CN104376742B - A kind of parking space state detection method and system - Google Patents
A kind of parking space state detection method and system Download PDFInfo
- Publication number
- CN104376742B CN104376742B CN201410722858.9A CN201410722858A CN104376742B CN 104376742 B CN104376742 B CN 104376742B CN 201410722858 A CN201410722858 A CN 201410722858A CN 104376742 B CN104376742 B CN 104376742B
- Authority
- CN
- China
- Prior art keywords
- space state
- parking space
- vehicle
- image
- 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.)
- Expired - Fee Related
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 claims abstract description 41
- 230000003287 optical effect Effects 0.000 claims abstract description 19
- 238000007689 inspection Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
Abstract
The invention discloses a kind of parking space state detection method, parking position monitoring image is analyzed and processed, determine whether that object passes in and out parking stall using optical flow method, current parking space state is kept during without disengaging parking stall object, and the object that marginal density detection method judges to pass in and out parking stall is used to update parking space state, the invention also discloses a kind of parking space state detecting system whether for vehicle, including image processing module, image processing module includes：Initialization module, motion estimation module, car plate detection module and marginal density detection module；Using the method for detecting parking stalls and system of the present invention, avoid and the strong jamming such as ditch background is mistaken for vehicle, there is strong robustness, strong antijamming capability, it is accurate to detect fast results.
Description
Technical field
The present invention relates to picture control process field, more particularly to a kind of parking space state detection method and system.
Background technology
Parking stall measure technology is that one kind detects whether parking space state has car i.e. on parking stall by external equipment, and parking stall
State is sent to the technology that display device is shown.
At present, in the market has a variety of method for detecting parking stalls, and common method has carries out parking stall inspection using infrared ray, ultrasonic wave
Survey and induction coil is buried on the ground of parking stall, but these methods are affected by environment larger, easily become in environment
Dynamic occasion such as outdoor parking space, carries out the parking stall measure easily disturbed error for causing result, can not accurately and reliably detect
Parking space state.
The content of the invention
In view of this, can be accurate it is a primary object of the present invention to provide a kind of parking space state detection method and system
Reliably detect parking space state.
To achieve the above object, the present invention provides a kind of parking space state detection method, including：
Judge whether image is the first two field picture, optical flow method and parking space state are if it is initialized, if otherwise calculated
And determine the strong angle point in previous frame；
Strong angle point described in front and rear frame is judged with the presence or absence of movement using optical flow method, if it is, determining there is thing on parking stall
Body moves, if it is not, then keeping current parking space state；
One total direction of motion is estimated to all strong angle points, judges whether edge passes in and out parking stall side to the direction of motion
To if it is, the object disengaging parking stall is determined, if it is not, then keeping current parking space state；
Whether the object for judging to pass in and out parking stall is vehicle；
Whether the object for judging to pass in and out parking stall is that vehicle includes：
Detect whether the object is vehicle using marginal density detection method, if it is, determine that the object is vehicle,
Parking space state is updated, if it is not, then keeping current parking space state.
Preferably, it is described to detect whether the object is that vehicle includes using marginal density detection method：
Obtain the gradient image of present frame gray image；
Seek the gradient integrogram of the gradient image；
The gradient integrogram is searched for respectively using the search box of multiple default dimensionings, preserves integrated value more than presetting
The point of threshold value；
To the region clustering preserved, judge whether the region after cluster has light stream campaign, if it is determine described
Object is vehicle, parking space state is updated, if it is not, then keeping current parking space state.
Preferably, whether the object for judging to pass in and out parking stall is that vehicle includes：
Judge whether to detect that object has car plate, the object for if it is determining disengaging parking stall is to have board car
, parking space state is updated, if it is not, then detecting whether the object is vehicle using marginal density detection method, if it is, really
The fixed object is vehicle, parking space state is updated, if it is not, then keeping current parking space state.
Preferably, it is described to judge whether image is to further include acquisition image before the first two field picture.
