CN105894823B - A kind of parking detection method and apparatus and system - Google Patents
A kind of parking detection method and apparatus and system Download PDFInfo
- Publication number
- CN105894823B CN105894823B CN201610391319.0A CN201610391319A CN105894823B CN 105894823 B CN105894823 B CN 105894823B CN 201610391319 A CN201610391319 A CN 201610391319A CN 105894823 B CN105894823 B CN 105894823B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- vehicle target
- parking
- parking stall
- 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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- 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
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Traffic Control Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
A kind of parking detection method disclosed in the present application and apparatus and system.According to the video frame obtained from video camera, monitor whether that, there are the first vehicle target, the first vehicle target is the vehicle target during parking.After detecting there are the first vehicle target, the license board information of the first vehicle target is obtained.It realizes and just obtains license board information before vehicle does not stop into parking stall.And then it provides evidence for Car park payment and supports.
Description
Technical field
This application involves art of image analysis, more specifically to a kind of parking detection method and device and are
System.
Background technology
With the development of economy, the quantity of motor vehicle continues to increase, in order to solve the problems, such as parking difficulty, new added road parking
The parking mode of position.Traditional parking detection method is no longer desirable for the parking mode of road parking place.For example, stopping
Position setting sensor carries out the method detected into position, generally use infrared sensor, geomagnetic sensor or ultrasonic sensor etc.
Equipment obtains temperature change, changes of magnetic field or ohject displacement variation etc. and realizes parking detection.But it is this in parking stall setting
Sensor, which carries out vehicle, to be entered a detection mode and is highly susceptible to the interference of ambient enviroment to cause flase drop, also, can not be to vehicle
License board information is detected, and then evidence support can not be provided for Car park payment.And the parking detection mode based on video,
After vehicle completes position, the license board information of collection vehicle, accuracy of detection with respect to parking stall setting sensor detect into position
Method accuracy of detection significantly improves, and evidence support can be provided for Car park payment.
But traditional parking detection mode based on video is not suitable for the parking mode of road parking place, because
Be vehicle road parking place complete parking after, the car plate before and after vehicle, can not by the occlusion on front and back parking stall
The acquisition of vehicle license plate information is carried out again.
Invention content
In view of this, the application proposes a kind of parking detection method and apparatus and system, be intended to realize vehicle stop into
The purpose obtained to license board information is completed before parking stall.
To achieve the goals above, it is proposed that scheme it is as follows：
A kind of parking detection method, including：
Video frame is obtained from video camera, the video camera monitors its corresponding monitoring area in real time, the prison
Control region includes L parking stall position, and the L is positive number；
According to the video frame, monitor whether that, there are the first vehicle target, first vehicle target is in parking
Process；
After detecting there are first vehicle target, the license board information of first vehicle target is obtained.
Preferably, according to the video frame, monitoring whether that there are the first vehicle targets includes：
The video frame is calculated using background modeling algorithm, obtains the foreground area of moving target；
Detect the second vehicle target in the foreground area；
Target following is carried out to second vehicle target, obtains the movement locus of second vehicle target；
According to the feature of the movement locus of second vehicle target, judge second vehicle target whether in parking
Enter a process.
Preferably, further include after the foreground area for obtaining moving target：
Feature point extraction is carried out to the foreground area；
If being more than predetermined threshold value in the number of the characteristic point of parking stall position, it is determined that the parking stall position is to exist to move
First parking stall position of target；
If the movement locus place of first parking stall position and second vehicle target in parking process
Region is identical, then judges whether the moving target existing for the position of first parking stall is vehicle target；
If the moving target existing for the position of first parking stall is vehicle target, it is determined that the vehicle target is first
Vehicle target.
Preferably, further include after detecting there are first vehicle target：
Vehicle detection signal is obtained from earth magnetism wagon detector, the earth magnetism wagon detector corresponds to first vehicle
Parking stall position where target；
When the vehicle detection signal is to detect the signal of vehicle, and described detect that the signal duration of vehicle is big
When preset time threshold, determine that first vehicle target is completed into position.
