CN105390021B - The detection method and device of parking space state - Google Patents
The detection method and device of parking space state Download PDFInfo
- Publication number
- CN105390021B CN105390021B CN201510783507.3A CN201510783507A CN105390021B CN 105390021 B CN105390021 B CN 105390021B CN 201510783507 A CN201510783507 A CN 201510783507A CN 105390021 B CN105390021 B CN 105390021B
- Authority
- CN
- China
- Prior art keywords
- parking space
- image information
- space state
- detection
- stable state
- 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
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/143—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces inside the vehicles
Abstract
The invention discloses a kind of detection method and device of parking space state, including：Obtain the stable state image information of parking stall to be detected；The scene residing for parking stall is classified according to the display content in the stable state image information, and the parking space state judgment mode according to corresponding to the selection of the result of the scene classification, to obtain parking space state.Beneficial effects of the present invention are：By the way that the display content in stable state image information is compared, and scene classification, it can faster and more accurately obtain parking space state.
Description
Technical field
The present embodiments relate to technical field of data processing, more particularly to a kind of computational methods of parking space state detection and
Device.
Background technology
Parking space state detection technique is one kind detects whether occupy vehicle on parking stall by external equipment, and parking stall shape
State is sent to a kind of technology shown on car-mounted terminal.
At present, the existing a variety of parking space state detection methods of in the market, conventional method have using infrared ray, ultrasonic wave and
No matter the mode of earth coil detection, take foregoing any detection mode, be required in each parking stall to be detected
The device such as the matched information of either above or below construction and installation and transmission, these devices are by each parking stall Parking situation
Simple information upper control computer is transmitted to by dedicated network circuit, and then sent instructions to after being judged by host computer aobvious
Show end, the device that these detection modes need needs construction, and need periodic maintenance in advance, spends a large amount of expenses.
When being detected by earth induction detection mode, it is necessary to the Geomagnetic signal to collection carried out again after averaging statistics and
Calculate, chain reaction can be caused if value mistake, influences the detection to parking space state, causes to judge by accident on a large scale, and it is right
In the detection mode such as infrared ray and ultrasonic wave, some takes optical flow method to be judged, its is affected by environment larger, carries out parking stall
Easily it is interfered during state-detection and causes the error of result, can not accurately and reliably detects parking space state.
And the video frequency car position detection technique for gradually rising, then car-mounted terminal is mainly handled by image algorithm and grabbed in real time
The image of bat, judge whether current parking stall is occupied by whether there is car plate in the image to parking stall to be detected, this method base
Originally the detection of parking space state can be realized, but in actual applications, it is long run time to be present in this method, it is impossible to faster
Respond the change of current parking space state, and to unlicensed car, drive into the car during rolling away from, stop the car before stopping partially all can not be just
Really grab car plate, or car plate has been blocked in someone station in Chinese herbaceous peony, the occlusion passed through on road camera, or
The situation that parking stall is taken by other barriers only can not accurately equally provide judgement by Recognition Algorithm of License Plate, thus only
Relying on Recognition Algorithm of License Plate can not be comprehensive, quickly, correctly judges current parking space state.
The content of the invention
The present invention provides a kind of detection method and device of parking space state, faster and more accurately to detect the state of parking stall.
In a first aspect, the embodiments of the invention provide a kind of detection method of parking space state, the detection method includes：
Obtain the stable state image information of parking stall to be detected；
The scene residing for parking stall is classified according to the display content in the stable state image information, and according to the field
Parking space state judgment mode corresponding to the result selection of scape classification, to obtain parking space state.
The detection method of above-mentioned parking space state, further, before the stable state image information of parking stall to be detected is obtained,
Also include：
Obtain the continuous image information of parking stall to be detected；
When the continuous image information of acquisition is consistent, judges and select one of described consecutive image information to be used as steady state picture
As information.
The detection method of above-mentioned parking space state, further, the parking space state judgment mode are sentenced including background detection
Disconnected mode, skin texture detection judgment mode or classification and Detection judgment mode, wherein：
The background detection judgment mode, including：By download parking stall to be detected without vehicle context figure, the nothing
Vehicle context figure and the stable state image information, draw parking space state；
The skin texture detection judgment mode, including：Whether included according in the display content in the stable state image information
There is centrality texture, draw parking space state；
The classification and Detection judgment mode, including：By classifying to display content in the stable state image information, obtain
Go out parking space state.