Preferably, the image for obtaining image and including obtaining analog video camera or digital camera collection.
Preferably, whether the object for judging to pass in and out parking stall is to further include after vehicle to receive the result judged and shown
Show.
Present invention also offers a kind of parking space state detecting system, including judge according to image the image procossing of parking space state
Module；
Described image processing module includes：
Initialization submodule, estimation submodule and marginal density detection sub-module；
Optical flow method and parking space state are initialized when the initialization submodule is used to judge image for the first two field picture；
Strong angle point when the estimation submodule is used to non-first two field picture be calculated and determined in previous frame, uses light
The strong angle point before and after stream method judges in frame is with the presence or absence of movement, if it is, determine there is object of which movement on parking stall, if
It is no, then current parking space state is kept, a total direction of motion is estimated to all strong angle points, judges that the direction of motion is
No edge disengaging parking stall direction, if it is, the object disengaging parking stall is determined, if it is not, then keeping current parking space state；
The marginal density detection sub-module is used to detect the object for passing in and out parking stall using marginal density detection method
No is vehicle, if it is, determining that the object is vehicle, updates parking space state.
Preferably, the parking space state detecting system further includes：Car plate detection submodule, for judging whether to detect
There is car plate to object, the object for if it is determining disengaging parking stall is to have board vehicle, updates parking space state, if it is not, then
Detect whether the object is vehicle using marginal density detection method by marginal density detection sub-module, if it is, determining institute
It is vehicle to state object, parking space state is updated, if it is not, then keeping current parking space state.
Preferably, the parking space state detecting system further includes：Image capture module, for obtaining image.
Preferably, the parking space state detecting system further includes：Parking space state display module, for judging disengaging parking stall
Whether the object is to receive the result of judgement after vehicle and shown.
Using parking space state detection method provided by the invention and system, parking position monitoring image is analyzed and processed, is adopted
Determine whether that object passes in and out parking stall with optical flow method, when no disengaging parking stall object keeps current parking space state, and uses edge
Whether the object that Density Detection method judges to pass in and out parking stall is vehicle, more new car when the object for detecting disengaging parking stall is vehicle
Position state, into parking stall and is gone out renewal of two kinds of the parking stall motion state to parking space state and is detected judgement using vehicle on parking stall,
Avoid and the strong jamming such as ditch background is mistaken for vehicle, there is strong robustness, strong antijamming capability, detection fast results standard
Really.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is an a kind of flow chart of parking space state detection method of the present invention；
Fig. 2 is an a kind of detail flowchart of parking space state detection method of the present invention；
Fig. 3 is a kind of another detail flowchart of parking space state detection method of the present invention；
Fig. 4 is a kind of another detail flowchart of parking space state detection method of the present invention；
Fig. 5 is a kind of another flow chart of parking space state detection method of the present invention；
Fig. 6 is an a kind of structure diagram of parking space state detecting system of the present invention；
Fig. 7 is a kind of another structure diagram of parking space state detecting system of the present invention；
Fig. 8 is a kind of another structure diagram of parking space state detecting system of the present invention.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment, belongs to the scope of protection of the invention.
The present invention provides a kind of parking space state detection method, as depicted in figs. 1 and 2, is detected for parking space state of the present invention
The flow chart of embodiment of the method, including：
Step S101：Judge whether image is the first two field picture, if yes then enter step S102, if otherwise entering step
Rapid S103；
Image is analyzed, judges whether current frame image is the first frame.
Step S102：Initialize optical flow method and parking space state；
Parameter and the parking space state of the current parking stall that optical flow method needs, i.e. car are initialized when current frame image is the first frame
Whether there is car on position.
Step S103：The strong angle point in previous frame is calculated and determined；
When present frame is not the first frame, the strong angle point determined in previous frame is calculated, Shi-Tomasi method meters can be utilized
Calculate previous frame in be easy to tracking strong angle point, strong corner description be by this put centered on around there are at least two different directions
Texture, there is Shift invariance, rotational invariance, illumination invariant.
