CN105389991B - A kind of adaptive Jaywalking snapshot method - Google Patents
A kind of adaptive Jaywalking snapshot method Download PDFInfo
- Publication number
- CN105389991B CN105389991B CN201510882078.5A CN201510882078A CN105389991B CN 105389991 B CN105389991 B CN 105389991B CN 201510882078 A CN201510882078 A CN 201510882078A CN 105389991 B CN105389991 B CN 105389991B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- tail
- light
- night
- line
- 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.)
- Active
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
Abstract
The present invention provides a kind of adaptive Jaywalking snapshot method, comprises the following steps：Setting, which is made a dash across the red light, captures parameter of regularity；Obtain the video image of area to be monitored；It is daytime period or night-time hours to judge current video image；Captured.Night tracing mode proposed by the present invention, after tail-light pairing, add Car license recognition, the confidence level that tail-light belongs to same car is strengthened, simultaneously as feature unobvious of the vehicle at night, tracked with tail-light and substitute vehicle tracking, can more accurately carry out candid photograph of making a dash across the red light.
Description
Technical field
The present invention relates to intelligent Video Surveillance Technology, more particularly to a kind of adaptive Jaywalking snapshot method.
Background technology
Intelligent transportation system (Intelligent traffic system), by advanced scientific and technical (information technology, meter
Calculation machine technology, data communication technology, sensor technology, electron controls technology, Theory of Automatic Control, operational research, artificial intelligence etc.)
Effectively integrated use strengthens the connection between vehicle, road and user three in communications and transportation, Service controll and vehicle manufacture
System, so as to form a kind of comprehensive transportation system for ensuring safety, improving efficiency, improving environment, save the energy.
In recent years, as the raising of China's vehicle guaranteeding organic quantity, traffic safety problem are had become in socio-economic development
One important restraining factors, intelligent transportation system is on airport, track passenger flow is dredged, urban transportation intelligent scheduling, highway
The application that intelligent scheduling, vehicle in use management and running and motor vehicle automatically control etc., can effectively alleviate increasingly busy
Contradiction between traffic service management and execution police strength wretched insufficiency, therefore obtain many concerns of researcher.But due to
Open-air conditions are more complicated, and by weather conditions, season, road section traffic volume flow is different is influenceed, and each crossing is in different time points
Situation it is different, therefore propose a set of robust, real-time monitoring method, self-adapting intelligent traffic system faced it is various when
Between section, weather condition and stream of people's vehicle flowrate crossing situation, turn into the technical problem of urgent need to resolve.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of adaptive Jaywalking snapshot method, can distinguish dialogue
Its period and night-time hours carry out candid photograph of accurately making a dash across the red light, and improve the degree of accuracy of vehicle tracking.
The technical proposal for solving the technical problem of the invention is：
A kind of adaptive Jaywalking snapshot method, comprises the following steps：
1) set to make a dash across the red light and capture parameter of regularity；
2) video image of area to be monitored is obtained；
3) it is daytime period or night-time hours to judge current video image；
4) captured accordingly according to the judged result of step 3).
While using above-mentioned technical proposal, the present invention can also be used or combined using technology further below
Scheme：
The candid photograph parameter of regularity captures line including vehicle detection area, track, stop line, straight trip, turns left to capture line, right-hand rotation
Line and vehicle tracking area are captured, the candid photograph parameter of regularity, which is used to set, captures rule.
The step 2) is the video image of the real-time web camera transmission for obtaining area to be monitored, and the step 3) is
It it is daytime period or night according to brightness of image, tail-light unlatching situation and system time, comprehensive descision current video image
Between the period.
The step 3) specifically includes：
3.1) pixel count that brightness in current video image is less than certain threshold value is counted, calculates total picture in current video image
The ratio of prime number, if the ratio is more than certain threshold value, then it is assumed that be night-time hours, otherwise carry out in next step；Because night lamp
Shadow rings, and the mean flow rate of image is unable to the difference of accurate description daytime and Night, and the part that light does not cover
Absolute brightness can preferably describe the difference at daytime and night, therefore be made using the statistics of the pixel in image compared with dark-part
For one of basis for estimation of daytime and Night.
3.2) vehicle of stop line is crossed using the detection of tailstock detector, detects the unlatching situation of these vehicle tail-lights,
If the vehicle number for currently crossing stop line is more than 5, and 80% tail-light is opened, then it is assumed that it is night-time hours, it is no
Then carry out next step judgement；
3.3) comparison of the daytime period and night-time hours that are set according to current time and artificially, when final judgement is daytime
Section or night-time hours.Because certain uncertainty be present in current time and artificial setting, if it is possible to by step 3.1 or
The data that the judgement of person's step 3.2 obtains result can be more more accurate than what is artificially set, but in step 3.1 and the equal nothing of step 3.2
When method obtains accurate result, judgment mode of revealing all the details is used as by the system time artificially set.
