CN105389991A - Self-adaptive snapshot method for behavior of running red light - Google Patents
Self-adaptive snapshot method for behavior of running red light Download PDFInfo
- Publication number
- CN105389991A CN105389991A CN201510882078.5A CN201510882078A CN105389991A CN 105389991 A CN105389991 A CN 105389991A CN 201510882078 A CN201510882078 A CN 201510882078A CN 105389991 A CN105389991 A CN 105389991A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- tail
- light
- night
- adaptive
- 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
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a self-adaptive snapshot method for a behavior of running the red light. The method comprises the following steps that snapshot rule parameters for the behavior of running the red light are set; a video image of a monitored area is obtained; whether the present video image belongs to daytime or night is determined; and snapshot is implemented. According to a night tracking mode provided by the invention, license plate identification is implemented after pairing of vehicle taillight, and the confidence that the taillight belongs to the same vehicle is improved; and at the same time, features of the vehicle are not obvious at night, taillight tracking replaces vehicle tracking, so that snapshot for the behavior of running the red light can be more accurate.
Description
Technical field
The present invention relates to Intelligent Video Surveillance Technology, particularly relate to a kind of adaptive Jaywalking snapshot method.
Background technology
Intelligent transportation system (Intelligenttrafficsystem), by the science and technology (infotech, computer technology, data communication technology, sensor technology, electron controls technology, Theory of Automatic Control, operational research, artificial intelligence etc.) of advanced person effectively integrated use in communications and transportation, Service controll and Rail car manufacture, strengthen vehicle, contact between road and user three, thus formed a kind ofly to ensure safety, raise the efficiency, the comprehensive transportation system of environmental protect, economize energy.
In recent years, along with the raising of China's vehicle guaranteeding organic quantity, traffic safety problem to become in socio-economic development important restraining factors day by day, application in intelligent transportation system is dredged in airport, track passenger flow, the scheduling of urban transportation intelligent scheduling, express highway intelligent, vehicle in use management and running and motor vehicle control automatically etc., the contradiction effectively can alleviated day by day busy traffic service management and perform between police strength wretched insufficiency, therefore obtains many concerns of researchist.But due to open-air conditions more complicated, by the impact that weather conditions, season, road section traffic volume flow are different, each crossing is different in the situation of different time points, therefore that propose a set of robust, real-time method for supervising, self-adapting intelligent traffic system faced by the various time periods, weather condition and stream of people's vehicle flowrate crossing situation, become the technical matters needing solution badly.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of adaptive Jaywalking snapshot method, the accuracy of can make a dash across the red light accurately to daytime period and night-time hours respectively candid photograph, raising vehicle tracking.
The technical scheme that technical solution problem of the present invention adopts is:
A kind of adaptive Jaywalking snapshot method, comprises the following steps:
1) the candid photograph parameter of regularity that makes a dash across the red light is set;
2) video image of area to be monitored is obtained;
3) judge that current video image is daytime period or night-time hours;
4) capture accordingly according to the judged result of step 3).
While employing technique scheme, the present invention can also adopt or combine and adopt following further technical scheme:
Described candid photograph parameter of regularity comprises vehicle detection district, track, stop line, craspedodrome candid photograph line, turns left to capture line, turns right and capture line and vehicle tracking district, and described candid photograph parameter of regularity is for setting candid photograph rule.
Described step 2) be the video image that the web camera of Real-time Obtaining area to be monitored transmits, open situation and system time according to brightness of image, tail-light, comprehensive descision current video image is daytime period or night-time hours.
Described step 2) specifically comprise:
2.1) add up brightness in current video image, lower than the pixel count of certain threshold value, to calculate the ratio of total pixel number in current video image, if this ratio is greater than certain threshold value, then think night-time hours, otherwise carry out next step; Because night lights affects, the mean flow rate of image can not the difference of accurate description daytime and Night, and the absolute brightness of the part that light does not cover can describe the difference at daytime and night better, therefore adopt in image compared with the basis for estimation one of of the statistics of the pixel of dark-part as daytime and Night.
