CN106023594A - Parking stall shielding determination method and device and vehicle management system - Google Patents
Parking stall shielding determination method and device and vehicle management system Download PDFInfo
- Publication number
- CN106023594A CN106023594A CN201610411016.0A CN201610411016A CN106023594A CN 106023594 A CN106023594 A CN 106023594A CN 201610411016 A CN201610411016 A CN 201610411016A CN 106023594 A CN106023594 A CN 106023594A
- Authority
- CN
- China
- Prior art keywords
- parking stall
- detection target
- target
- video frame
- frame images
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Abstract
The invention discloses a parking stall shielding method, comprising steps of obtaining a video frame image of a parking lot; performing algorithm analysis on the video frame image; determining a detection object in the video frame image; determining whether the detection object has intersection with the parking lot shielding area, wherein the parking stall shielding area is an area having a first predetermined distance from a boundary line of a driving side of the parking stall; and if yes, determining the corresponding detection object as a shielding object. The parking stall shielding method can detect whether the parking stall is shielded through determining whether the detection object is intersected with the parking stall shielding area and can accurately detect the parking stall shielding condition. The invention also discloses a parking stall shielding determination device and a vehicle management system, which can accurately detect the parking stall shielding condition.
Description
Technical field
The present invention relates to intelligent transportation field, the decision method that blocks particularly to a kind of parking stall, device and
Vehicle management system.
Background technology
Along with the development of science and technology, intelligent transportation system is more and more higher in field of traffic popularization degree, by direct shadow
Ring the development process of future transportation system, it be by advanced information technology, data communication transmission technology,
Electronic transducer technology, control technology and computer technology etc. are effectively integrated a kind of big model together built up
Enclose, comprehensive, in real time, comprehensive traffic management system accurately and efficiently.Parking stall based on video manages
System, as a part important in intelligent transportation system, provides vehicle parking letter for intelligent transportation system
Breath, it provides the accuracy of information will to directly influence the intelligent of intelligent transportation system.
Now, along with the development in city, road parking place gets more and more, and this manages to parking stall based on video
Reason system proposes new challenge.Because road parking place is in road on both sides of the road, it not only receives various sky
The impact of gas factor, is also blocked parking stall by vehicular traffic and is affected.Limited by camera position,
Occlusion issue can not eliminate and will exist always, so the disposal ability that intelligent algorithm is to blocking will be directly
Have influence on the accuracy of detection of parking space management system.Therefore, how parking stall is blocked and judges accurately,
It is those skilled in the art's technical issues that need to address.
Summary of the invention
It is an object of the invention to provide the decision method that a kind of parking stall is blocked, by judging whether detect target
Intersect with parking stall occlusion area, detect whether parking stall blocks, it is possible to parking stall circumstance of occlusion accurately detected；
It is a further object of the present invention to provide decision maker and vehicle management system that a kind of parking stall is blocked.
For solving above-mentioned technical problem, the present invention provides the decision method that a kind of parking stall is blocked, including:
Obtain the video frame images in parking lot；
Described video frame images is carried out Algorithm Analysis, determines the detection target in described video frame images；
Judge whether described detection target is positioned at parking stall occlusion area and has common factor；Wherein, described parking stall is blocked
Region is the region of driving side boundary line, distance parking stall the first preset distance；
The most corresponding detection target is shelter target.
Wherein, described video frame images is carried out Algorithm Analysis, determine the detection in described video frame images
Target, including:
Detection region in described video frame images is carried out Algorithm Analysis, determines in described detection region
Detection target；Wherein, described detection region is the district of driving side boundary line, distance parking stall the second preset distance
Territory, and described second preset distance is more than described first preset distance.
Wherein, described video frame images is carried out Algorithm Analysis, determine the detection in described video frame images
Target, including:
Utilize background modeling algorithm that described video frame images is carried out Algorithm Analysis, it is thus achieved that sport foreground information,
Using described sport foreground information as motion detection target；And/or,
Utilize wagon detector that described video frame images is carried out Algorithm Analysis, it is thus achieved that the position of vehicle target
Information, and utilize background modeling algorithm to be identified described video frame images processing, it is thus achieved that sport foreground
Information, and according to described positional information and described sport foreground information, determine static detection target.
Wherein, when described detection target is for motion detection target, it is judged that whether described detection target is positioned at
Parking stall occlusion area has common factor, including:
Calculate the number in virtual coil of the foreground features point in described sport foreground information；
Judge that whether described number is more than occlusion threshold；
The most corresponding motion detection target is motion shelter target.
