CN105632175B - Vehicle behavior analysis method and system - Google Patents
Vehicle behavior analysis method and system Download PDFInfo
- Publication number
- CN105632175B CN105632175B CN201610011764.XA CN201610011764A CN105632175B CN 105632175 B CN105632175 B CN 105632175B CN 201610011764 A CN201610011764 A CN 201610011764A CN 105632175 B CN105632175 B CN 105632175B
- Authority
- CN
- China
- Prior art keywords
- license plate
- vehicle
- location information
- image
- module
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention proposes a kind of vehicle behavior analysis method, comprising the following steps: obtains vehicle image in real time, detection obtains the license plate location information in image；New car board location information is compared with the history license plate location information in tracking list, the corresponding matching license plate item that license plate Xiang Ze inserts new car board location information in tracking list is matched if it exists, adds new license plate item in tracking list if without matching license plate；The license plate number in image is identified according to newest license plate position；The vehicle license plate characteristic point of each license plate location information is extracted to construct license plate motion profile；According to license plate motion profile and default behavior decision rule, the behavior of the vehicle of the license plate number is determined.The present invention can analyze vehicle behavior based on the result of car plate detection, and accuracy rate is high, and system and maintenance cost are lower.
Description
Technical field
The present invention relates to the technical fields of intelligent transportation, in particular to be vehicle behavior analysis method and system.
Background technique
Intellectual technology reaches its maturity in the development of field of traffic, is mainly used for highway bayonet or parking lot entrance.At present
Mainstream intelligent transportation settling mode be, ground induction coil perceive vehicle by information after, send signal pass to vehicle inspection
Device is surveyed, it is that a vehicle passes through that wagon detector, which is analyzed to identify, then sends trigger signal to video camera, video camera receives letter
Number, light compensating lamp is controlled on one side and issues light, is pressed shutter shooting image on one side and is identified license plate.Such as the method, vehicle passes through
When only take candid photograph to a picture, it is very limited to the differentiation type of vehicle behavior, an equipment can only realize one or two it is single
Intelligent video function；Construction trouble, camera, upright bar, lamp, ground induction coil etc. require accurate placement, and the software of camera is also required to
Many settings；System cost is high, video camera, lamp, cross bar, radar etc., all high per the same price；Maintenance cost is very high, right
For intelligent transportation system company, maintenance cost accounts for 50% of total expenditure or more；Stability is poor, because system is too complicated, as long as
There is an equipment out of joint or certain two equipment cooperation is out of joint, whole system cannot work normally.
In addition the driving trace of vehicle, such as application disclosed in Patent Office of the People's Republic of China are recorded also by the mode that polyphaser links
Traffic video behavioural analysis and Alarm Server number for CN201110026713, but still remain defect: the installation of hardware
With maintenance cost height, multiple cameras are needed；Stability is poor, has a camera to go wrong, whole system cannot work normally；
And software realization is complicated.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of vehicle behavior analysis methods, can be based on car plate detection
As a result vehicle behavior is analyzed, accuracy rate is high, and system and maintenance cost are lower.
To solve the above problems, the present invention proposes a kind of vehicle behavior analysis method, comprising the following steps:
S1: obtaining vehicle image in real time, and detection obtains the license plate location information in image；
S2: new car board location information is compared with the history license plate location information in tracking list, is matched if it exists
New car board location information is inserted the corresponding matching license plate item in tracking list by license plate Xiang Ze, is arranged if without matching license plate in tracking
New license plate item is added in table；
S3: the license plate number in image is identified according to newest license plate position；
S4: the vehicle license plate characteristic point of each license plate location information is extracted to construct license plate motion profile；
S5: according to license plate motion profile and default behavior decision rule, determine the behavior of the vehicle of the license plate number.
According to one embodiment of present invention, further include step S6: the image for obtaining unlawful practice vehicle is compressed, and is obtained
It takes the image/video of monitoring scene to be compressed, and forms the behavioural analysis knot of text description according to information of vehicles and violation information
Fruit information.
It according to one embodiment of present invention, further include step S21 between step S2 and S3: according to new car memorial tablet confidence
History license plate location information in breath and tracking list carries out license plate position correction, with the newest license plate position after being corrected
It sets.