Step S104：Strong angle point described in front and rear frame is judged with the presence or absence of movement using optical flow method, if it is, entering step
Rapid S105, if it is not, then entering step S106；
Calculate the light stream campaign of strong angle point, the movement of strong angle point calculated with reference to previous frame and present frame, can use than
More ripe Lucas-Kanade (abbreviation LK) optical flow method, the method are to seek a kind of important method of sparse optical flow, mainly base
In three kinds of hypothesis：
(a) brightness constancy：Refer to and tracked partial pixel do not changed over time and is changed,
F (x, t)=I (x (t), t)=I (x (t+dt), t+dt)；
(b) Time Continuous：Refer to that the movement between consecutive frame is smaller；
(c) space is consistent:Refer to that the neighbor point in a scene on same surface has similar movement.
The tracking of larger movement is can solve using pyramid LK optical flow approach.
Step S105：Determine there is object of which movement on parking stall；
If strong angle point movement, illustrates there is the object of movement on parking stall, whether the object of movement is that vehicle is needed into one
Step is demonstrate,proved.
Step S106：Keep current parking space state；
If strong angle point illustrates do not have moving object on the parking stall, keeps the current car in the parking stall there is no movement
Position state is constant.
Step S107：One total direction of motion is estimated to all strong angle points, judge the direction of motion whether edge
Parking stall direction is passed in and out, if it is, S108 is entered step, if it is not, then entering step S109；
According to the overall movement direction of the estimation object of required strong angle point in previous step, judge the direction of motion whether be
The direction of parking stall is passed in and out, an angle threshold can be set, side of the direction of motion for disengaging parking stall is represented in this angle threshold
To.
Step S108：Determine the object disengaging parking stall；
If the direction of object of which movement is the direction of disengaging parking stall, it can be determined that moving object passes in and out parking stall.
Step S109：Keep current parking space state；
If the direction of object of which movement is not into and out the direction of parking stall, it may be possible to which the movement of chaff interferent, is not vehicle, then protects
Hold current parking space state.
Step S110：Whether the object for judging to pass in and out parking stall is vehicle.
Whether the object for determining whether disengaging parking stall is vehicle to determine parking space state.
As shown in Fig. 2, be the detail flowchart of step S108, including：
Step S201：Detect whether the object is vehicle using marginal density detection method, if it is, entering step
S202, if it is not, then entering step S203；
The object for passing in and out parking stall is detected using marginal density detection method, further verifies whether the object is car
.
Step S202：It is vehicle to determine the object, updates parking space state；
Detect that then moving object is vehicle to vehicle using marginal density detection method, update parking space state.
Step S203：Keep current parking space state.
Vehicle is not detected by using marginal density detection method and then illustrates no vehicles while passing parking stall, keeps current parking space state not
Become.
Using parking space state detection method provided in this embodiment, the monitoring image of parking stall is analyzed and processed, is used
Optical flow method determines whether that object passes in and out parking stall, and when no disengaging parking stall object keeps current parking space state, and close using edge
Whether the object that degree detection method judges to pass in and out parking stall is vehicle, and the object for detecting disengaging parking stall updates parking stall when being vehicle
State, into parking stall and is gone out renewal of two kinds of the parking stall motion state to parking space state and is detected judgement, kept away using vehicle on parking stall
Exempt from the strong jamming such as ditch background being mistaken for vehicle, there is strong robustness, strong antijamming capability, it is accurate to detect fast results.
As shown in figure 3, be the detail flowchart of marginal density detection method, including：
Step S301：Obtain the gradient image of present frame gray image；
Horizontal direction gradient image and vertical gradient image are asked to present frame gray image：Gx (i, j)=abs
(gray (i-1, j)-gray (i+1, j)), Gy (i, j)=abs (gray (i, j-1)-gray (i, j+1)),
For horizontal gradient image and vertical gradient image, it is weighted, obtains gradient image G (i, j)：
G (i, j)=a*Gx (i, j)+(1-a) Gy (i, j), wherein weights
Step S302：Seek the gradient integrogram of the gradient image；
Seek the integrogram Gi (x, y) of Gt (x, y).