Wherein, when described detection target is static detection target, it is judged that whether described detection target is positioned at
Parking stall occlusion area has common factor, including:
The positional information of described static detection target is compared with the positional information of parking stall occlusion area,
Judge whether the positional information of described static detection target and the positional information of parking stall occlusion area have common factor；
The most corresponding static detection target is static shelter target.
The present invention also provides for the decision maker that a kind of parking stall is blocked, including:
Image collection module, for obtaining the video frame images in parking lot；
Detection target determination module, for described video frame images is carried out Algorithm Analysis, determine described in regard
Frequently the detection target in two field picture；
Shadowing module, is used for judging whether described detection target is positioned at parking stall occlusion area and has common factor；
Wherein, described parking stall occlusion area is the region of driving side boundary line, distance parking stall the first preset distance；If
It is that then corresponding detection target is shelter target.
Wherein, described detection target determination module is specially to enter the detection region in described video frame images
Line algorithm is analyzed, and determines the module of detection target in described detection region；Wherein, described detection region
For the region of distance parking stall driving side boundary line the second preset distance, and described second preset distance is more than institute
State the first preset distance.
Wherein, described detection target determination module includes:
Motion detection object element, is used for utilizing background modeling algorithm that described video frame images is carried out algorithm
Analyze, it is thus achieved that sport foreground information, using described sport foreground information as motion detection target；And/or,
Static detection object element, is used for utilizing wagon detector that described video frame images is carried out algorithm and divides
Analysis, it is thus achieved that the positional information of vehicle target, and utilize background modeling algorithm that described video frame images is carried out
Identifying processing, it is thus achieved that sport foreground information, and according to described positional information and described sport foreground information,
Determine static detection target.
Wherein, described shadowing module includes: motion shadowing unit and/or static shadowing list
Unit；Wherein,
Motion shadowing unit, for calculating the foreground features point in described sport foreground information virtual
Number in coil；Judge that whether described number is more than occlusion threshold；The most corresponding motion detection mesh
It is designated as motion shelter target；
Static shadowing unit, for by the positional information of described static detection target and blocked area, parking stall
The positional information in territory compares, it is judged that the positional information of described static detection target and parking stall occlusion area
Positional information whether have common factor；The most corresponding static detection target is static shelter target.
The present invention also provides for a kind of vehicle management system, including:
Photographic head, for gathering the video frame images in parking lot；
The decision maker that parking stall described in any of the above-described item is blocked.
The decision method that parking stall provided by the present invention is blocked, including: obtain the video frame images in parking lot；
Described video frame images is carried out Algorithm Analysis, determines the detection target in described video frame images；Judge
Whether described detection target is positioned at parking stall occlusion area common factor；Wherein, described parking stall occlusion area be away from
Region from driving side boundary line, parking stall the first preset distance；The most corresponding detection target is for blocking mesh
Mark；It can thus be appreciated that the method is by judging whether detection target intersects with parking stall occlusion area, detect car
Whether position blocks, it is possible to parking stall circumstance of occlusion accurately detected；
And the method can also be classified as static detection target by the analysis to detection target further
With motion detection target, different targets is used different detection algorithms, it is possible to increase the efficiency of judgement
And accuracy；And can determine block for static block or move block；There is provided convenient for subsequent treatment；
Additionally present invention also offers decision maker and vehicle management system that a kind of parking stall is blocked, having above-mentioned has
Benefit effect, does not repeats them here.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to reality
Execute the required accompanying drawing used in example or description of the prior art to be briefly described, it should be apparent that below,
Accompanying drawing in description is only embodiments of the invention, for those of ordinary skill in the art, not
On the premise of paying creative work, it is also possible to obtain other accompanying drawing according to the accompanying drawing provided.
The schematic diagram that Fig. 1 blocks by the parking stall that the embodiment of the present invention is provided；
The flow chart of the decision method that Fig. 2 blocks by the parking stall that the embodiment of the present invention is provided；
The structured flowchart of the decision maker that Fig. 3 blocks by the parking stall that the embodiment of the present invention is provided.
Detailed description of the invention
The core of the present invention is to provide the decision method that a kind of parking stall is blocked, by judging whether detect target
Intersect with parking stall occlusion area, detect whether parking stall blocks, it is possible to parking stall circumstance of occlusion accurately detected；
Another core of the present invention is to provide decision maker and the vehicle management system that a kind of parking stall is blocked.