According to one embodiment of present invention, the license plate location information includes at least coordinate on a vertex on license plate, and
License plate width and license plate height.
It according to one embodiment of present invention, will be in new car board location information and tracking list in the step S2
History license plate location information is compared according to license plate method for estimating and feature matching method, if new car board location information with
Tracking the history license plate location information in list, there is motion continuity and vehicle license plate characteristic to match consistency, then sentences the license plate item
Break to match license plate item.
According to one embodiment of present invention, the step S5 includes:
The judgement of vehicle heading, to shoot the camera of image as object of reference, the direction that camera is set up is used as reference
Direction determines vehicle heading according to license plate moving direction in the picture and the reference orientation；And/or
The judgement of vehicle lane change, using the lane line in image as line of reference, when continuous multiple on license plate motion profile
Point is in the side of lane line, and then, continuous multiple points on the motion profile of license plate, in the other side, are determined as vehicle in lane line
Lane change；And/or
The retrograde judgement of vehicle judges the traffic direction of vehicle according to license plate running track, when license plate running track line is in
When U-shaped, it is determined as that vehicle drives in the wrong direction；And/or
The judgement of overspeed of vehicle carries out image space to the conversion of real physical space, needs to calculate two spaces
Conversion parameter matrix calculates speed according to four vertex of known length and the lane line of width, is moved according to the license plate of image
The image pixel difference of each adjacent two frame is converted to the difference of real physical space, according to frame by track and conversion parameter matrix
Rate calculates speed, when speed is greater than preset threshold, is determined as overspeed of vehicle.
According to one embodiment of present invention, after the step S5 further include: vehicle flowrate is known according to license plate number
Not as a result, counting to the license plate number passed through in monitoring scene, each license plate number corresponds to unique vehicle, to realize wagon flow
Amount statistics.
The present invention also provides a kind of vehicle behavior analysis systems, comprising:
Car plate detection module, obtains vehicle image in real time, and detection obtains the license plate location information in image；
License plate tracking module receives the license plate location information of the car plate detection module, by new car board location information with
History license plate location information in track list is compared, and matches license plate Xiang Ze if it exists for new car board location information and inserts tracking
Corresponding matching license plate item in list adds new license plate item in tracking list if without matching license plate；
Car license recognition module receives the license plate location information of the license plate tracking module, is known according to newest license plate position
License plate number in other image；
Trajectory extraction module receives the license plate location information of the license plate tracking module, extracts each license plate location information
Vehicle license plate characteristic point to construct license plate motion profile；
Behavioural analysis module receives the license plate motion profile of the trajectory extraction module, according to license plate motion profile and in advance
If behavior decision rule determines the behavior of the vehicle of the license plate number.
It according to one embodiment of present invention, further include information describing module, the image for obtaining unlawful practice vehicle carries out
Compression, and the information of vehicles of Car license recognition module and the violation information of received behavioural analysis module form text based on the received
The behavioural analysis result information of description.
According to one embodiment of present invention, further include result output module, obtain the compression video of monitoring scene, receive
The compression image and behavioural analysis result information of the information describing module, receive by network and show monitoring scene video,
And epideictic behaviour analyzes result information and its corresponding image.
It according to one embodiment of present invention, further include vehicle flowrate module, according to license plate number recognition result, to monitoring
The license plate number passed through in scene is counted, and each license plate number corresponds to unique vehicle, to realize vehicle flowrate.
It according to one embodiment of present invention, further include position correction module, license plate tracking module is new based on the received
History license plate location information in license plate location information and tracking list, to the new car memorial tablet confidence of received car plate detection module
Breath carries out license plate position correction, with the newest license plate position after being corrected；Car license recognition module position based on the received
Set the license plate number in the newest license plate position identification image of correction module.
After adopting the above technical scheme, have the advantages that compared with prior art can be from monitoring scene by the present invention
The vehicle image for obtaining high definition in real time, detects the license plate of vehicle, on original high-resolution image in every frame image of acquisition
License plate is detected, high-definition picture ensure that the integrality of license plate area information, license plate tracked and recorded, according to
Newest license plate position identifies license plate number, the license plate motion profile of the license plate number is constructed, so as to judge the vehicle of the license plate number
Behavior, the result based on car plate detection analyze vehicle behavior, such as lane change, drive in the wrong direction, and hypervelocity, vehicle flowrate can
Analysis monitoring vehicle behavior while detecting license board information, to easily and timely obtain rule-breaking vehicle information, behavioural analysis
Accuracy rate is high, and the cost for installing equipment and maintenance is all lower.