The detection method of above-mentioned parking space state, further, when skin texture detection judges, by downloading parking stall to be detected
Without vehicle context figure, with reference to whether including collection in display content in the no vehicle context figure, the stable state image information
Neutral texture and environmental information, judge parking space state.
The detection method of above-mentioned parking space state, further, according to car corresponding to the selection of the result of the scene classification
Position condition adjudgement mode, to obtain parking space state, including：
According to the result of the scene classification, at least one preferred embodiment and extremely of selection parking space state judgment mode is drawn
Few one kind time selects mode；
When the unfavorable factor for influenceing the preferred embodiment is not present in the display content in the stable state image information, then
Parking space state is judged using the preferred embodiment, to draw parking space state；
When the unfavorable factor for influenceing the preferred embodiment during the steady state picture is as informational display be present, then institute is selected
State and time select mode to judge parking space state, to draw parking space state.
The detection method of above-mentioned parking space state, further, the display content in the stable state image information are at least wrapped
Include：Environmental information, biological information and information of vehicles.
On the other hand, a kind of detection means of parking space state, the detection means bag are additionally provided in the embodiment of the present invention
Include：
Image acquisition unit, obtain the stable state image information of parking stall to be detected；
Scene classification unit, for being carried out according to the display content in the stable state image information to the scene residing for parking stall
Classification；
Judge selecting unit, including parking space state judging unit, the judgement selecting unit is used for according to the scene point
The classification results of class unit select the parking space state judgment mode of the parking space state judging unit, to obtain parking space state.
The detection means of above-mentioned parking space state, the parking space state judging unit include background detection judging unit, line
Reason detection judging unit and classification and Detection judging unit：
The background detection judging unit, for by download parking stall to be detected without vehicle context figure, the nothing
Vehicle context figure and the stable state image information, draw parking space state；
The skin texture detection judging unit, for when whether including centrality in the display content in stable state image information
Texture, draw the parking space state；
The classification and Detection judging unit, for by classifying to display content in the stable state image information, obtaining
Go out parking space state.
The detection means of above-mentioned parking space state, the judgement selecting unit also include intelligent selection unit, the intelligence
Selecting unit is used for：
According to the result of the scene classification, at least one preferred embodiment and extremely of selection parking space state judgment mode is drawn
Few one kind time selects mode；
When the unfavorable factor for influenceing the preferred embodiment is not present in the display content in the stable state image information, then
Parking space state is judged using the preferred embodiment, to draw parking space state；
When the unfavorable factor for influenceing the preferred embodiment during the steady state picture is as informational display be present, then institute is selected
State and time select mode to judge parking space state, to draw parking space state.
The detection means of above-mentioned parking space state, the display content for the stable state elementary area that described image acquiring unit obtains
Comprise at least：Environmental information, biological information and information of vehicles.
The present invention obtains the stable state image information of parking stall by video technique, by analyzing the display in stable state image information
The distributing position of the pixel shown in content, such as display content and dense degree etc., with reference to the classification results of scene,
The most suitable parking space state detection mode of selection in shortest time, eliminate single judgment mode and handling unknown scene luck
The problem of row overlong time and error in judgement, the parking space state under different scenes under polytype can be made faster more accurate
True judgement.
Brief description of the drawings
Fig. 1 is the method flow diagram in the embodiment of the present invention one；
Fig. 2 is the method flow diagram in the embodiment of the present invention two；
Fig. 3 is the theory diagram in the embodiment of the present invention three；
Fig. 4 is the structured flowchart of the judgement selecting unit in Fig. 3；
Fig. 5 is the structured flowchart of parking space state judging unit in the embodiment of the present invention three.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
The present invention provides a kind of detection method of parking space state, and it is based on video frequency car position detection technique, can be in single car
The detection for the parking stall driven into the vehicle is above realized, can also realize the video detection to multiple parking stalls in a such as parking lot,
In the latter's embodiment, the image information in the camera device of each parking stall can be gathered by host computer, and be unified in upper
Analyzed and processed in machine, result is sent and shown into car-mounted terminal, central idea of the invention is：Calculated by image
The image information that method processing video detection parking stall terminal device captures in real time, is sentenced by the classification to display content in image information
It is disconnected, suitable algorithm is selected, is judged with faster and more accurately making detection to parking space state, and the result for detecting judgement is sent
Or it is shown to user.