The detecting step of tail-light includes in the step 3.2)：
3.2.1 the exceedingly popular pixel for 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 is respectively that the rgb value component , ＆＆ of pixel is represented while met condition；
3.2.2 expansion and cavity filling) are carried out, the pixel of some missing inspections of periphery is included；
3.2.3 independent tail-light) is found using connected region；
3.2.4) in the target frame of vehicle, matched according to tail-light size and location, obtain final tail-light
It is right.
In the step 4), if a determination be made that daytime period, then corresponding grasp shoot method specifically includes：
4.1) in vehicle detection area, subtracted each other with present frame gray image and previous frame gray level image, obtained after binaryzation
Foreground picture, if prospect ratio is more than certain threshold value, start tailstock detector；
4.2) car plate is identified in the vehicle target that tailstock detector detects, after finding car plate, by corresponding vehicle mesh
Initial tracking box of the image as tracker corresponding to frame is marked, while initializes tracking parameter, car is tracked with meanshift methods
；
4.3) it is located at the diverse location of image according to vehicle, vehicle size is adaptively adjusted according to the diminution ratio in track,
And when adjustment every time, tracking parameter is reinitialized according to the size and location of Current vehicle；
4.4) captured according to the relative position of the relative regular line that makes a dash across the red light of vehicle, the image of candid photograph, which includes, clearly may be used
The signal lamp state of information of vehicles, license board information and the vehicle traveling behavior distinguished.
In the step 4), if a determination be made that night-time hours, then corresponding grasp shoot method specifically includes：
5.1) in vehicle detection area, tail-light is detected, is matched according to the size and location of tail-light；
5.2) according to tail-light and the relative position relation of car plate, toward extending out, car plate is identified in the range of this, finds car
Bridge queen, it is believed that the tail-light represents corresponding vehicle to belonging to same car, the pursuit path of the tail-light pair；
5.3) using distance and similarity tracking tail-light, the pursuit path of tail-light is obtained；
5.4) captured according to the relative position of the relative regular line that makes a dash across the red light of tail-light, two tailstock corresponding to a car
Any one in lamp, which meets to capture, to be required, is considered as meeting candid photograph condition of making a dash across the red light, the image of candid photograph is comprising clear and legible
The signal lamp state of information of vehicles, license board information and vehicle traveling behavior.
In the step 5.4), the regular line that makes a dash across the red light includes stop line, line is captured in straight trip, turns left to capture line and the right side
Turn to capture line.
The beneficial effects of the invention are as follows：The present invention, with analyzing current scene, is realized to daytime and night by Intelligent Measurement
Between road vehicle accurately make a dash across the red light candid photograph, car can not adaptively be adjusted by improving in meadshift target tracking algorisms
The problem of size, improve the vehicle tracking degree of accuracy.The present invention has following innovation：1st, the statistical nature with reference to brightness of image,
Tail-light open statistical nature and system time comprehensive descision day mode or Night, compare be manually set and its
His method, can more robust, change day mode and Night exactly.
2nd, tracing mode on daytime proposed by the present invention, vehicle size is adaptively adjusted according to lane information, and adjusted in real time
Meanshift tracking parameters, solve the problems, such as that meanshift tracking can not adaptive tracing target sizes.
3rd, night tracing mode proposed by the present invention, after tail-light pairing, Car license recognition is added, strengthens the tailstock
Lamp belongs to the confidence level of same car, simultaneously as feature unobvious of the vehicle at night, tracked with tail-light substitute vehicle with
Track, it can more accurately carry out candid photograph of making a dash across the red light.
Brief description of the drawings
Fig. 1 is the flow chart of the present invention.
Embodiment
Referring to the drawings.
A kind of adaptive Jaywalking snapshot method of the present invention comprises the following steps：
Step A：Setting, which is made a dash across the red light, captures rule, including：Vehicle detection area, track, stop line, straight trip are captured line, turned left
Line is captured, turns right and captures line and vehicle tracking area.