Detailed description of the invention
Fig. 1 is the flow diagram of the vehicle behavior analysis method of one embodiment of the invention；
Fig. 2 is the structural block diagram of the vehicle behavior analysis system of one embodiment of the invention；
Fig. 3 is the structural block diagram of the vehicle behavior analysis system of another embodiment of the present invention.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing to the present invention
Specific embodiment be described in detail.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention.But the present invention can be with
Much it is different from other way described herein to implement, those skilled in the art can be without prejudice to intension of the present invention the case where
Under do similar popularization, therefore the present invention is not limited to the specific embodiments disclosed below.
Referring to Fig. 1, the vehicle behavior analysis method of the present embodiment, comprising the following steps:
S1: obtaining vehicle image in real time, and detection obtains the license plate location information in image；
S2: new car board location information is compared with the history license plate location information in tracking list, is matched if it exists
New car board location information is inserted the corresponding matching license plate item in tracking list by license plate Xiang Ze, is arranged if without matching license plate in tracking
New license plate item is added in table；
S3: the license plate number in image is identified according to newest license plate position；
S4: the vehicle license plate characteristic point of each license plate location information is extracted to construct license plate motion profile；
S5: according to license plate motion profile and default behavior decision rule, determine the behavior of the vehicle of the license plate number.
Vehicle image can be obtained from the monitoring scene video of high-definition camera captured in real-time, be obtained according to certain frame per second
Image in video, image are high-definition picture, and detection carries out on high-definition picture with subsequent processing, and license plate is examined
It surveys as real-time image detection frame by frame.
In step sl, license plate is detected on the vehicle image of the original high resolution obtained in real time, high-resolution
Rate image ensure that the integrality of license plate area information, and the license plate location information detected is used for subsequent tracking, license plate position
Information for example can be the left vertex of license plate x coordinate in the picture and y-coordinate (can certainly be other vertex or multiple
The coordinate on vertex), license plate width, license plate height.It can positioning licence plate entire frame in the picture according to license plate location information
Position.
In step s 2, it is pre-established with tracking list, the license plate passed through in image then establishes a license plate item if new,
The license plate location information that each frame image obtains is recorded in license plate item, after obtaining new car board location information, is arranged with tracking is put into before
History license board information in the license plate item of table is compared, and there is matching license plate item, that is, be matched to same license plate, by new car
Board information is put into corresponding matching license plate item in tracking list, and the license plate not matched regards as new license plate, i.e., newly
Into the vehicle in video image, a new license plate item is added in tracking list, realizes the tracking to license plate.
Wherein it is possible to which new car board location information and the history license plate location information in tracking list are estimated according to license plate movement
Meter method and feature matching method are compared, if the history license plate location information in new car board location information and tracking list has
There are motion continuity and vehicle license plate characteristic matching consistency, then the license plate item is judged as matching license plate item.
In step s3, the new car board location information according to obtained in step S2 identifies license plate number in the picture, due to even
Continuous to have carried out multiframe tracking, multiframe can be known in this course by carrying out identification acquisition license plate number to each character of license plate
Other result is integrated, and is selected most believable as a result, to guarantee the promotion to the recognition accuracy of each character of license plate.
Before step S3, license plate position can be corrected, according in new car board location information and tracking list
History license plate location information carries out license plate position correction to the license plate in image, with the newest license plate position after being corrected,
Using the license plate position after the correction as the license plate position for identifying license plate number in image in step S3, school has been carried out to license plate position
Just, license plate position is more accurate, is further ensured that the accuracy rate of Car license recognition.
In step s 4, the available license plate location information after VLP correction, or be also possible to not calibrated
License plate location information, extract the vehicle license plate characteristic point of each license plate location information, the movement of the characteristic point of each frame image constructed
As license plate motion profile.Vehicle license plate characteristic point is, for example, the left apex coordinate of license plate, can also be the other positions on license plate certainly
Point or region.