A kind of parking detection device, including：
Image acquisition unit, for obtaining video frame from video camera, the video camera to its corresponding monitoring area into
Row real time monitoring, the monitoring area include L parking stall position, and the L is positive number；
First vehicle target unit is monitored whether there are the first vehicle target, described first for according to the video frame
Vehicle target is in parking process；
Information of vehicles unit is obtained, for after detecting there are first vehicle target, obtaining first vehicle
The license board information of target.
Preferably, the first vehicle target unit includes：
First foreground area unit obtains movement mesh for being calculated the video frame using background modeling algorithm
Target foreground area；
Second vehicle target unit, for detecting the second vehicle target in the foreground area；
Movement locus unit obtains second vehicle target for carrying out target following to second vehicle target
Movement locus；
First judging unit is used for the feature of the movement locus according to second vehicle target, judges second vehicle
Whether target is in parking process.
Preferably, the first vehicle target unit further includes：
Feature extraction unit, for carrying out feature point extraction to the foreground area；
First parking stall unit, if the number for the characteristic point in parking stall position is more than predetermined threshold value, it is determined that should
Parking stall position is the first parking stall position there are moving target；
Second judgment unit, second vehicle for judging first parking stall position with being in parking process
When the movement locus region of target is identical, then third judging unit is transferred to；
Third judging unit, when for judging that the moving target is vehicle target existing for the position of first parking stall,
Then determine that the vehicle target of first parking stall position is the first vehicle target.
Preferably, described device further includes：
Geomagnetism detecting unit is obtained, for obtaining vehicle detection signal, the inspection of described ground magnetic vehicle from earth magnetism wagon detector
It surveys device and corresponds to the parking stall position where first vehicle target；
Enter position and completes detection unit, for being to detect the signal of vehicle when the vehicle detection signal, and the detection
To vehicle signal duration be more than preset time when, determine that first vehicle target is completed into position.
A kind of parking detecting system, which is characterized in that including：N number of video camera and controller, the controller include
Above-mentioned parking detection device, the N are positive integer.
Preferably, the system also includes：
M earth magnetism wagon detector being connect with the controller, each parking stall of earth magnetism wagon detector pair position
Vehicle detection is carried out, the M is positive integer；
The parking detection device further includes：
Geomagnetism detecting unit is obtained, for obtaining vehicle detection signal, the inspection of described ground magnetic vehicle from earth magnetism wagon detector
It surveys device and corresponds to the parking stall position where first vehicle target；
Enter position and completes detection unit, for being to detect the signal of vehicle when the vehicle detection signal, and the detection
To vehicle signal duration be more than preset time when, determine that first vehicle target is completed into position.
Preferably, the system also includes：The display device being connect with the controller, for showing that vehicle target is completed
Enter information.
Preferably, the display device includes：Mobile terminal or computer.
Preferably, the mobile terminal includes：Smart mobile phone or tablet computer.
Preferably, the video camera is：Ball-shaped camera.
It can be seen from the above technical scheme that a kind of parking detection method disclosed in the present application and device and being
System.According to the video frame obtained from video camera, monitor whether that, there are the first vehicle target, the first vehicle target is in parking
Enter the vehicle target during position.After detecting there are the first vehicle target, the license board information of the first vehicle target is obtained.It is real
Present vehicle just obtains license board information before not stopping into parking stall.And then it provides evidence for Car park payment and supports.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow chart of parking detection method disclosed in the present embodiment；
Fig. 2 is the schematic diagram of camera supervised monitoring area disclosed in the present embodiment；
Fig. 3 is the flow chart of another parking detection method disclosed in the present embodiment；
Fig. 4 is in the flow chart of the judgment method of parking process for a kind of vehicle target disclosed in the present embodiment；
Fig. 5 is the flow chart for the judgment method that another vehicle target is in parking process disclosed in the present embodiment；
Fig. 6 is a kind of schematic diagram of parking detection device disclosed in the present embodiment；
Fig. 7 is the schematic diagram of another parking detection device disclosed in the present embodiment；
Fig. 8 is a kind of schematic diagram of first vehicle target unit disclosed in the present embodiment；
Fig. 9 is the schematic diagram of another first vehicle target unit disclosed in the present embodiment；
Figure 10 is a kind of schematic diagram of parking detecting system disclosed in the present embodiment；
Figure 11 is the schematic diagram of another parking detecting system disclosed in the present embodiment；
Figure 12 is the schematic diagram of another parking detecting system disclosed in the present embodiment.