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under not making creative work premise
The every other embodiment obtained, broadly falls into the scope of protection of the invention.
Due to the vehicle of dealing or other object target in road parking place, can be to parking stall and parking stall inside
The vehicle stopped blocks, and the when of with Video Detection vehicle, because blocking, algorithm can detect parking stall
Inside the car of outside rather than parking stall, parking space state so can be caused to judge by accident.Refer to Fig. 1, owing to taking the photograph
The position limitation of camera, the parking stalls such as parking stall 1, parking stall 2, parking stall 3 can be blocked by vehicular traffic 8.Arrow table
Show the travel direction of vehicle.Square frame corresponding outside No. 5 parking stalls represents the virtual coil that this parking stall is corresponding.
In order to solve vehicle parking during road parking stall, parking space management system based on video is easily subject to
The impact that car blocks, causes the problem that parking stall real-time status is judged by accident by parking space management system, following
Parking stall can be blocked and be judged by embodiment accurately.Refer to Fig. 2, Fig. 2 is embodiment of the present invention institute
The flow chart of the decision method that the parking stall provided is blocked；The method may include that
S100, the video frame images in acquisition parking lot；
Wherein, by video equipment, parking lot can be monitored obtain parking lot in real time here to regard
Frequently two field picture.Here video equipment can be photographic head, ball-shaped camera etc..
S110, described video frame images is carried out Algorithm Analysis, determine the detection in described video frame images
Target；
Wherein, the needs that the main purpose of this step is intended to identify in video frame images carry out the inspection detected
Survey target.The most the concrete grammar of image recognition is not defined.Such as can pass through vehicle detection
Device identifies all vehicles in video frame images.Wherein, wagon detector namely vehicle checker, function is
Vehicle target in detection frame of video, can detect the positional information of vehicle in frame of video, and headstock parking stall is believed
Breath, believe one side only about vehicle body breath.Vehicle checker can be according to DPM (Deformable Parts Model) target
Detection algorithm builds.Might not be vehicle entirely due to the object that parking stall can be blocked again, also
Can be other objects such as tricycles, pedestrian etc., therefore can also use the method for background modeling
The object of motion is detected.
Here detection target can also be screened, because the scope that video frame images comprises is bigger,
The most whole runway is all in video frame images, if all targets all conduct detection targets to the inside,
The amount of calculation then needed can be bigger；Therefore, in order to reduce amount of calculation, improve computational accuracy, here may be used
So that the scope choosing detection target to be defined, in a selection range, i.e. carry out Algorithm Analysis, really
Determine the detection target in video frame images；The size of selection range here can be according to user's actual need
It is determined, such as, considers device computing capability, use the precision of recognizer, parking stall occlusion detection
Accuracy requires to carry out considering determining.
Improve the accuracy of parking stall occlusion detection further, it is also possible to detection target is classified, such as
Parking stall is blocked by detection vehicle；Or only parking stall is blocked by detection stationary vehicle；Or only
Parking stall is blocked by detection moving target；Or only parking stall is blocked by detection static target；Again or
It is detection moving target and the situation such as is blocked in parking stall by static target；Here by detection target
Classification improves the specific aim of parking stall occlusion detection result, thus improves the accuracy of parking stall occlusion detection
And reliability.
S120, judge whether described detection target is positioned at parking stall occlusion area and has common factor；Wherein, described car
Position occlusion area is the region of driving side boundary line, distance parking stall the first preset distance；
S130, the most corresponding detection target are shelter target.
Wherein, to be also determined i.e. first according to practical situation pre-for the size of parking stall occlusion area here
Set a distance can have user to be determined, and concrete numerical value can also be obtained by test, and parking stall blocks one
As be all that vehicle has been parked in side, parking stall, and near the side, boundary line, parking stall of driving side, side；Such as
It can be 1/5th overall width that one preset distance sets, it is also possible to be 1/3rd overall width, it is also possible to be three
/ mono-parking stall width.
Judge whether detection target is positioned at parking stall occlusion area and has common factor, can be directly by comparing detection mesh
Target positional information compares with the positional information of parking stall occlusion area, if as there is at least one
Point of location information then proves that detecting target is positioned at parking stall occlusion area, exists parking stall and blocks.
Based on technique scheme, the decision method that the parking stall that the embodiment of the present invention provides is blocked, by sentencing
Whether disconnected detection target intersects with parking stall occlusion area, detects whether parking stall blocks, it is possible to accurately detect
To parking stall circumstance of occlusion.