In step s 5, according to the license plate motion profile and default behavior decision rule obtained in step S4, determine the vehicle
The behavior of the vehicle of the trade mark, default behavior decision rule can set object of reference, the conversion of image and real scene, and correlation
Parameter etc..
Specifically, the judgement of judgement content and decision procedure for example including following content to vehicle behavior:
The judgement of vehicle heading, to shoot the camera of image as object of reference, the direction that camera is set up is used as reference
Direction, such as be divided into: it is to the south, northwards, eastwards, westwards, according to license plate moving direction in the picture and the reference orientation, sentence
Determine vehicle heading, direction determining can be carried out to the vehicle on two-way lane or unidirectional lane, it is to the south for such as setting camera
When, then when vehicle by it is mobile below directional image on image when, i.e., speed is forward direction, can labeled as vehicle heading by south to
North, otherwise for by north to south, other directions are similar；And/or
The judgement of vehicle lane change, by software interface, is inputted lane line and taken up an official post using the lane line in image as line of reference
Two o'clock of anticipating realizes the calibration of lane line, when continuous multiple points on license plate motion profile are in the side of lane line, then, license plate
Continuous multiple points on motion profile, in the other side, are determined as vehicle lane change in lane line；And/or
The retrograde judgement of vehicle judges the traffic direction of vehicle according to license plate running track, when license plate running track line is in
When U-shaped, it is determined as that vehicle drives in the wrong direction；And/or
The judgement of overspeed of vehicle carries out image space to the conversion of real physical space, needs to calculate two spaces
Conversion parameter matrix calculates speed according to four vertex of known length and the lane line of width, is moved according to the license plate of image
The image pixel difference of each adjacent two frame is converted to the difference of real physical space, according to frame by track and conversion parameter matrix
Rate calculates speed, when speed is greater than preset threshold, is determined as overspeed of vehicle.
It in a further embodiment, further include step S6, the processing to behavioural analysis result can be used for showing output
Deng.According to behavioural analysis as a result, obtaining the image of unlawful practice vehicle, and the image is compressed, while available prison
Scene video is controlled, equally video is compressed, is compressed to mitigate transmitted data amount burden, according to information of vehicles and violation information
The behavioural analysis result information of text description is formed, compressed picture, compression video and behavioural analysis result information text can lead to
It crosses network to be transmitted, is provided to display platform and is shown.
Optionally, after step s 5 further include: vehicle flowrate, according to license plate number recognition result, in monitoring scene
The license plate number of process is counted, and each license plate number corresponds to unique vehicle, to realize vehicle flowrate, and then can be to certain
The road degree of crowding of one designated time period is judged.
Referring to Fig. 2, the vehicle behavior analysis system of the present embodiment, including car plate detection module 1, license plate tracking module 2, vehicle
Board identification module 4, trajectory extraction module 3 and behavioural analysis module 5.
Car plate detection module 1 obtains vehicle image in real time, and detection obtains the license plate location information in image.Vehicle image is same
Sample can be the high-resolution image obtained frame by frame from the HD video that high-definition camera 100 is shot.
License plate tracking module 2 receives the license plate location information of car plate detection module 1, builds in advance in license plate tracking module 2
It is vertical to have tracking list, and the license plate item tracked in list is updated with the transformation of vehicle in image, by new car board location information
It is compared with the history license plate location information in tracking list, matches license plate Xiang Ze if it exists and insert new car board location information
The corresponding matching license plate item in list is tracked, adds new license plate item in tracking list if without matching license plate, a license plate item can
To be a data queue, for storing current and history the license plate location information of a license plate.
Car license recognition module 4 receives the license plate location information of license plate tracking module 2, is identified and is schemed according to newest license plate position
License plate number as in, the license plate number can be used for associating with subsequent vehicle behavioural analysis result.Trajectory extraction module 3 receives vehicle
The license plate location information of board tracking module 2 extracts the vehicle license plate characteristic point of the license plate location information in each frame image, with vehicle license plate characteristic
The variation of point constructs license plate motion profile.The license plate motion profile of 5 receiving locus extraction module 3 of behavioural analysis module, according to vehicle
Board motion profile and default behavior decision rule, determine the behavior of the vehicle of the license plate number.