Specific implementation mode
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The present embodiment discloses a kind of parking detection method, shown in Figure 1, including：
Step S11：Video frame is obtained from video camera.
Video camera monitors its corresponding monitoring area in real time, and the monitoring area includes L parking stall position, and L is
Positive number.As shown in Fig. 2, the monitoring area that ball-shaped camera 11 monitors includes parking stall position 21, parking stall position 22 and parking stall position
23 are set, the monitoring area that ball-shaped camera 12 monitors includes parking stall position 24, parking stall position 25 and parking stall position 26.Video camera
The specific number of the monitoring area parking stall position that includes determine that the application does not limit this according to actual road conditions
It is fixed.
Step S12：According to the video frame of acquisition, monitor whether that there are the first vehicle targets.
Vehicle target in parking process is the first vehicle target.After video camera is fixed, the scene of monitoring
It is also fixed area, position of each parking stall position in the image that video camera is shot is also in camera supervised monitoring area
It is fixed, and actual each parking stall region corresponds to each parking stall position in camera supervised monitoring area.From camera shooting
After machine obtains video frame, according to the method for image analysis, the vehicle target for having in parking process is detected whether.
Step S13：After detecting there are the first vehicle target, the license board information of the first vehicle target is obtained.
After detecting the presence of the vehicle target during parking, corresponding video camera alignment is controlled in parking
Enter the vehicle target during position to be focused, closely obtains the license board information of vehicle target.Realize vehicle do not stop into
License board information is just obtained before parking stall.And then it provides evidence for Car park payment and supports.
The present embodiment discloses another parking detection method, shown in Figure 3, including：
Step S11：Video frame is obtained from video camera.
Step S12：According to the video frame of acquisition, monitor whether that there are the first vehicle targets.
Step S13：After detecting there are the first vehicle target, the license board information of the first vehicle target is obtained.
Step S14：Vehicle detection is obtained from the corresponding earth magnetism wagon detector in parking stall position where the first vehicle target
Signal.
Step S15：When the vehicle detection signal be detect the signal of vehicle, and detect vehicle signal continue when
Between be more than preset time threshold when, determine that first vehicle target is completed into position.
Shown in Figure 2, each parking stall position corresponds to an earth magnetism wagon detector 3.When vehicle is in earth magnetism vehicle detection
Near device 3, earth magnetism wagon detector 3 can perceive the variation of signal, and then export the signal for detecting vehicle, when not having vehicle
When near earth magnetism wagon detector 3, earth magnetism wagon detector 3 exports the signal that vehicle is not detected.It is in when detecting
After the vehicle target of parking process, the vehicle detection of corresponding earth magnetism wagon detector is obtained as a result, further determining that vehicle
Enter a state, if the output result of earth magnetism wagon detector is that signals of vehicles is not detected or detects signals of vehicles
Duration is not more than preset time threshold, then it is assumed that the testing result of the first vehicle target is flase drop.It carries in this way
The high accuracy of detection of system.
It is monitored whether according to the video frame of acquisition there are the process of the first vehicle target is shown in Figure 4, including：
Step S21：The video frame of acquisition is calculated using background modeling algorithm, obtains the foreground zone of moving target
Domain.
Gaussian Background modeling algorithm can be specifically utilized to acquire the foreground area of moving target.
Step S22：Detect the second vehicle target in foreground area.