2.2) tailstock detecting device is used to detect the vehicle crossing stop line, detect the unlatching situation of these vehicle tail-lights, the vehicle number crossing stop line if current is greater than 5, and the tail-light of 80% is all opened, then think night-time hours, otherwise carry out next step judgement;
2.3) according to current time and the artificially daytime period of setting and the comparison of night-time hours, final judgement is daytime period or night-time hours.Due to current time with artificially arrange and there is certain uncertainty, if can by the judgement of step 2.1 or step 2.2 obtain result data can than artificial arrange more accurate, but when step 2.1 and step 2.2 all cannot obtain accurate result, by the system time that artificially arranges as judgment mode of revealing all the details.
Described step 2.2) in the detecting step of tail-light comprise:
2.2.1) the exceedingly popular pixel of crossing stop line is calculated, the decision rule of exceedingly popular pixel is: R>G+50 & & R>B+50 & & R>150 & & G<100 & & B<100, wherein R, G, B are respectively the rgb value component of pixel, and & & represents and satisfies condition simultaneously;
2.2.2) carry out expansion and cavity filling, some undetected pixels of periphery are comprised to come in;
2.2.3) connected region is used to find independently tail-light;
2.2.4) in the target frame of vehicle, match according to tail-light size and position, obtain final tail-light pair.
In described step 4), if judged result is daytime period, then corresponding grasp shoot method specifically comprises:
4.1) in vehicle detection district, subtract each other with present frame gray image and previous frame gray level image, after binaryzation, obtain foreground picture, if prospect ratio is greater than certain threshold value, then start tailstock detecting device;
4.2) in the vehicle target that tailstock detecting device detects, identify car plate, after finding car plate, using the initial tracking box of image corresponding for the vehicle target frame of correspondence as tracker, the tracking parameter of initialization simultaneously, follows the tracks of vehicle by meanshift method;
4.3) be positioned at the diverse location of image according to vehicle, according to the scale down self-adaptative adjustment vehicle size in track, and when each adjustment, reinitialize tracking parameter according to the size of Current vehicle and position;
4.4) capture according to relatively the make a dash across the red light relative position of regular line of vehicle, the image of candid photograph all comprises the signal lamp state that clear and legible information of vehicles, license board information and vehicle travel behavior.
In described step 4), if judged result is night-time hours, then corresponding grasp shoot method specifically comprises:
5.1) in vehicle detection district, inspection vehicle taillight, matches according to the size of tail-light and position;
5.2) according to the relative position relation of tail-light and car plate, toward extending out, identifying car plate, after finding car plate, thinking that this tail-light is to belonging to same car within the scope of this, the right pursuit path of this tail-light represents corresponding vehicle;
5.3) utilize Distance geometry similarity to follow the tracks of tail-light, obtain the pursuit path of tail-light;
5.4) capture according to relatively the make a dash across the red light relative position of regular line of tail-light, two tail-lights wherein any one satisfied candid photograph requirement that a car is corresponding, just think and meet candid photograph condition of making a dash across the red light, the image of candid photograph all comprises the signal lamp state that clear and legible information of vehicles, license board information and vehicle travel behavior.
In described step 5.4) in, described in make a dash across the red light regular line comprise stop line, keep straight on capture line, turn left capture line, turn right capture line.
The invention has the beneficial effects as follows: the present invention is by Intelligent Measurement and analyze current scene, realize to daytime and night road vehicle to make a dash across the red light accurately candid photograph, improving in meadshift target tracking algorism cannot the problem of self-adaptative adjustment vehicle size, improves vehicle tracking accuracy.The present invention has following innovation:
1, the statistical nature opened of the statistical nature of combining image brightness, tail-light and system time comprehensive descision day mode or Night, compare artificial setting and additive method, can more robust, change day mode and Night exactly.
2, the tracing mode on daytime that proposes of the present invention, according to lane information self-adaptative adjustment vehicle size, and real-time adjustment meanshift tracking parameter, solving that meanshift follows the tracks of cannot the problem of adaptive tracing target sizes.
3, the tracing mode at night of the present invention's proposition, after tail-light pairing, adds Car license recognition, strengthen the degree of confidence that tail-light belongs to same car, meanwhile, because vehicle is not obvious in the feature at night, follow the tracks of with tail-light and substitute vehicle tracking, candid photograph of making a dash across the red light can be carried out more accurately.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention.