In one embodiment, referring to Fig. 2, vehicle behavior analysis system further includes information describing module 6, obtains row in violation of rules and regulations
For vehicle image carry out compression form compressed picture, and based on the received the information of vehicles (license plate number) of Car license recognition module 4,
The violation information of received behavioural analysis module 5 forms the behavioural analysis result information of textual form description.
Referring to Fig. 3, vehicle behavior analysis system further include can result output module 8, obtain monitoring scene compression view
Frequently, the compression image and behavioural analysis result information for receiving information describing module 6 are received by network and show that monitoring scene regards
Frequently, and epideictic behaviour analyzes result information and its corresponding image.Information describing module 6 can by network will compress image and
The behavioural analysis result information of textual form is transferred to result output module 8, and as a result output module 8 can be with display screen
Computer platform.Preferably, being additionally provided with video compressing module 9, video between high-definition camera 100 and result output module 8
Compression module 9 is sent to result output module 8 after being compressed the HD video that high-definition camera 100 is shot, equally can be with
It is sent by network or other forms, while detecting license plate, the video of acquisition is compressed, be sent to result output mould
Block 8.
Vehicle behavior analysis system can also include vehicle flowrate module (not shown), identified and tied according to license plate number
Fruit counts the license plate number passed through in monitoring scene, and each license plate number corresponds to unique vehicle, to realize that vehicle flowrate is united
Meter.
Further, with continued reference to Fig. 3, vehicle behavior analysis system can also include position correction module 7, according to reception
License plate tracking module 2 new car board location information and tracking list in history license plate location information, in conjunction with current information with
Historical information correction error carries out license plate position correction to the new car board location information of received car plate detection module 1, to obtain
Newest license plate position after correction；Car license recognition module 4 receives the license plate location information after position correction module 7 corrects, root
According to the license plate number in newest license plate position identification image；Trajectory extraction module 3 receives the license plate after position correction module 7 corrects
Location information constructs license plate motion profile according to newest license plate location information.
It is worth noting that having been carried out briefly in description to System and method for content repeating part of the invention
Bright, system particular content can refer to the content of method part.It can be using the image recognition in conventional images processing technique, spy
The modes such as sign extraction, estimation realize that Car license recognition of the invention, location information extract, and matching is than equity.The present invention can be with
The behavior of analysis monitoring vehicle while detecting license plate.
Although the present invention is disclosed as above with preferred embodiment, it is not for limiting claim, any this field
Technical staff without departing from the spirit and scope of the present invention, can make possible variation and modification, therefore of the invention
Protection scope should be subject to the range that the claims in the present invention are defined.
Claims (8)
1. a kind of vehicle behavior analysis method, which comprises the following steps:
S1: obtaining vehicle image in real time, and detection obtains the license plate location information in image；
S2: new car board location information is compared with the history license plate location information in tracking list, matches license plate if it exists
New car board location information is inserted the corresponding matching license plate item in tracking list by Xiang Ze, if without matching license plate in tracking list
Add new license plate item；
S3: the license plate number in image is identified according to newest license plate position；
S4: the vehicle license plate characteristic point of each license plate location information is extracted to construct license plate motion profile；
S5: according to license plate motion profile and default behavior decision rule, determine the behavior of the vehicle of the license plate number；
In the step S2, new car board location information and the history license plate location information in tracking list are moved according to license plate
Estimation method and feature matching method are compared, if the history license plate location information in new car board location information and tracking list
Consistency is matched with motion continuity and vehicle license plate characteristic, then the license plate item is judged as matching license plate item；
It further include step S21 between step S2 and S3: according to the history license plate position in new car board location information and tracking list
Confidence breath carries out license plate position correction, with the newest license plate position after being corrected；
The license plate location information includes at least coordinate on a vertex and license plate width and license plate height on license plate；
The default behavior decision rule includes:
The judgement of vehicle heading, to shoot the camera of image as object of reference, the direction that camera is set up is used as reference orientation,
According to license plate moving direction in the picture and the reference orientation, vehicle heading is determined；And/or
The judgement of vehicle lane change, using the lane line in image as line of reference, when continuous multiple points on license plate motion profile exist
The side of lane line, then, continuous multiple points on the motion profile of license plate, in the other side, are determined as that vehicle becomes in lane line
Road；And/or
The retrograde judgement of vehicle judges the traffic direction of vehicle according to license plate running track, when license plate running track line is in U-shape
When, it is determined as that vehicle drives in the wrong direction；And/or
The judgement of overspeed of vehicle carries out image space to the conversion of real physical space, needs to calculate the conversion of two spaces
Parameter matrix calculates speed according to four vertex of known length and the lane line of width, according to the license plate motion profile of image
With conversion parameter matrix, the image pixel difference of each adjacent two frame is converted to the difference of real physical space, according to frame per second meter
Speed is calculated, when speed is greater than preset threshold, is determined as overspeed of vehicle.