Second vehicle target is the vehicle moved.Moving target in foreground area is not necessarily vehicle, further includes row
People, the moving targets such as bicycle.Using the calculation of the detection vehicle built based on DPM (Deformable Parts Model) algorithm
Method module carries out vehicle target detection to video frame.Vehicle target include vehicle location information in the picture, headstock information and
Vehicle left and right of vehicle body inside the position of parking stall believes one side only breath etc..After the foreground area for obtaining moving target, utilize what is detected
Vehicle target judges that the moving target of foreground area whether there is vehicle target.If there is vehicle target, just calculated using tracking
Method is to the vehicle target of foreground area into line trace.
Step S23：Target following is carried out to the second vehicle target, obtains the movement locus of the second vehicle target.
Specific may be used carries out target following based on matched the second vehicle target of track algorithm pair of Optical-flow Feature, leads to
Cross the movement locus that tracking obtains the second vehicle target.
Step S24：According to the feature of the movement locus of the second vehicle target, judge the second vehicle target whether in parking
Enter a process.
If the vehicle target of movement is in parking process, it is determined that be the first vehicle target.Vehicle stop into
During position, the track travelled has certain feature, for example, non-straight trip, rolls parking stall line etc..According to parking
The movement locus feature of the second vehicle target of movement locus feature pair is analyzed, and judges whether the second vehicle is in parking
Process.
Video frame is analyzed using background modeling algorithm, obtains the foreground area of moving target, binding characteristic extraction and spy
Sign calculates, and enhances robustness of the system to ambient enviroment, is suitable for blowing, sleet, the bad weathers such as illumination deficiency.
It is monitored whether according to the video frame of acquisition there are the process of the first vehicle target is shown in Figure 5, including：
Step S21：The video frame of acquisition is calculated using background modeling algorithm, obtains the foreground zone of moving target
Domain.
Step S22：Detect the second vehicle target in foreground area.
Step S23：Target following is carried out to the second vehicle target, obtains the movement locus of the second vehicle target.
Step S24：According to the feature of the movement locus of the second vehicle target, judge the second vehicle target whether in parking
Enter a process.
Step S31：Feature point extraction is carried out to the foreground area of moving target.
Step S32：If being more than predetermined threshold value in the number of the characteristic point of parking stall position, it is determined that the parking stall position is to exist
First parking stall position of moving target.
Step S33：If the movement locus place of the first parking stall position and the second vehicle target in parking process
Region is identical, then judges whether moving target existing for the first parking stall position is vehicle target.
Judge whether moving target existing for the first parking stall position is that the process of vehicle target is, using based on DPM algorithms
The algoritic module of the detection vehicle of structure, vehicle target detection is carried out to video frame.Using the vehicle target detected, is judged
Whether moving target existing for one parking stall position is vehicle target.
Step S34：If moving target existing for the first parking stall position is vehicle target, it is determined that the vehicle target is first
Vehicle target is transferred to step S13.
During vehicle enters parking stall position, corresponding parking stall position can detect foreground area.Judge the parking stall
There are the processes that vehicle target carries out parking for position.If according to the feature of the movement locus of the second vehicle target, also sentence
Break and the second vehicle target and be in parking process, and the movement locus location of the first parking stall position and the second vehicle target
When domain is identical, then further determines that the same area whether there is vehicle, that is, determine whether for the first vehicle target.Pass through parking stall
Position foreground area detection and the movement locus of vehicle target detect comprehensive descision, and the system of enhancing enters the accuracy of position detection.
For each method embodiment above-mentioned, for simple description, therefore it is all expressed as a series of combination of actions, but
Be those skilled in the art should understand that, the application is not limited by the described action sequence because according to the application, certain
A little steps can be performed in other orders or simultaneously.
The present embodiment discloses a kind of parking detection device, shown in Figure 6, including：
Image acquisition unit 11, for obtaining video frame from video camera, video camera carries out its corresponding monitoring area
Real time monitoring, monitoring area include L parking stall position, and the L is positive number.
First vehicle target unit 12, for according to the video frame of acquisition, monitoring whether there are the first vehicle target, first
Vehicle target is in parking process.
Information of vehicles unit 13 is obtained, for after detecting there are first vehicle target, obtaining the first vehicle mesh
Target license board information.
The present embodiment discloses a kind of parking detection device, shown in Figure 7, including：
Image acquisition unit 11, for obtaining video frame from video camera, video camera carries out its corresponding monitoring area
Real time monitoring, monitoring area include L parking stall position, and the L is positive number.
First vehicle target unit 12, for according to the video frame of acquisition, monitoring whether there are the first vehicle target, first
Vehicle target is in parking process.
Information of vehicles unit 13 is obtained, for after detecting there are first vehicle target, obtaining the first vehicle mesh
Target license board information.
Geomagnetism detecting unit 14 is obtained, for obtaining vehicle detection signal, earth magnetism vehicle detection from earth magnetism wagon detector
Device corresponds to the parking stall position where the first vehicle target；
Enter position and complete detection unit 15, for being to detect the signal of vehicle, and detect vehicle when vehicle detection signal
Signal duration be more than preset time when, determine that the first vehicle target is completed into position.
The present embodiment discloses a kind of first vehicle target unit, shown in Figure 8, including：
First foreground area unit 121 obtains moving target for being calculated video frame using background modeling algorithm
Foreground area.
Second vehicle target unit 122, for detecting the second vehicle target in foreground area.
Movement locus unit 123 obtains the movement of the second vehicle target for carrying out target following to the second vehicle target
Track.
First judging unit 124 is used for the feature of the movement locus according to the second vehicle target, judges the second vehicle target
Whether parking process is in.
The present embodiment discloses a kind of first vehicle target unit, shown in Figure 9, including：
First foreground area unit 121 obtains moving target for being calculated video frame using background modeling algorithm
Foreground area.
Second vehicle target unit 122, for detecting the second vehicle target in foreground area.
Movement locus unit 123 obtains the movement of the second vehicle target for carrying out target following to the second vehicle target
Track.
First judging unit 124 is used for the feature of the movement locus according to the second vehicle target, judges the second vehicle target
Whether parking process is in.
Feature extraction unit 125 carries out feature point extraction for the foreground area to moving target.
First parking stall unit 126, if the number for the characteristic point in parking stall position is more than predetermined threshold value, it is determined that the vehicle
Position position is the first parking stall position there are moving target；
Second judgment unit 127, the second vehicle target for judging the first parking stall position with being in parking process
Movement locus region it is identical when, then be transferred to third judging unit 128.
Third judging unit 128, for judging that the moving target is vehicle target existing for the position of first parking stall
When, it is determined that the vehicle target is the first vehicle target, is transferred to and obtains information of vehicles unit 13.
The present embodiment discloses a kind of parking detecting system, shown in Figure 10, including：N number of video camera (video camera
11 ... ..., video camera 1N) and controller 4, the N is positive integer, wherein
Each video camera (video camera 11 ... ..., video camera 1N) monitors its corresponding monitoring area in real time, described
Monitoring area includes L parking stall position, and the L is positive number；
Controller 4 is respectively with video camera 11 ... ..., and video camera 1N connections, controller 4 includes that above-mentioned parking detects
Device.
The present embodiment discloses another parking detecting system, shown in Figure 11, including：N number of video camera (video camera
11 ... ..., video camera 1N), M earth magnetism wagon detector (earth magnetism wagon detector 31 ... ..., earth magnetism wagon detector 3M) and
Controller 4, the M and N are positive integer, wherein
Each video camera (video camera 11 ... ..., video camera 1N) monitors its corresponding monitoring area in real time, monitors
Region includes L parking stall position, and the L is positive number.
Each earth magnetism wagon detector (earth magnetism wagon detector 31 ... ..., earth magnetism wagon detector 3M) is to a parking stall
Position carries out vehicle detection.
Controller 4 respectively with video camera 11 ... ..., video camera 1N, earth magnetism wagon detector 31 ... ..., ground magnetic vehicle inspection
Device 3M is surveyed, controller 4 includes above-mentioned parking detection device.
The present embodiment discloses another parking detecting system, shown in Figure 12, including：N includes：N number of video camera
(video camera 11 ... ..., video camera 1N), M earth magnetism wagon detector (earth magnetism wagon detector 31 ... ..., earth magnetism vehicle detection
Device 3M), controller 4 and display device 5 (being tablet computer shown in figure).
Wherein, display device 5 is connect with controller 4, for showing that vehicle target is completed into information.Display device 5 can
To be computer, it can also be the mobile terminals such as smart mobile phone or tablet computer, corresponding APP be set in mobile terminal, is used for
Vehicle target in controller 4 is obtained to complete into information.Vehicle target is completed into information to include but not limited to that vehicle target is complete
At at the time of entering, vehicle target completes the state etc. of the correspondence parking stall position into position.It is easily understood that when display device is
It when the mobile terminals such as smart mobile phone or tablet computer, is wirelessly connected with controller 4, and intelligent terminal passes through server with controller
Carry out data interaction.
For device embodiments, since it essentially corresponds to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separating component
The unit of explanation may or may not be physically separated, and the component shown as unit can be or can also
It is not physical unit, you can be located at a place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not
In the case of making the creative labor, you can to understand and implement.
Herein, relational terms such as first and second and the like be used merely to by an entity or operation with it is another
One entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this reality
Relationship or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or use the application.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or range.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (10)
1. a kind of parking detection method, which is characterized in that including：
Video frame is obtained from video camera, the video camera monitors its corresponding monitoring area in real time, the monitored space
Domain includes L parking stall position, and the L is positive number；
According to the video frame, monitor whether that, there are the first vehicle target, first vehicle target is in parking process；
After detecting there are first vehicle target, the license board information of first vehicle target is obtained；
According to the video frame, monitoring whether that there are the first vehicle targets includes：
The video frame is calculated using background modeling algorithm, obtains the foreground area of moving target；
Detect the second vehicle target in the foreground area；
Target following is carried out to second vehicle target, obtains the movement locus of second vehicle target；
According to the feature of the movement locus of second vehicle target, judge whether second vehicle target is in parking
Process；
Further include after the foreground area for obtaining moving target：
Feature point extraction is carried out to the foreground area；
If being more than predetermined threshold value in the number of the characteristic point of parking stall position, it is determined that the parking stall position is that there are moving targets
The first parking stall position；
If the movement locus region of first parking stall position and second vehicle target in parking process
It is identical, then judge whether the moving target existing for the position of first parking stall is vehicle target；
If the moving target existing for the position of first parking stall is vehicle target, it is determined that existing for first truck position
The vehicle target is the first vehicle target.
2. according to the method described in claim 1, it is characterized in that, also being wrapped after detecting there are first vehicle target
It includes：
Vehicle detection signal is obtained from earth magnetism wagon detector, the earth magnetism wagon detector corresponds to first vehicle target
The parking stall position at place；
When the vehicle detection signal is to detect the signal of vehicle, and the signal duration for detecting vehicle is more than in advance
If when time threshold, determining that first vehicle target is completed into position.
3. a kind of parking detection device, which is characterized in that including：
Image acquisition unit, for obtaining video frame from video camera, the video camera carries out its corresponding monitoring area real
When monitor, the monitoring area includes L parking stall position, and the L is positive number；
First vehicle target unit, for according to the video frame, monitoring whether that there are the first vehicle target, first vehicles
Target is in parking process；
Information of vehicles unit is obtained, for after detecting there are first vehicle target, obtaining first vehicle target
License board information；
The first vehicle target unit includes：
First foreground area unit obtains moving target for being calculated the video frame using background modeling algorithm
Foreground area；
Second vehicle target unit, for detecting the second vehicle target in the foreground area；
Movement locus unit obtains the fortune of second vehicle target for carrying out target following to second vehicle target
Dynamic rail mark；
First judging unit is used for the feature of the movement locus according to second vehicle target, judges the second vehicle mesh
Whether mark is in parking process；
The first vehicle target unit further includes：
Feature extraction unit, for carrying out feature point extraction to the foreground area；；
First parking stall unit, if the number for the characteristic point in parking stall position is more than predetermined threshold value, it is determined that the parking stall
Position is the first parking stall position there are moving target；
Second judgment unit, second vehicle target for judging first parking stall position with being in parking process
Movement locus region it is identical when, then be transferred to third judging unit；
Third judging unit, when for judging that the moving target is vehicle target existing for the position of first parking stall, then really
The vehicle target of fixed first parking stall position is the first vehicle target.
4. device according to claim 3, which is characterized in that described device further includes：
Geomagnetism detecting unit is obtained, for obtaining vehicle detection signal, the earth magnetism wagon detector from earth magnetism wagon detector
Corresponding to the parking stall position where first vehicle target；
Enter position and complete detection unit, for being to detect the signal of vehicle, and described detect vehicle when the vehicle detection signal
Signal duration be more than preset time when, determine that first vehicle target is completed into position.
5. a kind of parking detecting system, which is characterized in that including：N number of video camera and controller, the controller include such as
Parking detection device described in claim 3 or 4 any one, the N are positive integer.
6. system according to claim 5, which is characterized in that the system also includes：
M earth magnetism wagon detector being connect with the controller, each parking stall of earth magnetism wagon detector pair position carry out
Vehicle detection, the M are positive integer；
The parking detection device further includes：
Geomagnetism detecting unit is obtained, for obtaining vehicle detection signal, the earth magnetism wagon detector from earth magnetism wagon detector
Corresponding to the parking stall position where first vehicle target；
Enter position and complete detection unit, for being to detect the signal of vehicle, and described detect vehicle when the vehicle detection signal
Signal duration be more than preset time when, determine that first vehicle target is completed into position.
7. system according to claim 5 or 6, which is characterized in that the system also includes：It is connect with the controller
Display device, for showing that vehicle target is completed into information.
8. system according to claim 7, which is characterized in that the display device includes：Mobile terminal or computer.
9. system according to claim 8, which is characterized in that the mobile terminal includes：Smart mobile phone or tablet computer.
10. system according to claim 5 or 6, which is characterized in that the video camera is：Ball-shaped camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610391319.0A CN105894823B (en) | 2016-06-03 | 2016-06-03 | A kind of parking detection method and apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610391319.0A CN105894823B (en) | 2016-06-03 | 2016-06-03 | A kind of parking detection method and apparatus and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105894823A CN105894823A (en) | 2016-08-24 |
| CN105894823B true CN105894823B (en) | 2018-08-21 |
Family
ID=56710115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610391319.0A Active CN105894823B (en) | 2016-06-03 | 2016-06-03 | A kind of parking detection method and apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105894823B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678217A (en) * | 2015-12-29 | 2016-06-15 | 安徽海兴泰瑞智能科技有限公司 | Vehicle parking guidance positioning method |
| CN106446892A (en) * | 2016-09-13 | 2017-02-22 | 东软集团股份有限公司 | Vehicle license plate recognizing method, apparatus and charging pile |
| TWI633525B (en) * | 2016-12-09 | 2018-08-21 | 正文科技股份有限公司 | Parking position sensing device |
| CN106652551B (en) * | 2016-12-16 | 2021-03-09 | 浙江宇视科技有限公司 | Parking space detection method and equipment |
| CN107292277B (en) * | 2017-06-30 | 2020-08-21 | 深圳信路通智能技术有限公司 | Trackable method for roadside double-parking-space parking |
| CN107622672A (en) * | 2017-09-19 | 2018-01-23 | 智慧互通科技有限公司 | Roadside Parking management equipment and method based on earth magnetism and video camera array linkage |
| CN108520236A (en) * | 2018-04-09 | 2018-09-11 | 迪蒙智慧交通（深圳）有限公司 | It drives into and outgoing vehicles information collecting method, device and information of vehicles processing system |
| CN110097651A (en) * | 2019-05-06 | 2019-08-06 | 杨洪文 | Vehicle parking management charge system and management method |
| CN110473426A (en) * | 2019-08-20 | 2019-11-19 | 北京精英路通科技有限公司 | Parking management method, device, computer equipment and storage medium |
| CN112150857B (en) * | 2020-08-21 | 2021-10-08 | 山东科技大学 | Parking position indicating system and method based on video image processing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663357A (en) * | 2012-03-28 | 2012-09-12 | 北京工业大学 | Color characteristic-based detection algorithm for stall at parking lot |
| CN103700283A (en) * | 2014-01-09 | 2014-04-02 | 北京交通发展研究中心 | Geomagnetic sensor parking monitoring method |
| CN104966045A (en) * | 2015-04-02 | 2015-10-07 | 北京天睿空间科技有限公司 | Video-based airplane entry-departure parking lot automatic detection method |
| CN105390021A (en) * | 2015-11-16 | 2016-03-09 | 北京蓝卡科技股份有限公司 | Parking spot state detection method and parking spot state detection device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9514366B2 (en) * | 2014-02-03 | 2016-12-06 | Xerox Corporation | Vehicle detection method and system including irrelevant window elimination and/or window score degradation |
-
2016
- 2016-06-03 CN CN201610391319.0A patent/CN105894823B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663357A (en) * | 2012-03-28 | 2012-09-12 | 北京工业大学 | Color characteristic-based detection algorithm for stall at parking lot |
| CN103700283A (en) * | 2014-01-09 | 2014-04-02 | 北京交通发展研究中心 | Geomagnetic sensor parking monitoring method |
| CN104966045A (en) * | 2015-04-02 | 2015-10-07 | 北京天睿空间科技有限公司 | Video-based airplane entry-departure parking lot automatic detection method |
| CN105390021A (en) * | 2015-11-16 | 2016-03-09 | 北京蓝卡科技股份有限公司 | Parking spot state detection method and parking spot state detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105894823A (en) | 2016-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894823B (en) | A kind of parking detection method and apparatus and system | |
| CN205680289U (en) | A kind of parking detecting system | |
| CN102254429B (en) | Video identification-based detection method of detection device of violation vehicles | |
| CN103400500B (en) | Vehicle information data acquisition device and method | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| CN105894529B (en) | Parking space state detection method and apparatus and system | |
| CN104103030B (en) | Image analysis method, camera apparatus, control apparatus and control method | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| JP2013218679A (en) | Video-based detection device and notification device for catching short-time parking violation | |
| CN107845289A (en) | A kind of Roadside Parking management and charging system based on height digital video array | |
| CN103376336A (en) | Method and system for measuring vehicle running speed | |
| CN103021182B (en) | Method and device for monitoring motor vehicle in case of regulation violation for running red light | |
| CN111932901A (en) | Road vehicle tracking detection apparatus, method and storage medium | |
| KR101051005B1 (en) | An apparatus and a system regulating an illegal stopping or parking car and a method controlling the same | |
| CN106023594A (en) | Parking stall shielding determination method and device and vehicle management system | |
| CN107977596A (en) | A kind of car plate state identification method and device | |
| CN112562406B (en) | Method and device for identifying off-line driving | |
| CN110246336A (en) | The determination method and system of information of vehicles | |
| CN109446926A (en) | A kind of traffic monitoring method and device, electronic equipment and storage medium | |
| CN110111582A (en) | Multilane free-flow vehicle detection method and system based on TOF camera | |
| CN103886761B (en) | Intelligent bayonet system and the operation method thereof of road exception parking can be found fast | |
| CN113990101B (en) | Method, system and processing device for detecting vehicles in no-parking area | |
| CN105869413A (en) | Method for measuring traffic flow and speed based on camera video | |
| CN110880205A (en) | Parking charging method and device | |
| KR101736431B1 (en) | System and Method for Smart Traffic Monitoring Using Multiple Image |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200728 Address after: Room 101, 2 / F, building 17, No. 17, huanke Middle Road, Tongzhou District, Beijing Patentee after: Beijing Elite Road Technology Co.,Ltd. Address before: 100000 Beijing city Haidian District West Road No. 27 small business Qinghe small Haisheng C block second layer Patentee before: BEIJING JAYA TECHNOLOGY Co.,Ltd. |