Step B：The video image of the web camera transmission of traffic intersection is obtained in real time, according to brightness of image, tail-light
Unlatching situation and system time, comprehensive descision are currently at daytime period or night-time hours；
1st, brightness is less than 20 pixel count in statistical picture, the ratio with image total pixel number is calculated, if the ratio is big
In 0.2, then it is assumed that be night-time hours, otherwise carry out next step judgement, because night lights influence, the mean flow rate of image can not
Accurate description daytime and the difference of Night, and the absolute brightness for the part that light does not cover can preferably describe daytime and
The difference at night, so, using in image compared with dark-part pixel statistics as daytime and Night judgement according to
One of according to；
2nd, the vehicle of stop line is crossed using the detection of tail-light detector, detects the unlatching situation of these vehicle tail-lights,
If the vehicle number for currently crossing stop line is more than 5, and 80% tail-light is opened, then it is assumed that it is night-time hours, it is no
Then carry out next step judgement；
The detecting step of tail-light detector is：
First, the exceedingly popular pixel for 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 is respectively that the rgb value component , ＆＆ of pixel is represented while met condition；
Then, expansion and cavity filling are carried out, the pixel of some missing inspections of periphery is included；
Again, independent tail-light is found using connected region；
Finally, in the target frame of vehicle, matched according to tail-light size and location, obtain final tail-light
It is right.
3rd, the comparison of the daytime period and night-time hours that are set according to current time and artificially, it is final to judge it is daytime period
Or night-time hours.
Step C：If a determination be made that daytime period, then corresponding grasp shoot method specifically includes：
1st, in vehicle detection area, subtracted each other with present frame gray image and previous frame gray level image, before being obtained after binaryzation
Jing Tu, if prospect ratio is more than 0.05, start tailstock detector.
2nd, car plate is identified by car plate detection device in the vehicle target that tailstock detector detects, will after finding car plate
Initial tracking box of the image as tracker corresponding to corresponding vehicle target frame, while tracking parameter is initialized, use
Meanshift methods track vehicle, specifically, parking space detector and car plate detection device are the svm graders based on haar special medical treatments.
3rd, it is located at the diverse location of image according to vehicle, vehicle size is adaptively adjusted according to the diminution ratio in track, and
And when adjustment every time, tracking parameter is reinitialized according to the size and location of Current vehicle.
4th, captured according to the relative position of the relative regular line that makes a dash across the red light of vehicle, the image of candid photograph is comprising clear and legible
Information of vehicles, license board information and vehicle traveling behavior signal lamp state.
Step D：If a determination be made that night-time hours, then corresponding grasp shoot method specifically includes：
1st, in vehicle detection area, tail-light is detected, is matched according to the size and location of tail-light；
2nd, car plate is identified by car plate detection device according to the relative position relation of tail-light and car plate, after finding car plate, recognized
Be the tail-light to belonging to same car, the pursuit path of the tail-light pair represents corresponding vehicle, specifically, car plate detection device is
Svm graders based on haar.
3rd, tail-light is tracked using distance and similarity, obtains the pursuit path of tail-light；
4th, captured according to the relative position of the relative regular line that makes a dash across the red light of tail-light, two tail-lights corresponding to a car
Wherein any one meets to capture and required, is considered as meeting candid photograph condition of making a dash across the red light, the image of candid photograph is comprising clear and legible
The signal lamp state of information of vehicles, license board information and vehicle traveling behavior.
The regular line that makes a dash across the red light includes stop line, line is captured in straight trip, turns left to capture line, turns right and capture line.
Claims (6)
- A kind of 1. adaptive Jaywalking snapshot method, it is characterised in that：Comprise the following steps：1) set to make a dash across the red light and capture parameter of regularity；2) video image of area to be monitored is obtained；3) it is daytime period or night-time hours to judge current video image；4) captured accordingly according to the judged result of step 3)；If the judged result of step 3) is daytime period, corresponding grasp shoot method specifically includes：4.1) in vehicle detection area, subtracted each other with present frame gray image and previous frame gray level image, prospect is obtained after binaryzation Figure, if prospect ratio is more than certain threshold value, start tailstock detector；4.2) car plate is identified in the vehicle target that tailstock detector detects, after finding car plate, by corresponding vehicle target frame Initial tracking box of the corresponding image as tracker, while tracking parameter is initialized, track vehicle with meanshift methods；4.3) it is located at the diverse location of image according to vehicle, vehicle size is adaptively adjusted according to the diminution ratio in track, and Every time when adjustment, tracking parameter is reinitialized according to the size and location of Current vehicle；4.4) captured according to the relative position of the relative regular line that makes a dash across the red light of vehicle, the image of candid photograph is comprising clear and legible The signal lamp state of information of vehicles, license board information and vehicle traveling behavior；If the judged result of step 3) is night-time hours, corresponding grasp shoot method specifically includes：5.1) in vehicle detection area, tail-light is detected, is matched according to the size and location of tail-light；5.2) car plate is identified according to the relative position relation of tail-light and car plate, after finding car plate, it is believed that the tail-light is to belonging to Same car, the pursuit path of the tail-light pair represent corresponding vehicle；5.3) using distance and similarity tracking tail-light, the pursuit path of tail-light is obtained；5.4) captured according to the relative position of the relative regular line that makes a dash across the red light of tail-light, in two tail-lights corresponding to a car Any one, which meets to capture, requires, is considered as meeting candid photograph condition of making a dash across the red light, the image of candid photograph includes clear and legible vehicle The signal lamp state of information, license board information and vehicle traveling behavior.
- A kind of 2. adaptive Jaywalking snapshot method as claimed in claim 1, it is characterised in that：The candid photograph parameter of regularity Line, the candid photograph line that turns left are captured including vehicle detection area, track, stop line, straight trip, turns right and captures line and vehicle tracking area, institute State and capture parameter of regularity for setting candid photograph rule.
- A kind of 3. adaptive Jaywalking snapshot method as claimed in claim 1, it is characterised in that：The step 2) is real-time The video image of the web camera transmission of area to be monitored is obtained, the step 3) is according to brightness of image, tail-light unlatching Situation and system time, comprehensive descision current video image are daytime period or night-time hours.
- A kind of 4. adaptive Jaywalking snapshot method as claimed in claim 3, it is characterised in that：The step 3) is specifically wrapped Include：3.1) pixel count that brightness in current video image is less than certain threshold value is counted, calculates the pixel count and current video image The ratio of middle total pixel number, if the ratio is more than certain threshold value, then it is assumed that be night-time hours, otherwise carry out in next step；3.2) vehicle of stop line is crossed using the detection of tailstock detector, detects the unlatching situation of these vehicle tail-lights, if The current vehicle number for crossing stop line is more than 5, and 80% tail-light is opened, then it is assumed that is night-time hours, otherwise enters Row judges in next step；3.3) comparison of the daytime period and night-time hours that are set according to current time and artificially, it is final judge be daytime period also It is night-time hours.
- A kind of 5. adaptive Jaywalking snapshot method as claimed in claim 4, it is characterised in that：Car in the step 3.2) The detecting step of taillight includes：3.2.1 the exceedingly popular pixel for 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 is respectively that the rgb value component , ＆＆ of pixel is represented while met condition；3.2.2 expansion and cavity filling) are carried out, the pixel of some missing inspections of periphery is included；3.2.3 independent tail-light) is found using connected region；3.2.4) in the target frame of vehicle, matched according to tail-light size and location, obtain final tail-light pair.
- A kind of 6. adaptive Jaywalking snapshot method as claimed in claim 1, it is characterised in that：In the step 5.4) In, the regular line that makes a dash across the red light includes stop line, line is captured in straight trip, turns left to capture line and turn right to 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 CN105389991A (en) | 2016-03-09 |
| CN105389991B true 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) |
Families Citing this family (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 |
| 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 |
| 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 |
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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105389991A (en) | 2016-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9704060B2 (en) | Method for detecting traffic violation | |
| CN101872546B (en) | Video-based method for rapidly detecting transit vehicles | |
| CN105389991B (en) | A kind of adaptive Jaywalking snapshot method | |
| CN101656023B (en) | Management method of indoor car park in video monitor mode | |
| CN109410601A (en) | Method for controlling traffic signal lights, device, electronic equipment and storage medium | |
| EP2995177B1 (en) | Smart optical sensor for adaptive, predictive, and on-demand control of public lighting | |
| CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
| CN101739827B (en) | Vehicle detecting and tracking method and device | |
| CN109703460B (en) | Multi-camera complex scene self-adaptive vehicle collision early warning device and early warning method | |
| CN105913685A (en) | Video surveillance-based carport recognition and intelligent guide method | |
| CN106571039A (en) | Automatic snapshot system for highway traffic offence | |
| CN106485927A (en) | A kind of intelligent transportation violation information harvester and acquisition method | |
| CN104537841A (en) | Unlicensed vehicle violation detection method and detection system thereof | |
| CN107808392B (en) | Automatic tracking and positioning method and system for security check vehicle in open scene | |
| CN103646550A (en) | Intelligent vehicle license plate recognition system | |
| CN202422425U (en) | Video-detection-based intelligent signal control system for crossing | |
| CN109784254A (en) | A kind of method, apparatus and electronic equipment of rule-breaking vehicle event detection | |
| CN103325258A (en) | Red light running detecting device and method based on video processing | |
| CN109887276B (en) | Night traffic jam detection method based on fusion of foreground extraction and deep learning | |
| CN107316463A (en) | A kind of method and apparatus of vehicle monitoring | |
| CN112750170A (en) | Fog feature identification method and device and related equipment | |
| CN102768802B (en) | Method for judging road vehicle jam based on finite-state machine (FSM) | |
| Magrini et al. | Computer vision on embedded sensors for traffic flow monitoring | |
| CN106571035B (en) | Urban Travel Time noise data processing method | |
| CN204596151U (en) | Vehicle image acquisition system |
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 |