2. vehicle behavior analysis method as described in claim 1, which is characterized in that further include step S6: obtaining unlawful practice
The image of vehicle is compressed, and the image/video for obtaining monitoring scene is compressed, and according to information of vehicles and violation information shape
The behavioural analysis result information described at text.
3. vehicle behavior analysis method as claimed in claim 1 or 2, which is characterized in that after the step S5 further include:
Vehicle flowrate counts the license plate number passed through in monitoring scene according to license plate number recognition result, and each license plate number is corresponding
Unique vehicle, to realize vehicle flowrate.
4. a kind of vehicle behavior analysis system characterized by comprising
Car plate detection module, obtains vehicle image in real time, and detection obtains the license plate location information in image；
License plate tracking module receives the license plate location information of the car plate detection module, and new car board location information and tracking are arranged
History license plate location information in table is compared, and matches license plate Xiang Ze if it exists for new car board location information and inserts tracking list
In corresponding matching license plate item, if without matching license plate if tracking list in add new license plate item；By new car board location information with
History license plate location information in tracking list is compared according to license plate method for estimating and feature matching method, if new car
Board location information with the history license plate location information in tracking list there is motion continuity and vehicle license plate characteristic to match consistency, then
The license plate item is judged as matching license plate item；
Car license recognition module receives the license plate location information of the license plate tracking module, is identified and is schemed according to newest license plate position
License plate number as in；
Trajectory extraction module receives the license plate location information of the license plate tracking module, extracts the vehicle of each license plate location information
Board characteristic point is to construct license plate motion profile；
Behavioural analysis module receives the license plate motion profile of the trajectory extraction module, according to license plate motion profile and default row
For decision rule, the behavior of the vehicle of the license plate number is determined；
The default behavior decision rule includes:
The judgement of vehicle heading, to shoot the camera of image as object of reference, the direction that camera is set up is used as reference orientation,
According to license plate moving direction in the picture and the reference orientation, vehicle heading is determined；And/or
The judgement of vehicle lane change, using the lane line in image as line of reference, when continuous multiple points on license plate motion profile exist
The side of lane line, then, continuous multiple points on the motion profile of license plate, in the other side, are determined as that vehicle becomes in lane line
Road；And/or
The retrograde judgement of vehicle judges the traffic direction of vehicle according to license plate running track, when license plate running track line is in U-shape
When, it is determined as that vehicle drives in the wrong direction；And/or
The judgement of overspeed of vehicle carries out image space to the conversion of real physical space, needs to calculate the conversion of two spaces
Parameter matrix calculates speed according to four vertex of known length and the lane line of width, according to the license plate motion profile of image
With conversion parameter matrix, the image pixel difference of each adjacent two frame is converted to the difference of real physical space, according to frame per second meter
Speed is calculated, when speed is greater than preset threshold, is determined as overspeed of vehicle.
5. vehicle behavior analysis system as claimed in claim 4, which is characterized in that further include information describing module, obtain and disobey
The image of rule behavior vehicle is compressed, and the information of vehicles of Car license recognition module and received behavioural analysis mould based on the received
The violation information of block forms the behavioural analysis result information of text description.
6. vehicle behavior analysis system as claimed in claim 5, which is characterized in that further include result output module, obtain prison
The compression video for controlling scene, receives the compression image and behavioural analysis result information of the information describing module, is connect by network
Receive and show monitoring scene video, and epideictic behaviour analysis result information and its corresponding image.
7. vehicle behavior analysis system as claimed in claim 6, which is characterized in that it further include vehicle flowrate module, according to
License plate number recognition result counts the license plate number passed through in monitoring scene, and each license plate number corresponds to unique vehicle, thus
Realize vehicle flowrate.