Embodiment one
As shown in figure 1, being the method flow diagram of the embodiment of the present invention one, the embodiment of the present invention provides a kind of parking space state
Detection method, the detection method include：
Step S101:Obtain the stable state image information of parking stall to be detected；
In this step, the stable state image information of parking stall to be detected is obtained, can be imaged and obtained by car-mounted terminal, such as car
The preposition camera device of parking assist apparatus, vehicle GPS etc., can also be obtained by the camera device that parking stall to be detected is installed,
VDT video data terminal is installed on each parking stall to be detected, its process is as follows：First need to be from vehicle-mounted middle control unit to parking lot
Host computer send request, host computer respond the request and open camera device parking stall to be detected is taken pictures in real time or
Shooting, transmitting procedure can take wireless communication mode and data message in a digital format is transmitted, to obtain host computer pair
The real-time stable state image information of the parking stall to be detected.
Step S102：The scene residing for parking stall to be detected is divided according to the display content in the stable state image information
Class, and the parking space state judgment mode according to corresponding to the selection of the result of the scene classification, to obtain parking space state.
Stable state image information may generally be parking stall inactive state to be detected (no vehicle drives into or out of, without staff's dealing)
The image information of lower acquisition, according to the display content in stable state image information, such as analyze to obtain the display by spectra methods
Band in content, judge whether the band is possessed peculiar spectrum under the occupied state in parking stall, or pixel point
Analysis method, whether the pixel analyzed in display content is with given shape, to judge whether there is work people in the display content
Member or driver, etc..
When classifying to the scene residing for parking stall to be detected, specific common scene may include：Vehicle do not park normally,
The presence or absence of car plate, whether there is biological information to influence parking, failing to obtain state, the parking stall quilt of stable state image information for vehicle
Concrete scene classification, the specific implement scenes such as other barriers occupancy are not limited to this, will can also run into a particular application
New classification be added in above-mentioned classification.
A kind of parking space state judgment mode is accordingly preset per a kind of scene to above-mentioned, so as to enter to each scene
Row is effectively identified and quickly judged.
According to the result of scene classification, parking space state judgment mode corresponding to selection, carried out again without the scene to complexity
Analysis judgement, and according to the result of the scene classification and the parking space state judgment mode of selection, easily draw parking space state.
The embodiment of the present invention is accessible to be had the beneficial effect that：The stable state image information of parking stall is obtained, by figure information
Display content is compared, and not only the parking space state under several scenes can be detected, and can also be detected simultaneously multiple
Parking stall, the detection to multiple parking stalls and safety monitoring are realized in a manner of host computer.
As shown in Fig. 2 on the basis of above-described embodiment, the mistake of the stable state image information therein for obtaining parking stall to be detected
Journey is concretely：
Step S201:Obtain the continuous image information of parking stall to be detected；
Continuously parking stall to be detected is captured by camera device, using the image of real-time grasp shoot as to be detected
The continuous image information of parking stall；
Step S202:When the continuous image information of acquisition is consistent, judges and select one of consecutive image conduct
Stable state image information；
The continuous image information of each group (in the unit interval) of acquisition is judged, as in wherein each image information
The distributing position of pixel, the dense degree etc. of pixel as the standard judged, to identify the continuous image information of the group
Whether stable state is reached, the phase such as dense degree of distributing position, pixel when the pixel in each image information in each group
When closing the difference of information within defined error, meet foregoing criterion, that is, judge the continuous image that the group obtains
Information is consistent, and selects one of described consecutive image information to be used as stable state image information.
When not meeting foregoing criterion, then next group of candid photograph is carried out by camera device, that is, repeats step
S201, and circulate and judged according to foregoing criterion, until the one of which image information of shooting is followed when reaching stable state
Ring terminates, and selects a width of last group image information as stable state image information.
Stable state image information can ensure the stable state of parking stall to be detected, under ensureing parking stall to be detected at a time
It can park, the safety of parking people can be ensured from side.
After obtaining stable state image information, continue:According to the display content in the stable state image information to be checked
Scene residing for measuring car position is classified, and the parking space state judgment mode according to corresponding to the selection of the result of the scene classification,
To obtain parking space state.