Step S303：The gradient integrogram is searched for respectively using the search box of multiple default dimensionings, preserves integrated value
More than the point of pre-set threshold；
Multiple dimensioned frame searches for gradient integrogram, in order to obtains the region of integrated value maximum, judges whether parking stall has
Car, specific implementation method are：
(a) the search box R1, R2 ..., Rn of n different scale are set, in order to meet different size of vehicle, increase
The adaptability of strong algorithms.
(b) weight factor S1, the S2 that n search box corresponds to integrated value are set ..., Sn, it is intended that in order to different scale
The integrated value in space is transformed into same metric space and goes to compare.
(c) full figure is traveled through using each search box, preserves the integrated value Vn (i, j) of correspondence position.Vn if (i, j) * Sn>
T, then preserve this search box, otherwise do not preserve, and wherein T is self-defined threshold value.
Step S304：To the region clustering preserved；
The region remained is clustered, obtains several cluster groups, illustrates there are several doubtful vehicle regions, therefore
Also need to carry out a step card.
Step S305：Judge whether the region after cluster has light stream campaign, if it is, S306 is entered step, if not,
Then enter step S307；
Light stream campaign is determined whether to the cluster areas of acquisition.
Step S306：It is unlicensed vehicle to determine the object, updates parking space state；
If there is light stream campaign, then the object for passing in and out parking stall is determined as unlicensed vehicle, updates parking space state.
Step S307：Then keep current parking space state.
If no light stream campaign, it may be strongly disturbing background, keep current parking space state.
As shown in figure 4, be the detail flowchart of step S108 another kind embodiments in Fig. 1, including：
Step S401：Judge whether to detect that object has car plate, if it is, S402 is entered step, if it is not, then
Enter step S403；
Car plate most significantly indicates for a vehicle, here using car plate detection method, to passing in and out the object of parking stall into driving
Board detects, and whether the object for judging to pass in and out parking stall has car plate.
Step S402：Determine that the object of disengaging parking stall to there is board vehicle, updates parking space state；
There is car plate if detecting the object of disengaging parking stall, can determine the object of disengaging parking stall to there is board vehicle, it is right
Current parking space state is updated, such as the parking space state before renewal has car for parking stall, after having detected board vehicles while passing parking stall
It is no car to update parking space state.
Step S403：Detect whether the object is vehicle using marginal density detection method, if it is, entering step
S404, if it is not, then entering step S405；
If do not detect disengaging parking stall object have car plate, have one kind be probably vehicle do not register the license also, it is necessary to using
Marginal density detection method is detected the object for passing in and out parking stall, is further verified.
Step S404：It is unlicensed vehicle to determine the object, updates parking space state；
Detect that then moving object is unlicensed vehicle to vehicle using marginal density detection method, update parking space state.
Step S405：Keep current parking space state.
Vehicle is not detected by using marginal density detection method and then illustrates no vehicles while passing parking stall, keeps current parking space state not
Become.
Vehicle, which may be divided into, has licence plate and two kinds of situations of unlicensed, when vehicle has licence plate, it is true can directly to detect licence plate
Whether fixed be vehicle, and method is more convenient quick, improves detection efficiency, and marginal density detection is reused when being not detected by licence plate
Method, it is as a result more precisely reliable.
As shown in figure 5, for the flow chart of parking space state detection method specific embodiment of the present invention, corresponding to Fig. 1, also wrap
Include：
Step S100：Obtain image.
The present invention is that the image on the parking stall that monitors is analyzed, and can utilize charge coupled cell CCD or complementation
Metal-oxide semiconductor (MOS) COMS sensor devices image-forming principle obtains image, can use analog video camera or digital camera here
The equipment such as machine obtain image.