8. vehicle behavior analysis system as claimed in claim 4, which is characterized in that further include position correction module, according to connecing
History license plate location information in the new car board location information and tracking list of the license plate tracking module of receipts, examines received license plate
The new car board location information for surveying module carries out license plate position correction, with the newest license plate position after being corrected；The license plate
Identification module based on the received position correction module newest license plate position identification image in license plate number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610011764.XA CN105632175B (en) | 2016-01-08 | 2016-01-08 | Vehicle behavior analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610011764.XA CN105632175B (en) | 2016-01-08 | 2016-01-08 | Vehicle behavior analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105632175A CN105632175A (en) | 2016-06-01 |
| CN105632175B true CN105632175B (en) | 2019-03-29 |
Family
ID=56047048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610011764.XA Active CN105632175B (en) | 2016-01-08 | 2016-01-08 | Vehicle behavior analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105632175B (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295810B (en) * | 2016-07-25 | 2020-09-08 | 国网山东省电力公司青岛供电公司 | Fault repair work order distribution method and device |
| CN106251633A (en) * | 2016-08-09 | 2016-12-21 | 成都联众智科技有限公司 | License auto-recognition system and the system of tracking |
| CN107862862B (en) * | 2016-09-22 | 2020-11-20 | 杭州海康威视数字技术股份有限公司 | Vehicle behavior analysis method and device |
| CN106529401A (en) * | 2016-09-26 | 2017-03-22 | 北京格灵深瞳信息技术有限公司 | Vehicle anti-tracking method, vehicle anti-tracking device and vehicle anti-tracking system |
| CN106781513A (en) * | 2016-11-28 | 2017-05-31 | 东南大学 | The recognition methods of vehicle behavior in a kind of urban transportation scene of feature based fusion |
| CN107635188A (en) * | 2017-09-08 | 2018-01-26 | 安徽四创电子股份有限公司 | A kind of video frequency vehicle trace analysis method based on Docker platforms |
| CN107424412A (en) * | 2017-09-21 | 2017-12-01 | 程丹秋 | A kind of traffic behavior analysis system |
| CN107886055A (en) * | 2017-10-27 | 2018-04-06 | 中国科学院声学研究所 | A kind of retrograde detection method judged for direction of vehicle movement |
| CN108548543B (en) * | 2018-03-27 | 2019-08-02 | 上海识加电子科技有限公司 | Vehicle route management method and device |
| CN108846906B (en) * | 2018-06-04 | 2021-07-30 | 西安艾润物联网技术服务有限责任公司 | Parking management method, system and computer readable storage medium |
| CN113366548A (en) * | 2018-12-28 | 2021-09-07 | 北京航迹科技有限公司 | System and method for vehicle identification |
| CN109747642B (en) * | 2019-01-04 | 2020-09-08 | 北京博宇通达科技有限公司 | Vehicle travel control method and apparatus |
| CN109887303B (en) * | 2019-04-18 | 2022-07-05 | 齐鲁工业大学 | Lane-changing behavior early warning system and method |
| CN110728843B (en) * | 2019-09-10 | 2021-08-31 | 浙江大华技术股份有限公司 | Vehicle snapshot method, vehicle snapshot device, and storage medium |
| US11709828B2 (en) | 2019-10-31 | 2023-07-25 | Genetec Inc | Method and system for associating a license plate number with a user |
| CN110807934A (en) * | 2019-11-13 | 2020-02-18 | 赵洪涛 | Intelligent scheduling platform for monitoring highway operation |
| CN111145555B (en) * | 2019-12-09 | 2021-02-26 | 浙江大华技术股份有限公司 | Method and device for detecting vehicle violation |
| CN111127949B (en) * | 2019-12-18 | 2021-12-03 | 北京中交兴路车联网科技有限公司 | Vehicle high-risk road section early warning method and device and storage medium |
| CN111539337A (en) * | 2020-04-26 | 2020-08-14 | 上海眼控科技股份有限公司 | Vehicle posture correction method, device and equipment |
| CN111640300B (en) * | 2020-04-28 | 2022-06-17 | 武汉万集信息技术有限公司 | Vehicle detection processing method and device |
| CN111815960A (en) * | 2020-06-28 | 2020-10-23 | 贵州数据宝网络科技有限公司 | Vehicle information display method based on big data |
| CN113591820A (en) * | 2021-09-30 | 2021-11-02 | 深圳市鑫道为科技有限公司 | Driving data storage method capable of extracting hit-and-run license plate information |
| CN114170810A (en) * | 2021-12-28 | 2022-03-11 | 深圳市捷顺科技实业股份有限公司 | Vehicle traveling direction identification method, system and device |
| CN115762143B (en) * | 2022-11-02 | 2024-05-03 | 宁波云弧科技有限公司 | Vehicle track processing method |
| CN116071688A (en) * | 2023-03-06 | 2023-05-05 | 台州天视智能科技有限公司 | Behavior analysis method and device for vehicle, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7970644B2 (en) * | 2003-02-21 | 2011-06-28 | Accenture Global Services Limited | Electronic toll management and vehicle identification |
| CN101877174B (en) * | 2009-09-29 | 2012-07-25 | 杭州海康威视软件有限公司 | Vehicle speed measurement method, supervisory computer and vehicle speed measurement system |
| CN102509457B (en) * | 2011-10-09 | 2014-03-26 | 青岛海信网络科技股份有限公司 | Vehicle tracking method and device |
| CN102521979B (en) * | 2011-12-06 | 2013-10-23 | 北京万集科技股份有限公司 | High-definition camera-based method and system for pavement event detection |
| CN203606951U (en) * | 2013-11-06 | 2014-05-21 | 杭州海康威视数字技术股份有限公司 | Image acquisition device based on license plate identification and system |
-
2016
- 2016-01-08 CN CN201610011764.XA patent/CN105632175B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105632175A (en) | 2016-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105632175B (en) | Vehicle behavior analysis method and system | |
| Sochor et al. | Comprehensive data set for automatic single camera visual speed measurement | |
| KR102167291B1 (en) | System and method for providing road status information | |
| CA2747337C (en) | Multiple object speed tracking system | |
| CN103164706B (en) | Object counting method and device based on video signal analysis | |
| CN104575003B (en) | A kind of vehicle speed detection method based on traffic surveillance videos | |
| CN107424412A (en) | A kind of traffic behavior analysis system | |
| KR102200204B1 (en) | 3-D Image Analyzing System Using CCTV Image | |
| US20030190058A1 (en) | Apparatus and method for measuring queue length of vehicles | |
| CN109615862A (en) | Road vehicle movement of traffic state parameter dynamic acquisition method and device | |
| KR102167292B1 (en) | Apparatus and method for providing road status information | |
| CN114170580A (en) | Highway-oriented abnormal event detection method | |
| CN108922172B (en) | Road congestion monitoring system based on vehicle characteristic matrix sequence change analysis | |
| CN113505638B (en) | Method and device for monitoring traffic flow and computer readable storage medium | |
| CN110929676A (en) | Deep learning-based real-time detection method for illegal turning around | |
| CN111878174B (en) | High-speed railway tunnel lining block dropping video monitoring method and device | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| CN116128360A (en) | Road traffic congestion level evaluation method and device, electronic equipment and storage medium | |
| CN113052125B (en) | Construction site violation image recognition and alarm method | |
| CN117710843A (en) | Intersection dynamic signal timing scheme detection method based on unmanned aerial vehicle video | |
| KR100782205B1 (en) | Apparatus and system for displaying speed of car using image detection | |
| CN113177508B (en) | Method, device and equipment for processing driving information | |
| CN106919889A (en) | The method and apparatus detected to the number of people in video image | |
| KR102492290B1 (en) | Drone image analysis system based on deep learning for traffic measurement | |
| CN111627224A (en) | Vehicle speed abnormality detection 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 | ||
| CP03 | "change of name, title or address" | ||
| CP03 | "change of name, title or address" |
Address after: No.1 Workshop No.1, Lugong Road, Gangkou Development Zone, Fuqiao Town, Taicang City, Suzhou City, Jiangsu Province Patentee after: Suzhou Weirui Intelligent Technology Co., Ltd Address before: 200233 room 9, building 509, No. 101-40, Xuhui District, Shanghai, Caobao Road Patentee before: SHANGHAI MICROSHARP INTELLIGENT TECHNOLOGY Co.,Ltd. |