Embodiment
With reference to accompanying drawing.
The adaptive Jaywalking snapshot method of one of the present invention comprises the following steps:
Steps A: arranging makes a dash across the red light captures rule, comprising: vehicle detection district, track, stop line, craspedodrome are captured line, turn left to capture line, turned right and capture line and vehicle tracking district.
Step B: the video image of the web camera transmission of Real-time Obtaining traffic intersection, open situation and system time according to brightness of image, tail-light, comprehensive descision is current is in daytime period or night-time hours;
1, in statistical picture brightness lower than 20 pixel count, calculate the ratio with image total pixel number, if this ratio is greater than 0.2, then think night-time hours, otherwise carry out next step to judge, because night lights affects, the mean flow rate of image can not the difference of accurate description daytime and Night, and the absolute brightness of the part that light does not cover can describe the difference at daytime and night better, so, adopt in image compared with the basis for estimation one of of the statistics of the pixel of dark-part as daytime and Night;
2, tail-light detecting device is used to detect the vehicle crossing stop line, detect the unlatching situation of these vehicle tail-lights, the vehicle number crossing stop line if current is greater than 5, and the tail-light of 80% is all opened, then think night-time hours, otherwise carry out next step judgement;
The detecting step of tail-light detecting device is:
First, calculate the exceedingly popular pixel of crossing stop line, the decision rule of exceedingly popular pixel is: R>G+50 & & R>B+50 & & R>150 & & G<100 & & B<100, wherein R, G, B are respectively the rgb value component of pixel, and & & represents and satisfies condition simultaneously;
Then, carry out expansion and cavity filling, some undetected pixels of periphery are comprised to come in;
Again, connected region is used to find independently tail-light;
Finally, in the target frame of vehicle, match according to tail-light size and position, obtain final tail-light pair.
3, according to current time and the artificially daytime period of setting and the comparison of night-time hours, final judgement is daytime period or night-time hours.
Step C: if judged result is daytime period, then corresponding grasp shoot method specifically comprises:
1, in vehicle detection district, subtract each other with present frame gray image and previous frame gray level image, after binaryzation, obtain foreground picture, if prospect ratio is greater than 0.05, then start tailstock detecting device.
2, in the vehicle target that tailstock detecting device detects by car plate detecting device identification car plate, after finding car plate, using the initial tracking box of image corresponding for the vehicle target frame of correspondence as tracker, the tracking parameter of initialization simultaneously, vehicle is followed the tracks of by meanshift method, concrete, parking space detector and car plate detecting device are the svm sorter based on haar special medical treatment.
3, be positioned at the diverse location of image according to vehicle, according to the scale down self-adaptative adjustment vehicle size in track, and when each adjustment, reinitialize tracking parameter according to the size of Current vehicle and position.
4, capture according to relatively the make a dash across the red light relative position of regular line of vehicle, the image of candid photograph all comprises the signal lamp state that clear and legible information of vehicles, license board information and vehicle travel behavior.
Step D: if judged result is night-time hours, then corresponding grasp shoot method specifically comprises:
1, in vehicle detection district, inspection vehicle taillight, matches according to the size of tail-light and position;
2, car plate detecting device identification car plate is passed through according to the relative position relation of tail-light and car plate, after finding car plate, think that this tail-light is to belonging to same car, the right pursuit path of this tail-light represents corresponding vehicle, concrete, car plate detecting device is the svm sorter based on haar.
3, utilize Distance geometry similarity to follow the tracks of tail-light, obtain the pursuit path of tail-light;
4, capture according to relatively the make a dash across the red light relative position of regular line of tail-light, two tail-lights wherein any one satisfied candid photograph requirement that a car is corresponding, just think and meet candid photograph condition of making a dash across the red light, the image of candid photograph all comprises the signal lamp state that clear and legible information of vehicles, license board information and vehicle travel behavior.
The described regular line that makes a dash across the red light comprises stop line, line is captured in craspedodrome, the candid photograph line that turns left, candid photograph line of turning right.
Claims (8)
1. an adaptive Jaywalking snapshot method, is characterized in that: comprise the following steps:
1) the candid photograph parameter of regularity that makes a dash across the red light is set;
2) video image of area to be monitored is obtained;
3) judge that current video image is daytime period or night-time hours;
4) capture accordingly according to the judged result of step 3).
2. a kind of adaptive Jaywalking snapshot method as claimed in claim 1, it is characterized in that: described candid photograph parameter of regularity comprises vehicle detection district, track, stop line, craspedodrome candid photograph line, turns left to capture line, turns right and capture line and vehicle tracking district, and described candid photograph parameter of regularity is for setting candid photograph rule.
3. a kind of adaptive Jaywalking snapshot method as claimed in claim 1, it is characterized in that: described step 2) be the video image that the web camera of Real-time Obtaining area to be monitored transmits, open situation and system time according to brightness of image, tail-light, comprehensive descision current video image is daytime period or night-time hours.
4. a kind of adaptive Jaywalking snapshot method as claimed in claim 3, is characterized in that: described step 2) specifically comprise:
2.1) add up brightness in current video image, lower than the pixel count of certain threshold value, to calculate the ratio of total pixel number in this pixel count and current video image, if this ratio is greater than certain threshold value, then think night-time hours, otherwise carry out next step;
2.2) tailstock detecting device is used to detect the vehicle crossing stop line, detect the unlatching situation of these vehicle tail-lights, the vehicle number crossing stop line if current is greater than 5, and the tail-light of 80% is all opened, then think night-time hours, otherwise carry out next step judgement;
2.3) according to current time and the artificially daytime period of setting and the comparison of night-time hours, final judgement is daytime period or night-time hours.
5. a kind of adaptive Jaywalking snapshot method as claimed in claim 4, is characterized in that: described step 2.2) in the detecting step of tail-light comprise:
2.2.1) the exceedingly popular pixel of crossing stop line is calculated, the decision rule of exceedingly popular pixel is: R>G+50 & & R>B+50 & & R>150 & & G<100 & & B<100, wherein R, G, B are respectively the rgb value component of pixel, and & & represents and satisfies condition simultaneously;
2.2.2) carry out expansion and cavity filling, some undetected pixels of periphery are comprised to come in;
2.2.3) connected region is used to find independently tail-light;
2.2.4) in the target frame of vehicle, match according to tail-light size and position, obtain final tail-light pair.
6. a kind of adaptive Jaywalking snapshot method as claimed in claim 1, is characterized in that: in described step 4), if judged result is daytime period, then corresponding grasp shoot method specifically comprises:
4.1) in vehicle detection district, subtract each other with present frame gray image and previous frame gray level image, after binaryzation, obtain foreground picture, if prospect ratio is greater than certain threshold value, then start tailstock detecting device;
4.2) in the vehicle target that tailstock detecting device detects, identify car plate, after finding car plate, using the initial tracking box of image corresponding for the vehicle target frame of correspondence as tracker, the tracking parameter of initialization simultaneously, follows the tracks of vehicle by meanshift method;
4.3) be positioned at the diverse location of image according to vehicle, according to the scale down self-adaptative adjustment vehicle size in track, and when each adjustment, reinitialize tracking parameter according to the size of Current vehicle and position;
4.4) capture according to relatively the make a dash across the red light relative position of regular line of vehicle, the image of candid photograph all comprises the signal lamp state that clear and legible information of vehicles, license board information and vehicle travel behavior.
7. a kind of adaptive Jaywalking snapshot method as claimed in claim 1, is characterized in that: in described step 4), if judged result is night-time hours, then corresponding grasp shoot method specifically comprises:
5.1) in vehicle detection district, inspection vehicle taillight, matches according to the size of tail-light and position;
5.2) according to the relative position relation identification car plate of tail-light and car plate, after finding car plate, think that this tail-light is to belonging to same car, the right pursuit path of this tail-light represents corresponding vehicle;
5.3) utilize Distance geometry similarity to follow the tracks of tail-light, obtain the pursuit path of tail-light;
5.4) capture according to relatively the make a dash across the red light relative position of regular line of tail-light, two tail-lights wherein any one satisfied candid photograph requirement that a car is corresponding, just think and meet candid photograph condition of making a dash across the red light, the image of candid photograph all comprises the signal lamp state that clear and legible information of vehicles, license board information and vehicle travel behavior.
8. a kind of adaptive Jaywalking snapshot method as claimed in claim 7, is characterized in that: in described step 5.4) in, described in make a dash across the red light regular line comprise stop line, keep straight on capture line, turn left capture line, turn right capture line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510882078.5A CN105389991B (en) | 2015-12-03 | 2015-12-03 | A kind of adaptive Jaywalking snapshot method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510882078.5A CN105389991B (en) | 2015-12-03 | 2015-12-03 | A kind of adaptive Jaywalking snapshot method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105389991A true CN105389991A (en) | 2016-03-09 |
| CN105389991B CN105389991B (en) | 2017-12-15 |
Family
ID=55422229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510882078.5A Active CN105389991B (en) | 2015-12-03 | 2015-12-03 | A kind of adaptive Jaywalking snapshot method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105389991B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894822A (en) * | 2016-06-24 | 2016-08-24 | 桂林金铱星科技发展有限公司 | Automatic capture system |
| CN110009913A (en) * | 2019-03-27 | 2019-07-12 | 江苏智通交通科技有限公司 | A kind of non-at-scene law enforcement picture intelligent checks method and system of vehicles running red light |
| CN111652143A (en) * | 2020-06-03 | 2020-09-11 | 浙江大华技术股份有限公司 | Vehicle detection method and device and computer storage medium |
| CN111968378A (en) * | 2020-07-07 | 2020-11-20 | 浙江大华技术股份有限公司 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CZ20032279A3 (en) * | 2001-01-26 | 2004-01-14 | Raytheon Company | System and method for reading license plates |
| CN101034005A (en) * | 2007-04-12 | 2007-09-12 | 上海交通大学 | Switching method between videos for detecting vehicles during day-night |
| CN101064062A (en) * | 2006-04-26 | 2007-10-31 | 刘业兴 | Automatic monitoring system for vehicle illegal turning and left turning |
| CN101216996A (en) * | 2007-12-28 | 2008-07-09 | 云南澜博科技有限公司 | A method for monitoring vehicle offences by video |
| CN101383096A (en) * | 2008-09-23 | 2009-03-11 | 青岛海信电子产业控股股份有限公司 | Video vehicle detection mode selecting method and device |
| TW200915240A (en) * | 2007-09-27 | 2009-04-01 | Univ Nat Yunlin Sci & Tech | Intelligent vehicle surveillance, video recording and search system |
| KR101038669B1 (en) * | 2009-06-15 | 2011-06-02 | (주) 알티솔루션 | The automatic vehicle identification system of non-trigger type based on image processing and that of using identification method |
| CN102280030A (en) * | 2011-07-20 | 2011-12-14 | 杭州海康威视软件有限公司 | Method and system for detecting vehicle at night |
| CN102332209A (en) * | 2011-02-28 | 2012-01-25 | 王志清 | Automobile violation video monitoring method |
| CN102768799A (en) * | 2011-12-21 | 2012-11-07 | 湖南工业大学 | Method for detecting red light running of vehicle at night |
| CN103020948A (en) * | 2011-09-28 | 2013-04-03 | 中国航天科工集团第二研究院二○七所 | Night image characteristic extraction method in intelligent vehicle-mounted anti-collision pre-warning system |
-
2015
- 2015-12-03 CN CN201510882078.5A patent/CN105389991B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CZ20032279A3 (en) * | 2001-01-26 | 2004-01-14 | Raytheon Company | System and method for reading license plates |
| CN101064062A (en) * | 2006-04-26 | 2007-10-31 | 刘业兴 | Automatic monitoring system for vehicle illegal turning and left turning |
| CN101034005A (en) * | 2007-04-12 | 2007-09-12 | 上海交通大学 | Switching method between videos for detecting vehicles during day-night |
| TW200915240A (en) * | 2007-09-27 | 2009-04-01 | Univ Nat Yunlin Sci & Tech | Intelligent vehicle surveillance, video recording and search system |
| CN101216996A (en) * | 2007-12-28 | 2008-07-09 | 云南澜博科技有限公司 | A method for monitoring vehicle offences by video |
| CN101383096A (en) * | 2008-09-23 | 2009-03-11 | 青岛海信电子产业控股股份有限公司 | Video vehicle detection mode selecting method and device |
| KR101038669B1 (en) * | 2009-06-15 | 2011-06-02 | (주) 알티솔루션 | The automatic vehicle identification system of non-trigger type based on image processing and that of using identification method |
| CN102332209A (en) * | 2011-02-28 | 2012-01-25 | 王志清 | Automobile violation video monitoring method |
| CN102280030A (en) * | 2011-07-20 | 2011-12-14 | 杭州海康威视软件有限公司 | Method and system for detecting vehicle at night |
| CN103020948A (en) * | 2011-09-28 | 2013-04-03 | 中国航天科工集团第二研究院二○七所 | Night image characteristic extraction method in intelligent vehicle-mounted anti-collision pre-warning system |
| CN102768799A (en) * | 2011-12-21 | 2012-11-07 | 湖南工业大学 | Method for detecting red light running of vehicle at night |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894822A (en) * | 2016-06-24 | 2016-08-24 | 桂林金铱星科技发展有限公司 | Automatic capture system |
| CN110009913A (en) * | 2019-03-27 | 2019-07-12 | 江苏智通交通科技有限公司 | A kind of non-at-scene law enforcement picture intelligent checks method and system of vehicles running red light |
| WO2020192122A1 (en) * | 2019-03-27 | 2020-10-01 | 江苏智通交通科技有限公司 | Off-site law enforcement picture intelligent auditing method and system for vehicles running red light |
| CN110009913B (en) * | 2019-03-27 | 2021-06-01 | 江苏智通交通科技有限公司 | Intelligent checking method and system for off-site law enforcement picture of vehicle running red light |
| CN111652143A (en) * | 2020-06-03 | 2020-09-11 | 浙江大华技术股份有限公司 | Vehicle detection method and device and computer storage medium |
| CN111652143B (en) * | 2020-06-03 | 2023-09-29 | 浙江大华技术股份有限公司 | Vehicle detection method and device and computer storage medium |
| CN111968378A (en) * | 2020-07-07 | 2020-11-20 | 浙江大华技术股份有限公司 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105389991B (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101872546B (en) | Video-based method for rapidly detecting transit vehicles | |
| CN103871079B (en) | Wireless vehicle tracking based on machine learning and light stream | |
| CN109703460B (en) | Multi-camera complex scene self-adaptive vehicle collision early warning device and early warning method | |
| CN101656023B (en) | Management method of indoor car park in video monitor mode | |
| CN102496285B (en) | Method for determining red-light running of vehicles at intersection based on video detection and signal control system | |
| CN106485927A (en) | A kind of intelligent transportation violation information harvester and acquisition method | |
| CN102074113B (en) | License tag recognizing and vehicle speed measuring method based on videos | |
| CN101739827B (en) | Vehicle detecting and tracking method and device | |
| CN102968625B (en) | Ship distinguishing and tracking method based on trail | |
| CN104537841A (en) | Unlicensed vehicle violation detection method and detection system thereof | |
| CN202422425U (en) | Video-detection-based intelligent signal control system for crossing | |
| CN105389991A (en) | Self-adaptive snapshot method for behavior of running red light | |
| CN106218492B (en) | A kind of night running light automatic switching control equipment and switching method | |
| CN105718923B (en) | A kind of vehicle detection at night and method of counting based on inverse projection figure | |
| CN104464305A (en) | Intelligent vehicle converse driving detecting device and method | |
| CN102897086A (en) | Back car driving information detecting and prompting method and system | |
| CN103325258A (en) | Red light running detecting device and method based on video processing | |
| CN205768952U (en) | Night intelligence auxiliary driving device | |
| CN114781479A (en) | Traffic incident detection method and device | |
| CN109887276B (en) | Night traffic jam detection method based on fusion of foreground extraction and deep learning | |
| CN102496281A (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
| CN110516600A (en) | A kind of bus passenger flow detection method based on Face datection | |
| CN103778790B (en) | A kind of vehicle flowrate square wave statistic law based on video sequence | |
| CN114708533A (en) | Target tracking method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |