and system for regulating switching of a traffic light |
| US7786855B2 (en) * | 2005-08-08 | 2010-08-31 | University Of Washington Through Its Center For Commercialization | Mobile system and method for traffic detector simulations |
| WO2007112284A2 (en) * | 2006-03-24 | 2007-10-04 | Wavetronix Llc | Monitoring signalized traffic flow |
| TWI298857B (en) * | 2006-06-16 | 2008-07-11 | Chunghwa Telecom Co Ltd | |
| CN102142194A (en) * | 2010-12-30 | 2011-08-03 | 杭州海康威视数字技术股份有限公司 | Video detection method and system |
| CN102136193A (en) * | 2011-03-10 | 2011-07-27 | 北京大学深圳研究生院 | Image feature-based virtual coil snapshot system |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778540B (en) * | 2013-03-28 | 2019-06-28 | 南通大学 | Parking detection is accurately based on the parking event detecting method of background double layer |
| CN106778540A (en) * | 2013-03-28 | 2017-05-31 | 南通大学 | Parking detection is accurately based on the parking event detecting method of background double layer |
| CN103218916B (en) * | 2013-04-07 | 2015-01-21 | 布法罗机器人科技（苏州）有限公司 | Method and system for detecting red light running based on complex high-dynamic environmental modeling |
| CN103218916A (en) * | 2013-04-07 | 2013-07-24 | 布法罗机器人科技（苏州）有限公司 | Method and system for detecting red light running based on complex high-dynamic environmental modeling |
| CN104134353A (en) * | 2014-08-24 | 2014-11-05 | 无锡北斗星通信息科技有限公司 | Vehicle red light jaywalking detecting system |
| CN105046980A (en) * | 2014-08-24 | 2015-11-11 | 薛青 | Detection system for red light running of vehicles |
| CN105046980B (en) * | 2014-08-24 | 2017-04-12 | 苏建福 | Detection system for red light running of vehicles |
| CN106056926B (en) * | 2016-07-18 | 2021-07-30 | 华南理工大学 | Video vehicle speed detection method based on dynamic virtual coil |
| CN106056926A (en) * | 2016-07-18 | 2016-10-26 | 华南理工大学 | Video vehicle speed detection method based on dynamic virtual coil |
| CN108765976A (en) * | 2018-06-21 | 2018-11-06 | 智慧互通科技有限公司 | The parallel parking information of trackside manages system and method |
| CN108765976B (en) * | 2018-06-21 | 2020-09-25 | 智慧互通科技有限公司 | Roadside parallel parking information management system and method |
| CN111275977A (en) * | 2019-08-23 | 2020-06-12 | 上海烜融信息技术服务有限公司 | System and method for monitoring red light running of vehicle |
| CN111145551A (en) * | 2020-01-03 | 2020-05-12 | 南京邮电大学 | Intersection traffic planning system based on CNN detection follows chapter rate |
| CN111523385A (en) * | 2020-03-20 | 2020-08-11 | 北京航空航天大学合肥创新研究院 | Stationary vehicle detection method and system based on frame difference method |
| CN111523385B (en) * | 2020-03-20 | 2022-11-04 | 北京航空航天大学合肥创新研究院 | Stationary vehicle detection method and system based on frame difference method |
| CN112255536A (en) * | 2020-09-21 | 2021-01-22 | 山东产研鲲云人工智能研究院有限公司 | Switch fault detection method and device, electronic equipment and storage medium |
| CN112255536B (en) * | 2020-09-21 | 2023-05-26 | 山东产研鲲云人工智能研究院有限公司 | Switch fault detection method and device, electronic equipment and storage medium |
| CN112632426A (en) * | 2020-12-22 | 2021-04-09 | 新华三大数据技术有限公司 | Webpage processing method and device |
| CN112632426B (en) * | 2020-12-22 | 2022-08-30 | 新华三大数据技术有限公司 | Webpage processing method and device |
| CN113746903A (en) * | 2021-08-04 | 2021-12-03 | 广西科技师范学院 | Internet of vehicles system and method applying visible light communication |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102496281B (en) | 2013-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102496281B (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
| US9704060B2 (en) | Method for detecting traffic violation | |
| CN105426864B (en) | One kind being based on the matched Multi-lane Lines Detection method of equidistant marginal point | |
| CN102722982B (en) | Based on wagon flow and the motion state detection method thereof of background and inter-frame difference algorithm | |
| CN103236160B (en) | Road network traffic condition monitoring system based on video image processing technology | |
| CN103522970B (en) | Based on vehicle driving safety method of inspection and the system of machine vision | |
| CN102324183B (en) | Method for detecting and shooting vehicle based on composite virtual coil | |
| CN102426785B (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
| CN107392103A (en) | The detection method and device of road surface lane line, electronic equipment | |
| CN106297278A (en) | A kind of method and system shedding thing vehicle for inquiry | |
| CN103050008B (en) | Method for detecting vehicles in night complex traffic videos | |
| CN101567097B (en) | Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof | |
| CN101656023A (en) | Management method of indoor car park in video monitor mode | |
| CN101872546A (en) | Video-based method for rapidly detecting transit vehicles | |
| CN105575125A (en) | Vehicle flow video detection and analysis system | |
| CN104123776B (en) | A kind of object statistical method based on image and system | |
| CN105513349A (en) | Double-perspective learning-based mountainous area highway vehicle event detection method | |
| CN104063882A (en) | Vehicle video speed measuring method based on binocular camera | |
| CN110298300A (en) | A method of detection vehicle violation crimping | |
| EP2813973B1 (en) | Method and system for processing video image | |
| CN104506800A (en) | Scene synthesis and comprehensive monitoring method and device for electronic police cameras in multiple directions | |
| CN103794050A (en) | Real-time transport vehicle detecting and tracking method | |
| CN103366581A (en) | Traffic flow counting device and counting method | |
| CN114781479A (en) | Traffic incident detection method and device | |
| CN111523385B (en) | Stationary vehicle detection method and system based on frame difference method |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201123 Address after: 226000 Jiangsu city of Nantong province Gangzha Xingtai Road No. 18 Patentee after: Nantong Yuanyuan Network Technology Co.,Ltd. Address before: 412007 Zhuzhou Research Institute, Hunan University of Technology, 88 West Taishan Road, Tianyuan District, Hunan Patentee before: HUNAN University OF TECHNOLOGY |