Embodiment two
The detection method of parking space state in the embodiment of the present invention, the present embodiment on the basis of above-described embodiment, according to
The classification results selection parking space state detection judgment mode of the scene, it may include background detection judgment mode, skin texture detection are sentenced
Disconnected mode or classification and Detection judgment mode, but with the development of science and technology, also can correspondingly increase newest detection judgement side
Formula, therefore, it is not limited in the embodiment of the present invention in a manner of this three kinds, and it is only illustrative, wherein：
The background detection judgment mode, including download parking stall to be detected without vehicle context figure, pass through the nothing
Vehicle context figure and the stable state image information, draw parking space state, for example, compared with without vehicle context figure pair, in acquisition
Include in the stable state image information comparatively dense and distribution profile uniformly or in car body streamline shape pixel when, then judge
It is seizure condition for the parking stall to be detected, if conversely, the stable state image information and the pixel point of the no vehicle context figure
Cloth is basically identical, then is free state, the background judgment mode is generally used for that light is dark and ground be stained it is more,
The scene of selection wherein algorithm is influenced whether, for example, when ground is stained more, is included in the stable state image information of acquisition closeer
During the centrality texture of collection, according to skin texture detection judgment mode, then error in judgement is easily caused, and now examined according to background
Judgment mode is surveyed, more intensive centrality texture be present in the display content in current stable state image information, should
The display location of centrality texture is similar to the texture of the presentation without vehicle context figure and when position is close, then judges that this is to be detected
Parking stall is free state, greatly improves the accuracy of parking space state detection.
The skin texture detection judgment mode, including：Whether included according in the display content in the stable state image information
There is centrality texture, draw parking space state；If specifically, include centrality line in display content in stable state image information
Reason, for example, include in a small area region and in car plate shape centrality texture when, then judge parking stall it is occupied, if surely
Not comprising when having centrality texture in display content in state image information, then judgement parking stall is unoccupied.
The characteristics of skin texture detection judgment mode is typically according to Chinese herbaceous peony air-inlet grille texture-rich, by steady state picture picture
Whether there is centrality texture to judge whether parking stall occupied in information, also can by stable state image information whether tool
The texture being made up of the pixel of the vehicle shape in big region judges whether parking stall to be detected is occupied.
The classification and Detection judgment mode, including：By classifying to display content in the stable state image information, obtain
Go out parking space state；
The classification and Detection judgment mode, by being taken to parking stall, that parking stall is unoccupied, camera device is blocked etc. is a variety of
The data of scene establish a disaggregated model, and the disaggregated model can be by representated by the display content in stable state image information next time
Number format pixel distribution or spectrum analysis etc. be mapped to some classification in given classification, quickly to realize to car
The condition adjudgement of position.
Above-mentioned skin texture detection judgment mode, further preferred embodiment is for it：By download parking stall to be detected without car
Background, with reference to whether including centrality line in display content in the no vehicle context figure, the stable state image information
Reason and environmental information, judge parking space state.
Generally, skin texture detection judgment mode is the detection mode first when carrying out parking space state detection, for
A certain specific parking stall, such as home-use parking stall, can according only in the display content in the stable state image information detected whether
Include car plate (texture whether with centrality) to judge the seizure condition of parking stall, the mode being more highly preferred to is, in car
Parking stall to be detected is prestored or downloaded in mounted terminal (is such as family without the environmental information in vehicle context figure and display content
With parking stall or public parking position), and combine centrality texture can the current parking stall to be detected of accurate judgement seizure condition, more
Specifically, have determined that the parking space state judgment mode of selection is skin texture detection judgement side according to the result of scene classification for example, working as
During formula, centrality texture is shown in the display content in stable state image information, and be tentatively judged as according to the distribution of its pixel
With license board information, it can also show that it has the car of centrality texture without vehicle context figure with reference to the parking stall to be detected of download
Board information, and further, when steady state picture is shown as home-use parking stall as the environmental information in informational display, then in car
The information field of addition " this is home-use parking stall " in the result that position detection judges, and when the ring in state image information display content
When environment information is shown as commons parking stall, then the information word of " this is commons parking stall " is added in the result that parking stall measure judges
Section, further to lift the parking stall judgment accuracy of skin texture detection judgment mode.
When selecting parking space state detection judgment mode according to the classification results of scene, grain inspection generally can be set
Judgment mode is surveyed as the first preferred detection judgment mode, however, during normal handling, in order to be made more to complex scene
Quickly response, at least the one of selection parking space state judgment mode according further to the result of the scene classification, can be drawn
Kind preferred embodiment and at least one time select mode.
Specifically, when such as scene classification result is " being not detected by car plate ", preferred embodiment therein can be background detection
Judgment mode, secondary to select mode can be then classification and Detection judgment mode, and for wherein mainly by detecting car plate the line that judges
Reason detects judgment mode and comes last position or do not enable such judgment mode.
For at least one preferred embodiment therein, influenceed when being not present in the display content in the stable state image information
During the unfavorable factor of the preferred embodiment, for example, under certain scene classification, the preferable judgment mode that detects is sentenced for skin texture detection
Disconnected mode, and in the display content in stable state image information, the centrality texture that it is included is not fairly obvious, or concentrates
Property texture it is more scattered, or be difficult to a variety of centrality textures to judge, etc., belong in this case unfavorable
Factor, in the presence of these unfavorable factors, mode is selected into selection time, parking space state sentenced such as background detection judgment mode
It is fixed.
And when in the display content in the stable state image information and in the absence of the unfavorable of the influence selection preferred embodiment
During factor, then parking space state is judged using the preferred embodiment, it is secondary to select mode then to rank in standby to draw parking space state
With in list.
Unfavorable factor therein, there is different definition under different scene classifications, for example, in " vehicle mounted imaging apparatus quilt
Block " scene classification under, if its default preferred embodiment is background detection judgment mode, its unfavorable factor may be：1、
Can not obtain current parking stall to be detected without vehicle context figure；2nd, the image letter shot when vehicle mounted imaging apparatus is blocked is takeed for
Cease for stable state image information；Etc.；And for example, under the scene classification of " excellent environment information ", its default preferred embodiment is line
Reason detection judgment mode, its unfavorable factor may be：1st, shown in the display content in the stable state image information more
Texture, may cause to judge by accident；2nd, fail to obtain the parking stall to be detected without vehicle context figure；Etc., in each preferred embodiment
Under, its unfavorable factor that may be present can be specified, and the unfavorable factor is taken into account when selecting preferred embodiment.
Certainly, the scene classification of the embodiment of the present invention is more than above-mentioned classification, also can be to field according to the analysis of concrete scene
The species of scape classification is deleted, and is judged with the parking space state being adapted under species occasion.
On the basis of the various embodiments described above, it may include to have in the display content in the stable state image information but unlimited
In：
Environmental information, including parking stall surrounding environment information, parking stall ground surface environment information etc.；
Biological information, mainly include and human characteristic information whether has been detected on the parking stall, in order to avoid parking
Cause to accidentally injure during car；
Information of vehicles, whether park cars on the parking stall, for unappropriated parking stall, information of vehicles can not be shown
Or tacit declaration is zero.
Embodiment three
As shown in figure 3, a kind of detection means of parking space state is additionally provided in the embodiment of the present invention, the detection means bag
Include：
Image acquisition unit 301, obtain the stable state image information of parking stall to be detected；
Scene classification unit 302, for according to the display content in the stable state image information to the scene residing for parking stall
Classified；
Judge selecting unit 303, including parking space state judging unit 401, the judgement selecting unit 303 is used for according to institute
The classification results for stating parking space state judging unit 401 select the parking space state judgment mode of the parking space state judging unit, with
Obtain parking space state.
As shown in figure 4, the judgement selecting unit 303 also includes intelligent selection unit 402：The intelligent selection unit
402 are used for：
According to the result of the scene classification, at least one preferred embodiment and extremely of selection parking space state judgment mode is drawn
Few one kind time selects mode；
When the unfavorable factor for influenceing the preferred embodiment is not present in the display content in the stable state image information, then
Parking space state is judged using the preferred embodiment, to draw parking space state；
When the unfavorable factor for influenceing the preferred embodiment during the steady state picture is as informational display be present, then institute is selected
State and time select mode to judge parking space state, to draw parking space state.
In embodiments of the present invention, the display content for the stable state elementary area that described image acquiring unit obtains at least is wrapped
Include：Environmental information, biological information and information of vehicles.
As shown in figure 5, the parking space state judging unit 401 includes background detection judging unit, skin texture detection judges list
Member and classification and Detection judging unit：
The background detection judging unit, for by download parking stall to be detected without vehicle context figure, the nothing
Vehicle context figure and the stable state image information, draw parking space state；It is dark and/or ground is stained more scene for light
Classification, it can be made comparisons by way of downloading without vehicle context figure, to judge the seizure condition of parking stall exactly.
The skin texture detection judging unit, for when whether including centrality in the display content in stable state image information
Texture, the parking space state is drawn, shown in the display content in stable state image information obtained for image acquisition unit 301
It is clean and parking stall number is not very big parking stall for ground, without downloading without vehicle context figure, and directly sentenced by the skin texture detection
Disconnected unit judged the state of parking stall, eliminate by hardware download Background the step for, effectively mitigate scene peace
The working strength of dress personnel；And for showing that there is the parking stall to be detected of stain on ground in display content, skin texture detection can be in empty wagons
More texture is detected during position, and then brings the judgement of mistake, at this moment then needs to download without vehicle context figure as background, and
And the stable state image information of acquisition is being made comparisons with without vehicle context figure every time, to make correct judgement.
The classification and Detection judging unit, for by classifying to display content in the stable state image information, obtaining
Go out parking space state, the classification and Detection judging unit by training disaggregated model jointly to the picture drawn in the case of various,
Corresponding detection judging unit is selected to classify for every a pair of disaggregated models, so as to improve the degree of accuracy.
Background detection judging unit that the parking space state judging unit 401 includes, skin texture detection judging unit and point
Class detection judging unit various situations can be judged, for example, parked on parking stall be unlicensed car, car at any driving condition
Car plate can not be photographed, was stopped before car stops partially, human pilot or staff are blocked on car plate and road has car to block vehicle-mounted pick-up
Device etc. situation, it largely ensure that accuracy and real-time that parking space state judges.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (8)
1. a kind of detection method of parking space state, it is characterised in that the detection method includes：
Obtain the stable state image information of parking stall to be detected；
The scene residing for parking stall is classified according to the display content in the stable state image information；
According to the result of the scene classification, at least one preferred embodiment and at least one for selecting parking space state judgment mode is drawn
Kind time selects mode；
When the unfavorable factor for influenceing the preferred embodiment is not present in the display content in the stable state image information, then use
The preferred embodiment is judged parking space state, to draw parking space state；
When the unfavorable factor for influenceing the preferred embodiment during the steady state picture is as informational display be present, then select described time
Mode is selected to judge parking space state, to draw parking space state.
2. detection method according to claim 1, it is characterised in that obtain parking stall to be detected stable state image information it
Before, in addition to：
Obtain the continuous image information of parking stall to be detected；
When the continuous image information of acquisition is consistent, judges and select one of described consecutive image information as steady state picture picture letter
Breath.
3. detection method according to claim 1, it is characterised in that the parking space state judgment mode includes background detection
Judgment mode, skin texture detection judgment mode or classification and Detection judgment mode, wherein：
The background detection judgment mode, including：By download parking stall to be detected without vehicle context figure, the no vehicle
Background and the stable state image information, draw parking space state；
The skin texture detection judgment mode, including：Whether include collection according in the display content in the stable state image information
Neutral texture, draws parking space state；
The classification and Detection judgment mode, including：By classifying to display content in the stable state image information, car is drawn
Position state.
4. detection method according to claim 3, it is characterised in that to be detected by downloading when skin texture detection judges
Parking stall without vehicle context figure, with reference to whether being included in display content in the no vehicle context figure, the stable state image information
There are centrality texture and environmental information, parking space state is judged.
5. detection method according to any one of claims 1 to 4, it is characterised in that the display in the stable state image information
Content comprises at least：Environmental information, biological information and information of vehicles.
6. a kind of detection means of parking space state, it is characterised in that the detection means includes：
Image acquisition unit, obtain the stable state image information of parking stall to be detected；
Scene classification unit, for being divided according to the display content in the stable state image information the scene residing for parking stall
Class；
Judge selecting unit, including parking space state judging unit, the judgement selecting unit is used for according to the scene classification list
The classification results of member select the parking space state judgment mode of the parking space state judging unit, to obtain parking space state；
The judgement selecting unit also includes intelligent selection unit, and the intelligent selection unit is used for：
According to the result of the scene classification, at least one preferred embodiment and at least one for selecting parking space state judgment mode is drawn
Kind time selects mode；
When the unfavorable factor for influenceing the preferred embodiment is not present in the display content in the stable state image information, then use
The preferred embodiment is judged parking space state, to draw parking space state；
When the unfavorable factor for influenceing the preferred embodiment during the steady state picture is as informational display be present, then select described time
Mode is selected to judge parking space state, to draw parking space state.
7. the detection means of parking space state according to claim 6, it is characterised in that the parking space state judging unit bag
Include background detection judging unit, skin texture detection judging unit and classification and Detection judging unit：
The background detection judging unit, for by download parking stall to be detected without vehicle context figure, the no vehicle
Background and the stable state image information, draw parking space state；
The skin texture detection judging unit, for when whether including centrality line in the display content in stable state image information
Reason, draws the parking space state；
The classification and Detection judging unit, for by classifying to display content in the stable state image information, drawing car
Position state.
8. the detection means of parking space state according to claim 6, it is characterised in that what described image acquiring unit obtained
The display content of stable state elementary area comprises at least：Environmental information, biological information and information of vehicles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510783507.3A CN105390021B (en) | 2015-11-16 | 2015-11-16 | The detection method and device of parking space state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510783507.3A CN105390021B (en) | 2015-11-16 | 2015-11-16 | The detection method and device of parking space state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105390021A CN105390021A (en) | 2016-03-09 |
| CN105390021B true CN105390021B (en) | 2018-03-27 |
Family
ID=55422258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510783507.3A Active CN105390021B (en) | 2015-11-16 | 2015-11-16 | The detection method and device of parking space state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105390021B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894823B (en) * | 2016-06-03 | 2018-08-21 | 北京精英智通科技股份有限公司 | A kind of parking detection method and apparatus and system |
| CN105894529B (en) * | 2016-06-03 | 2019-01-29 | 北京精英智通科技股份有限公司 | Parking space state detection method and apparatus and system |
| CN106023594A (en) * | 2016-06-13 | 2016-10-12 | 北京精英智通科技股份有限公司 | Parking stall shielding determination method and device and vehicle management system |
| CN105844959B (en) * | 2016-06-13 | 2018-07-24 | 北京精英智通科技股份有限公司 | The determination method, device and vehicle that vehicle enters position go out the determination method of position, device |
| CN105869182B (en) * | 2016-06-17 | 2018-10-09 | 北京精英智通科技股份有限公司 | A kind of parking stall condition detection method and system |
| CN107610499A (en) * | 2016-07-11 | 2018-01-19 | 富士通株式会社 | Detection method, detection means and the electronic equipment of parking stall state |
| CN106228835B (en) * | 2016-07-18 | 2019-04-26 | 北京精英智通科技股份有限公司 | A kind of parking stall Parking judgment method and system |
| CN106251695B (en) * | 2016-09-29 | 2019-07-09 | 成都通甲优博科技有限责任公司 | Destination parking stall intelligent recommendation system and method based on parking space state monitoring |
| WO2018076281A1 (en) * | 2016-10-28 | 2018-05-03 | 富士通株式会社 | Detection method and detection apparatus for parking space status, and electronic device |
| CN106504583B (en) * | 2017-01-05 | 2019-04-05 | 陕西理工学院 | The cloud monitoring method of parking position state |
| CN109472184A (en) * | 2017-09-08 | 2019-03-15 | 深圳市金溢科技股份有限公司 | The condition detection method in berth, system and its data processing equipment in road |
| CN108615405A (en) * | 2018-06-19 | 2018-10-02 | 芜湖岭上信息科技有限公司 | A kind of parking lot intelligent navigation shutdown system |
| CN109817013A (en) * | 2018-12-19 | 2019-05-28 | 新大陆数字技术股份有限公司 | Parking stall state identification method and device based on video flowing |
| CN111383457B (en) * | 2018-12-30 | 2021-02-09 | 浙江宇视科技有限公司 | Parking space state detection method and device, equipment and storage medium |
| CN111696378B (en) * | 2019-03-25 | 2020-12-08 | 六安同辉智能科技有限公司 | Automatic image data analysis method |
| CN110164178A (en) * | 2019-06-21 | 2019-08-23 | 甘肃万华金慧科技股份有限公司 | A kind of intelligent parking pick-up method and system |
| CN110276322B (en) * | 2019-06-26 | 2022-01-07 | 湖北亿咖通科技有限公司 | Image processing method and device combined with vehicle machine idle resources |
| CN111081064B (en) * | 2019-12-11 | 2021-12-14 | 上海赫千电子科技有限公司 | Automatic parking system and automatic passenger-replacing parking method of vehicle-mounted Ethernet |
| CN110689761B (en) * | 2019-12-11 | 2021-10-29 | 上海赫千电子科技有限公司 | Automatic parking method |
| CN111243185A (en) * | 2020-01-09 | 2020-06-05 | 杭州中恒电气股份有限公司 | Charging parking space occupation determination method, device and medium |
| CN113807209A (en) * | 2021-08-30 | 2021-12-17 | 阿波罗智联(北京)科技有限公司 | Parking space detection method and device, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574351A (en) * | 2014-08-06 | 2015-04-29 | 深圳市捷顺科技实业股份有限公司 | Parking space detection method based on video processing |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1717757A1 (en) * | 2005-04-28 | 2006-11-02 | Bayerische Motoren Werke Aktiengesellschaft | Method for graphically displaying the surroundings of a motor vehicle |
| CN100559420C (en) * | 2007-03-29 | 2009-11-11 | 汤一平 | Parking guidance system based on computer vision |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN101556739A (en) * | 2009-05-14 | 2009-10-14 | 浙江大学 | Vehicle detecting algorithm based on intrinsic image decomposition |
| CN101656023B (en) * | 2009-08-26 | 2011-02-02 | 西安理工大学 | Management method of indoor car park in video monitor mode |
| CN101783076B (en) * | 2010-02-04 | 2012-06-13 | 西安理工大学 | Method for quick vehicle type recognition under video monitoring mode |
| US9129524B2 (en) * | 2012-03-29 | 2015-09-08 | Xerox Corporation | Method of determining parking lot occupancy from digital camera images |
| CN102867183B (en) * | 2012-08-23 | 2015-04-15 | 安科智慧城市技术（中国）有限公司 | Method and device for detecting littered objects of vehicle and intelligent traffic monitoring system |
-
2015
- 2015-11-16 CN CN201510783507.3A patent/CN105390021B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574351A (en) * | 2014-08-06 | 2015-04-29 | 深圳市捷顺科技实业股份有限公司 | Parking space detection method based on video processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105390021A (en) | 2016-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105390021B (en) | The detection method and device of parking space state | |
| CN104952122B (en) | The drive recorder and system of evidence obtaining violating the regulations can be carried out automatically | |
| US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
| CN104103030B (en) | Image analysis method, camera apparatus, control apparatus and control method | |
| CN108399782A (en) | Method, apparatus, system, equipment and the storage medium of outdoor reversed guide-car | |
| CN107978157A (en) | Vehicles management method, device and computer-readable recording medium | |
| CN108197526A (en) | Detection method, system and computer readable storage medium | |
| CN109284674A (en) | A kind of method and device of determining lane line | |
| CN111783744A (en) | Operation site safety protection detection method and device | |
| KR100948382B1 (en) | Security service method and system | |
| CN108022431A (en) | A kind of method and system that parking stall is detected by video capture image | |
| CN109740590A (en) | The accurate extracting method of ROI and system based on target following auxiliary | |
| CN107977596A (en) | A kind of car plate state identification method and device | |
| KR101757750B1 (en) | Unified notice method for congestion information of subway | |
| CN107945445A (en) | A kind of thunder ball linkage warning monitoring system and its monitoring method with preprocessing function | |
| JP2019052889A (en) | Image processor | |
| CN101282419B (en) | Method and apparatus for automatically detecting bad point | |
| CN109979202A (en) | A kind of vehicle safety inspection method and device | |
| CN207938184U (en) | A kind of vehicle-mounted act of violating regulations capturing system | |
| CN104058306A (en) | Intelligent dispatching system of elevator | |
| JPH10285586A (en) | Image processor, monitoring image display system, image processing method and monitoring image display method | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| KR100782205B1 (en) | Apparatus and system for displaying speed of car using image detection | |
| KR101560810B1 (en) | Space controled method and apparatus for using template image | |
| CN108033329A (en) | A kind of elevator loses the automatic checkout system and detection method of junk |
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 |