Based on above-described embodiment, optionally, described video frame images is carried out Algorithm Analysis, determine described
Detection target in video frame images, including:
Detection region in described video frame images is carried out Algorithm Analysis, determines in described detection region
Detection target；Wherein, described detection region is the district of driving side boundary line, distance parking stall the second preset distance
Territory, and described second preset distance is more than described first preset distance.
Wherein, this embodiment improves calculating speed by reducing detection target, and is known by detection target
The screening in other region, it is also possible to improve the judging efficiency of shelter target.Second preset distance can be from car
Driving side boundary line, position is to the distance of a runway near parking stall.
Based on above-described embodiment, optionally, described video frame images is carried out Algorithm Analysis, determine described
Detection target in video frame images, including:
Utilize background modeling algorithm that described video frame images is carried out Algorithm Analysis, it is thus achieved that sport foreground information,
Using described sport foreground information as motion detection target；Corresponding is motion detection target when detecting target
Time, it is judged that whether detection target is positioned at parking stall occlusion area common factor, may include that
Calculate the number in virtual coil of the foreground features point in described sport foreground information；
Judge that whether described number is more than occlusion threshold；
The most corresponding motion detection target is motion shelter target.
Wherein, after obtaining frame of video, carry out background modeling, because background modeling needs a process, so
Have warm-up phase.Frame of video is carried out background modeling and can obtain sport foreground, be characterized a little with prospect,
Calculate the number of feature in virtual coil, if greater than the occlusion threshold set, indicate target occlusion car
Position.As being not above the occlusion threshold set, then can be directly entered the analysis of next frame.
Wherein, curb parking position is to have concrete position inside video scene, carries out certain extending out
It is defined as virtual coil later.So vehicle is when sailing near parking stall skidding, due to camera installation locations
Restriction, sport foreground just can be detected inside virtual coil.Each parking stall is correspondence one inside image
Individual virtual coil, initialization is to indicate that in image, some region is a virtual coil, after indicating,
The zone position information of virtual coil it has been known that in follow-up process.
Wherein, background modeling initialization procedure needs a certain amount of video frame images, A frame before selecting here
Model is initialized by image, initializes and does not completes, can not carry out Algorithm Analysis.Build at subsequent background
If handoff scenario does not avoids the need for warm during mode division analysis, handoff scenario is accomplished by carrying on the back scene
Scape model reinitializes.
And/or,
Utilize wagon detector that described video frame images is carried out Algorithm Analysis, it is thus achieved that the position of vehicle target
Information, and utilize background modeling algorithm to be identified described video frame images processing, it is thus achieved that sport foreground
Information, and according to described positional information and described sport foreground information, determine static detection target.Corresponding
When described detection target is static detection target, it is judged that whether described detection target is positioned at parking stall blocks
There is common factor in region, may include that
The positional information of described static detection target is compared with the positional information of parking stall occlusion area,
Judge whether the positional information of described static detection target and the positional information of parking stall occlusion area have common factor；
The most corresponding static detection target is static shelter target.
Wherein, vehicle checker can not judge that vehicle is static or motion, and vehicle checker may determine that the position of vehicle
Putting, needing after vehicle inside frame of video to judge that vehicle is on side, parking stall so finding, if
Then continue with movement background information on side, parking stall and judge that vehicle is static, if static, table
Show that stationary vehicle is blocked.
This embodiment i.e. can only include the static judgement blocked；Or only include the judgement that motion is blocked；
Can also all include that i.e. carrying out the static judgement blocked carries out again the judgement blocked of moving.
I.e. can be divided into two parts, stationary vehicle detection and moving object detection.Stationary vehicle is detected,
If vehicle is directly parked in outside parking stall, the position of vehicle can be detected by direct vehicle checker, the most right
Can be obtained by blocking parking stall than vehicle location and parking stall positional information, because vehicle checker detection vehicle is not
Componental movement or static, so needing to judge that vehicle is the most static, is to combine inside background modeling here
Sport foreground information, if be detected that the region of vehicle is not sport foreground region then represents that stationary vehicle hides
, anyway be moving vehicle, the most there is not stationary vehicle and block in gear.And for moving target, first transport
Extract sport foreground with background modeling, then calculate sport foreground number of characteristic point inside virtual coil,
If feature point number is shown with moving target more than threshold value table and blocks.
Based on technique scheme, the decision method that the parking stall that the embodiment of the present invention provides is blocked, for car
When road parking place stops, parking stall can be blocked by vehicular traffic, causes shutdown system to obtain real
Time parking space information error problem, the method realizes parking stall occlusion detection initially with video analysis mode,
Save hardware costs, reduced labor cost, it is only necessary to development process has increased inside algorithm accordingly
Occlusion detection module.Secondly, moving object detection and vehicle checker are blended, enhances algorithm to surrounding
The robustness of moving object detection in environment, improves the accuracy of detection that parking stall is blocked by moving vehicle.Again
Secondary, in conjunction with car test result and parking stall positional information, it is achieved parking stall surrounding static vehicle detection, it is to avoid quiet
The only vehicle impact on parking space state, enhances the disposal ability that stationary vehicle is blocked by algorithm.Finally,
Take into full account that the impact that parking stall is blocked by moving target and stationary vehicle, different situations use different
Determination strategy, enhances the adaptability of algorithm, to improve the algorithm detection to blocking accurate.
Embodiments provide the decision method that parking stall is blocked, by judge to detect target whether with car
Position occlusion area intersects, and detects whether parking stall blocks, it is possible to parking stall circumstance of occlusion accurately detected.
Decision maker and vehicle management system that the parking stall provided the embodiment of the present invention below is blocked are situated between
Continuing, decision maker and vehicle management system that parking stall described below is blocked block with above-described parking stall
Decision method can be mutually to should refer to.
Refer to the structural frames of the decision maker that Fig. 3, Fig. 3 block by the parking stall that the embodiment of the present invention is provided
Figure；This device may include that
Image collection module 100, for obtaining the video frame images in parking lot；
Detection target determination module 200, for described video frame images is carried out Algorithm Analysis, determines described
Detection target in video frame images；
Shadowing module 300, is used for judging whether described detection target is positioned at parking stall occlusion area and has friendship
Collection；Wherein, described parking stall occlusion area is the region of driving side boundary line, distance parking stall the first preset distance；
The most corresponding detection target is shelter target.
Optionally, described detection target determination module 200 is specially the detection in described video frame images
Region carries out Algorithm Analysis, determines the module of detection target in described detection region；Wherein, described inspection
Survey the region that region is driving side boundary line, distance parking stall the second preset distance, and described second preset distance
More than described first preset distance.
Optionally, described detection target determination module 200 includes:
Motion detection object element, is used for utilizing background modeling algorithm that described video frame images is carried out algorithm
Analyze, it is thus achieved that sport foreground information, using described sport foreground information as motion detection target；And/or,
Static detection object element, is used for utilizing wagon detector that described video frame images is carried out algorithm and divides
Analysis, it is thus achieved that the positional information of vehicle target, and utilize background modeling algorithm that described video frame images is carried out
Identifying processing, it is thus achieved that sport foreground information, and according to described positional information and described sport foreground information,
Determine static detection target.
Corresponding, described shadowing module 300 includes: motion shadowing unit and/or static block
Judging unit；Wherein,
Motion shadowing unit, for calculating the foreground features point in described sport foreground information virtual
Number in coil；Judge that whether described number is more than occlusion threshold；The most corresponding motion detection mesh
It is designated as motion shelter target；
Static shadowing unit, for by the positional information of described static detection target and blocked area, parking stall
The positional information in territory compares, it is judged that the positional information of described static detection target and parking stall occlusion area
Positional information whether have common factor；The most corresponding static detection target is static shelter target.
Wherein, i.e. this parking stall is blocked decision maker can only have motion detection object element and correspondence
Motion shadowing unit；Or only there is the static shadowing list of static detection object element and correspondence
Unit；Again or these four unit all have and i.e. can detect moving target and can also detect static target.
The embodiment of the present invention provides a kind of vehicle management system, including:
Photographic head, for gathering the video frame images in parking lot；
The decision maker that parking stall described in above-mentioned any technical scheme is blocked.
Wherein, the decision maker that parking stall is blocked can be integrated in intellectual analysis one ball machine, or embeds
In formula intellectual analysis equipment, photographic head can be connected to embedded intelligence analytical equipment by switch.
Wherein, ball machine is the abbreviation of ball-shaped camera, is used for obtaining parking lot Video stream information, according to regarding
Frequently stream information, intelligent algorithm analysis parking position state, when needs capture license board information, ball-type is taken the photograph
Camera can focus on the information closely obtaining corresponding vehicle.
Embedded intelligence analytical equipment is a embedded board, is the operation platform of algorithm.Equipment
Core processing part is Jetson TK1, and equipment is to add cooling system on this basis, plug-in storage
Equipment, forms embedded device.
Based on technique scheme, the vehicle management system that the embodiment of the present invention provides can solve the problem that vehicle stops
During leaning against road parking stall, parking space management system based on video is easily blocked by car to be affected,
Cause the problem that parking stall real-time status is judged by accident by parking space management system, can more accurately detect blocking of parking stall
Situation.
In description, each embodiment uses the mode gone forward one by one to describe, and what each embodiment stressed is
With the difference of other embodiments, between each embodiment, identical similar portion sees mutually.Right
For device disclosed in embodiment, owing to it corresponds to the method disclosed in Example, so describe
Fairly simple, relevant part sees method part and illustrates.
Professional further appreciates that, respectively shows in conjunction with what the embodiments described herein described
The unit of example and algorithm steps, it is possible to electronic hardware, computer software or the two be implemented in combination in,
In order to clearly demonstrate the interchangeability of hardware and software, the most general according to function
Describe composition and the step of each example.These functions perform with hardware or software mode actually,
Depend on application-specific and the design constraint of technical scheme.Professional and technical personnel can be to each specific
Should be used for use different methods to realize described function, but this realization is it is not considered that beyond this
The scope of invention.
The method described in conjunction with the embodiments described herein or the step of algorithm can directly use hardware,
The software module that processor performs, or the combination of the two implements.Software module can be placed in and deposit at random
Reservoir (RAM), internal memory, read only memory (ROM), electrically programmable ROM, electric erasable can be compiled
Appointing well known in journey ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technical field
In the storage medium of other form of anticipating.
The decision method, device and the vehicle management system that block parking stall provided by the present invention above are carried out
It is discussed in detail.Principle and the embodiment of the present invention are set forth by specific case used herein,
The explanation of above example is only intended to help to understand method and the core concept thereof of the present invention.It should be pointed out that,
For those skilled in the art, under the premise without departing from the principles of the invention, also may be used
So that the present invention is carried out some improvement and modification, these improve and modify and also fall into the claims in the present invention
In protection domain.
Claims (10)
1. the decision method that a parking stall is blocked, it is characterised in that including:
Obtain the video frame images in parking lot；
Described video frame images is carried out Algorithm Analysis, determines the detection target in described video frame images；
Judge whether described detection target is positioned at parking stall occlusion area and has common factor；Wherein, described parking stall is blocked
Region is the region of driving side boundary line, distance parking stall the first preset distance；
The most corresponding detection target is shelter target.
2. the decision method that parking stall as claimed in claim 1 is blocked, it is characterised in that to described video
Two field picture carries out Algorithm Analysis, determines the detection target in described video frame images, including:
Detection region in described video frame images is carried out Algorithm Analysis, determines in described detection region
Detection target；Wherein, described detection region is the district of driving side boundary line, distance parking stall the second preset distance
Territory, and described second preset distance is more than described first preset distance.
3. the decision method that parking stall as claimed in claim 1 or 2 is blocked, it is characterised in that to described
Video frame images carries out Algorithm Analysis, determines the detection target in described video frame images, including:
Utilize background modeling algorithm that described video frame images is carried out Algorithm Analysis, it is thus achieved that sport foreground information,
Using described sport foreground information as motion detection target；And/or,
Utilize wagon detector that described video frame images is carried out Algorithm Analysis, it is thus achieved that the position of vehicle target
Information, and utilize background modeling algorithm to be identified described video frame images processing, it is thus achieved that sport foreground
Information, and according to described positional information and described sport foreground information, determine static detection target.
4. the decision method that parking stall as claimed in claim 3 is blocked, it is characterised in that when described detection
When target is for motion detection target, it is judged that whether described detection target is positioned at parking stall occlusion area common factor,
Including:
Calculate the number in virtual coil of the foreground features point in described sport foreground information；
Judge that whether described number is more than occlusion threshold；
The most corresponding motion detection target is motion shelter target.
5. the decision method that parking stall as claimed in claim 3 is blocked, it is characterised in that when described detection
When target is static detection target, it is judged that whether described detection target is positioned at parking stall occlusion area common factor,
Including:
The positional information of described static detection target is compared with the positional information of parking stall occlusion area,
Judge whether the positional information of described static detection target and the positional information of parking stall occlusion area have common factor；
The most corresponding static detection target is static shelter target.
6. the decision maker that a parking stall is blocked, it is characterised in that including:
Image collection module, for obtaining the video frame images in parking lot；
Detection target determination module, for described video frame images is carried out Algorithm Analysis, determine described in regard
Frequently the detection target in two field picture；
Shadowing module, is used for judging whether described detection target is positioned at parking stall occlusion area and has common factor；
Wherein, described parking stall occlusion area is the region of driving side boundary line, distance parking stall the first preset distance；If
It is that then corresponding detection target is shelter target.
7. the decision maker that parking stall as claimed in claim 6 is blocked, it is characterised in that described detection mesh
Mark determines that module is specially and the detection region in described video frame images is carried out Algorithm Analysis, determines described
The module of the detection target in detection region；Wherein, described detection region is distance parking stall driving lateral boundaries
The region of line the second preset distance, and described second preset distance is more than described first preset distance.
The decision maker that parking stall the most as claimed in claims 6 or 7 is blocked, it is characterised in that described inspection
Survey target determination module includes:
Motion detection object element, is used for utilizing background modeling algorithm that described video frame images is carried out algorithm
Analyze, it is thus achieved that sport foreground information, using described sport foreground information as motion detection target；And/or,
Static detection object element, is used for utilizing wagon detector that described video frame images is carried out algorithm and divides
Analysis, it is thus achieved that the positional information of vehicle target, and utilize background modeling algorithm that described video frame images is carried out
Identifying processing, it is thus achieved that sport foreground information, and according to described positional information and described sport foreground information,
Determine static detection target.
9. the decision maker that parking stall as claimed in claim 8 is blocked, it is characterised in that described in block and sentence
Disconnected module includes: motion shadowing unit and/or static shadowing unit；Wherein,
Motion shadowing unit, for calculating the foreground features point in described sport foreground information virtual
Number in coil；Judge that whether described number is more than occlusion threshold；The most corresponding motion detection mesh
It is designated as motion shelter target；
Static shadowing unit, for by the positional information of described static detection target and blocked area, parking stall
The positional information in territory compares, it is judged that the positional information of described static detection target and parking stall occlusion area
Positional information whether have common factor；The most corresponding static detection target is static shelter target.
10. a vehicle management system, it is characterised in that including:
Photographic head, for gathering the video frame images in parking lot；
The decision maker that parking stall as described in any one of claim 6 to 9 is blocked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610411016.0A CN106023594A (en) | 2016-06-13 | 2016-06-13 | Parking stall shielding determination method and device and vehicle management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610411016.0A CN106023594A (en) | 2016-06-13 | 2016-06-13 | Parking stall shielding determination method and device and vehicle management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106023594A true CN106023594A (en) | 2016-10-12 |
Family
ID=57090263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610411016.0A Pending CN106023594A (en) | 2016-06-13 | 2016-06-13 | Parking stall shielding determination method and device and vehicle management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106023594A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112767681A (en) * | 2020-12-16 | 2021-05-07 | 济南博观智能科技有限公司 | Traffic state detection method, device and related equipment |
| CN113206995A (en) * | 2021-04-29 | 2021-08-03 | 超级视线科技有限公司 | Method for judging deflection angle of parking line based on video frame |
| CN113570872A (en) * | 2021-08-13 | 2021-10-29 | 深圳市捷顺科技实业股份有限公司 | Processing method and device for blocking parking space event |
| CN113963571A (en) * | 2021-10-28 | 2022-01-21 | 深圳市捷顺科技实业股份有限公司 | Method and device for processing vehicle entering and exiting parking lot identification event |
| CN114529858A (en) * | 2022-04-21 | 2022-05-24 | 浙江大华技术股份有限公司 | Vehicle state recognition method, electronic device, and computer-readable storage medium |
| CN115188202A (en) * | 2022-07-18 | 2022-10-14 | 浙江大华技术股份有限公司 | Method and equipment for determining real motion state of vehicle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110376A (en) * | 2011-02-18 | 2011-06-29 | 汤一平 | Roadside parking space detection device based on computer vision |
| CN102855758A (en) * | 2012-08-27 | 2013-01-02 | 无锡北邮感知技术产业研究院有限公司 | Detection method for vehicle in breach of traffic rules |
| CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
| CN104574354A (en) * | 2013-09-26 | 2015-04-29 | 张国飙 | Parking space monitoring method based on edge detection |
| CN104794931A (en) * | 2015-04-15 | 2015-07-22 | 深圳市景阳信息技术有限公司 | Method and system for monitoring usage of parking space through cameras |
| US20150206014A1 (en) * | 2014-01-22 | 2015-07-23 | Xerox Corporation | Video-based system for automated detection of double parking violations |
| 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 |
-
2016
- 2016-06-13 CN CN201610411016.0A patent/CN106023594A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110376A (en) * | 2011-02-18 | 2011-06-29 | 汤一平 | Roadside parking space detection device based on computer vision |
| CN102855758A (en) * | 2012-08-27 | 2013-01-02 | 无锡北邮感知技术产业研究院有限公司 | Detection method for vehicle in breach of traffic rules |
| CN104574354A (en) * | 2013-09-26 | 2015-04-29 | 张国飙 | Parking space monitoring method based on edge detection |
| US20150206014A1 (en) * | 2014-01-22 | 2015-07-23 | Xerox Corporation | Video-based system for automated detection of double parking violations |
| CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
| CN104794931A (en) * | 2015-04-15 | 2015-07-22 | 深圳市景阳信息技术有限公司 | Method and system for monitoring usage of parking space through cameras |
| 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 |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112767681A (en) * | 2020-12-16 | 2021-05-07 | 济南博观智能科技有限公司 | Traffic state detection method, device and related equipment |
| CN113206995A (en) * | 2021-04-29 | 2021-08-03 | 超级视线科技有限公司 | Method for judging deflection angle of parking line based on video frame |
| CN113570872A (en) * | 2021-08-13 | 2021-10-29 | 深圳市捷顺科技实业股份有限公司 | Processing method and device for blocking parking space event |
| CN113963571A (en) * | 2021-10-28 | 2022-01-21 | 深圳市捷顺科技实业股份有限公司 | Method and device for processing vehicle entering and exiting parking lot identification event |
| CN113963571B (en) * | 2021-10-28 | 2023-10-17 | 深圳市捷顺科技实业股份有限公司 | Method and device for processing identification event of vehicle entering and exiting parking lot |
| CN114529858A (en) * | 2022-04-21 | 2022-05-24 | 浙江大华技术股份有限公司 | Vehicle state recognition method, electronic device, and computer-readable storage medium |
| CN115188202A (en) * | 2022-07-18 | 2022-10-14 | 浙江大华技术股份有限公司 | Method and equipment for determining real motion state of vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106023594A (en) | Parking stall shielding determination method and device and vehicle management system | |
| JP7052663B2 (en) | Object detection device, object detection method and computer program for object detection | |
| Gupte et al. | Detection and classification of vehicles | |
| US10043082B2 (en) | Image processing method for detecting objects using relative motion | |
| CN106023595B (en) | A kind of judgment method of exception parking, device and ball-shaped camera | |
| CN104537841B (en) | Unlicensed vehicle violation detection method and detection system thereof | |
| CN103021186B (en) | Vehicle monitoring method and vehicle monitoring system | |
| CN102792314B (en) | Cross traffic collision alert system | |
| CN102902955B (en) | The intelligent analysis method of a kind of vehicle behavior and system | |
| US11170272B2 (en) | Object detection device, object detection method, and computer program for object detection | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| Ke et al. | A cost-effective framework for automated vehicle-pedestrian near-miss detection through onboard monocular vision | |
| CN110619674B (en) | Three-dimensional augmented reality equipment and method for accident and alarm scene restoration | |
| JP7135665B2 (en) | VEHICLE CONTROL SYSTEM, VEHICLE CONTROL METHOD AND COMPUTER PROGRAM | |
| JP2008052517A (en) | Traffic measurement method and traffic measurement apparatus | |
| CN111497741B (en) | Collision early warning method and device | |
| CN112885108B (en) | Vehicle change detection method and system on parking space based on deep learning algorithm | |
| CN110341621A (en) | A kind of obstacle detection method and device | |
| CN106570487A (en) | Method and device for predicting collision between objects | |
| CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
| Dai et al. | A vehicle detection method via symmetry in multi-scale windows | |
| CN112348845B (en) | System and method for parking space detection and tracking | |
| CN106127805A (en) | A kind of vehicle enters position detecting method and system | |
| US20200394435A1 (en) | Distance estimation device, distance estimation method, and distance estimation computer program | |
| CN114119955A (en) | Method and device for detecting potential dangerous target |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |
|
| RJ01 | Rejection of invention patent application after publication |