Step S111：Receive the result judged and shown.
Parking space state judge detection after whether kept parking space state information or update parking space state information as a result,
Receive result and show, can also further be responded.
Present invention also offers a kind of parking space state detecting system, as shown in fig. 6, being parking space state detecting system of the present invention
Structure diagram, including judge according to image the image processing module of parking space state；
Described image processing module includes：
Initialization submodule 101, estimation submodule 102 and marginal density detection sub-module 103；
Optical flow method and parking space state are initialized when the initialization submodule 101 is used to judge image for the first two field picture；
Strong angle point when the estimation submodule 102 is used to non-first two field picture be calculated and determined in previous frame, makes
Judge that the strong angle point in front and rear frame whether there is movement with optical flow method, if it is, determining there is object of which movement on parking stall, such as
Fruit is no, then keeps current parking space state, estimates a total direction of motion to all strong angle points, judges the direction of motion
Whether along disengaging parking stall direction, if it is, the object disengaging parking stall is determined, if it is not, then keeping current parking space state；
The marginal density detection sub-module 103 is used for the object using marginal density detection method detection disengaging parking stall
Whether it is vehicle, if it is, determining that the object is vehicle, updates parking space state.
Image processing module in the present embodiment belongs to algoritic module, mainly using ARM or DSP platform as carrier, loading
Image processing algorithm, when acquisition module exports an image to image processing module, after image processing module is handled, output
There is car without car state in parking stall.
Using parking space state detecting system provided in this embodiment, the monitoring image of parking stall is analyzed and processed, is used
Optical flow method determines whether that object passes in and out parking stall, and when no disengaging parking stall object keeps current parking space state, and close using edge
Whether the object that degree detection method judges to pass in and out parking stall is vehicle, and the object for detecting disengaging parking stall updates parking stall when being vehicle
State, into parking stall and is gone out renewal of two kinds of the parking stall motion state to parking space state and is detected judgement, kept away using vehicle on parking stall
Exempt from the strong jamming such as ditch background being mistaken for vehicle, there is strong robustness, strong antijamming capability, it is accurate to detect fast results.
As shown in fig. 7, the structure diagram of the specific embodiment for parking space state detecting system of the present invention, corresponding to figure
6, further include：
Car plate detection submodule 104, for detect disengaging parking stall the object whether have car plate, if it is determine into
Go out the object of parking stall to there is board vehicle, update parking space state.
Vehicle, which may be divided into, has licence plate and two kinds of situations of unlicensed, when vehicle has licence plate, it is true can directly to detect licence plate
Whether fixed be vehicle, and method is more convenient quick, improves detection efficiency, and marginal density detection is reused when being not detected by licence plate
Method, it is as a result more precisely reliable.
As shown in figure 8, the structure diagram of the specific embodiment for parking space state detecting system of the present invention, corresponding to figure
7, further include：
Image capture module 105, for obtaining image；
Image capture module is to obtain image using CCD or COMS sensor devices image-forming principle, refers here to simulation and takes the photograph
The equipment such as camera or digital camera.
Parking space state display module 106, whether the object for judging to pass in and out parking stall is to receive what is judged after vehicle
As a result and shown.
Parking space state display module receives the parking space state information of image processing module outflow, is shown, can also given
Do well response.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference with other embodiment, between each embodiment identical similar part mutually referring to.
For system embodiment, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to method
The part explanation of embodiment.
Finally, it is to be noted that, herein, term " comprising ", "comprising" or its any other variant are intended to
Cover non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only include those
Key element, but also including other elements that are not explicitly listed, or further include as this process, method, article or set
Standby intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Also there are other identical element in the process, method, article or apparatus that includes the element.
Parking space state detection method provided by the present invention and system are described in detail above, it is used herein
Specific case is set forth the principle of the present invention and embodiment, and the explanation of above example is only intended to help to understand this
The method and its core concept of invention；Meanwhile for those of ordinary skill in the art, according to the thought of the present invention, specific
There will be changes in embodiment and application range, in conclusion this specification content should not be construed as to the present invention's
Limitation.
Claims (9)
- A kind of 1. parking space state detection method, it is characterised in that including：Judge whether image is the first two field picture, if it is initialize optical flow method and parking space state, if otherwise calculated and true Determine the strong angle point in previous frame；Strong angle point described in front and rear frame is judged with the presence or absence of movement using optical flow method, if it is, determining there is object fortune on parking stall It is dynamic, if it is not, then keeping current parking space state；One total direction of motion is estimated to all strong angle points, judges whether edge passes in and out parking stall direction to the direction of motion, If it is, the object disengaging parking stall is determined, if it is not, then keeping current parking space state；Whether the object for judging to pass in and out parking stall is vehicle；Whether the object for judging to pass in and out parking stall is that vehicle includes：Detect whether the object is vehicle using marginal density detection method, if it is, determine that the object is vehicle, renewal Parking space state, if it is not, then keeping current parking space state.
- 2. parking space state detection method according to claim 1, it is characterised in that described to utilize the inspection of marginal density detection method Survey whether the object is that vehicle includes：Obtain the gradient image of present frame gray image；Seek the gradient integrogram of the gradient image；The gradient integrogram is searched for respectively using the search box of multiple default dimensionings, is preserved integrated value and is more than pre-set threshold Point；To the region clustering preserved, judge whether the region after cluster has light stream campaign, if it is determine the object For vehicle, parking space state is updated, if it is not, then keeping current parking space state.
- 3. parking space state detection method according to claim 1, it is characterised in that described to judge whether image is the first frame Acquisition image is further included before image.
- 4. parking space state detection method according to claim 3, it is characterised in that the acquisition image, which includes obtaining, simulates Video camera or the image of digital camera collection.
- 5. parking space state detection method according to claim 4, it is characterised in that judging the object of disengaging parking stall is It is no be vehicle after further include receive judge result and shown.
- A kind of 6. parking space state detecting system, it is characterised in that the image processing module including judging parking space state according to image；Described image processing module includes：Initialization submodule, estimation submodule and marginal density detection sub-module；Optical flow method and parking space state are initialized when the initialization submodule is used to judge image for the first two field picture；Strong angle point when the estimation submodule is used to non-first two field picture be calculated and determined in previous frame, uses optical flow method The strong angle point before and after judgement in frame is with the presence or absence of movement, if it is, determine there is object of which movement on parking stall, if it is not, then Keep current parking space state, a total directions of motion estimated to all strong angle points, judge the direction of motion whether edge Parking stall direction is passed in and out, if it is, the object disengaging parking stall is determined, if it is not, then keeping current parking space state；The marginal density detection sub-module be used for using marginal density detection method detect disengaging parking stall the object whether be Vehicle, if it is, determining that the object is vehicle, updates parking space state.
- 7. parking space state detecting system according to claim 6, it is characterised in that further include：Car plate detection submodule, is used In judging whether to detect that object has car plate, if it is determine that the object of disengaging parking stall to there is board vehicle, updates Parking space state, if it is not, then detecting whether the object is car using marginal density detection method by marginal density detection sub-module , if it is, determining that the object is vehicle, parking space state is updated, if it is not, then keeping current parking space state.
- 8. parking space state detecting system according to claim 7, it is characterised in that further include：Image capture module, is used for Obtain image.
- 9. parking space state detecting system according to claim 8, it is characterised in that further include：Parking space state display module, Whether the object for judging to pass in and out parking stall is to receive the result of judgement after vehicle and shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410722858.9A CN104376742B (en) | 2014-12-02 | 2014-12-02 | A kind of parking space state detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410722858.9A CN104376742B (en) | 2014-12-02 | 2014-12-02 | A kind of parking space state detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104376742A CN104376742A (en) | 2015-02-25 |
| CN104376742B true CN104376742B (en) | 2018-05-01 |
Family
ID=52555626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410722858.9A Expired - Fee Related CN104376742B (en) | 2014-12-02 | 2014-12-02 | A kind of parking space state detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104376742B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504580A (en) * | 2016-12-07 | 2017-03-15 | 深圳市捷顺科技实业股份有限公司 | A kind of method for detecting parking stalls and device |
| TWI671707B (en) * | 2018-06-15 | 2019-09-11 | 緯創資通股份有限公司 | Image analysis method, electronic system and non-transitory computer-readable recording medium |
| CN109686110A (en) * | 2019-01-17 | 2019-04-26 | 蜂寻（上海）信息科技有限公司 | Parking stall sky expires condition discrimination method and apparatus |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110376B (en) * | 2011-02-18 | 2012-11-21 | 汤一平 | Roadside parking space detection device based on computer vision |
| CN102426801A (en) * | 2011-12-12 | 2012-04-25 | 天津世纪晨实科技有限公司 | Automatic parking lot berth management method and system based on visual analysis |
| US8744132B2 (en) * | 2012-04-06 | 2014-06-03 | Orhan BULAN | Video-based method for detecting parking boundary violations |
| KR101522026B1 (en) * | 2012-12-11 | 2015-05-22 | 코스텍코리아 주식회사 | Method for managing to going out vehicle of parking system and system for the same |
| CN104112370B (en) * | 2014-07-30 | 2016-08-17 | 哈尔滨工业大学深圳研究生院 | Parking lot based on monitoring image intelligent car position recognition methods and system |
| CN104376741B (en) * | 2014-12-02 | 2017-03-22 | 深圳市捷顺科技实业股份有限公司 | Parking lot state detection method and system |
-
2014
- 2014-12-02 CN CN201410722858.9A patent/CN104376742B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN104376742A (en) | 2015-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104376741B (en) | Parking lot state detection method and system | |
| JP7052663B2 (en) | Object detection device, object detection method and computer program for object detection | |
| US9070023B2 (en) | System and method of alerting a driver that visual perception of pedestrian may be difficult | |
| US9646212B2 (en) | Methods, devices and systems for detecting objects in a video | |
| CN108182396B (en) | Method and device for automatically identifying photographing behavior | |
| US20180341823A1 (en) | Processing method for distinguishing a three dimensional object from a two dimensional object using a vehicular system | |
| US11030464B2 (en) | Privacy processing based on person region depth | |
| CN104103030B (en) | Image analysis method, camera apparatus, control apparatus and control method | |
| JP6261266B2 (en) | Moving body detection device | |
| CN103366155B (en) | Temporal coherence in unobstructed pathways detection | |
| US20180268225A1 (en) | Processing apparatus and processing system | |
| CN104376742B (en) | A kind of parking space state detection method and system | |
| CN105740792B (en) | Object detection method and device | |
| CN112270719A (en) | Camera calibration method, device and system | |
| CN109993134A (en) | A kind of intersection vehicle checking method based on HOG and SVM classifier | |
| CN104471436B (en) | The method and apparatus of the variation of imaging scale for computing object | |
| CN112399046B (en) | Object detection device and method | |
| JP7030451B2 (en) | Image processing equipment | |
| JP5870266B2 (en) | Calibration apparatus and calibration method | |
| JP2002027449A (en) | Method and apparatus for identifying moving object | |
| Rachman et al. | Camera Self-Calibration: Deep Learning from Driving Scenes | |
| US20130223692A1 (en) | Method for logo detection in memc | |
| JP2002027480A (en) | Dynamic image processing method and apparatus thereof | |
| JP2004208209A (en) | Device and method for monitoring moving body | |
| JP2003296877A (en) | Sensor selection method using data certainty, and road traffic monitoring system using the same |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180501 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |