CN109559519A - Monitoring device and its parking offense detection method, device, readable storage medium storing program for executing - Google Patents
Monitoring device and its parking offense detection method, device, readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109559519A CN109559519A CN201811552208.9A CN201811552208A CN109559519A CN 109559519 A CN109559519 A CN 109559519A CN 201811552208 A CN201811552208 A CN 201811552208A CN 109559519 A CN109559519 A CN 109559519A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- region
- identification region
- parking
- image
- 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
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of parking offense detection methods, this method comprises: obtaining the coverage of monitoring device；Demarcate the object detection area in the coverage；Obtain corresponding at least two picture frame of the coverage；Defining each described image frame and corresponding to the position of the object detection area is identification region；Judge whether each described image frame takes vehicle image in its identification region；When each described image frame takes vehicle image in its identification region, determines that the monitoring area of the monitoring device exists and disobey parking.The invention also discloses a kind of peccancy parking detector, monitoring device and readable storage medium storing program for executing.The present invention improves the efficiency and accuracy that parking is disobeyed in discovery, guarantees the patency in channel.
Description
Technical field
The present invention relates to technical field of transportation more particularly to a kind of parking offense detection method, peccancy parking detector,
Monitoring device and readable storage medium storing program for executing.
Background technique
With the development of the city, the needs of road management, the place that no parking is more and more, if without finding immediately simultaneously
The separated parking for handling these places, will lead to traffic jam, influence the appearance of most people.
The place that no parking is generally passed through manually with the presence or absence of the differentiation for disobeying parking at present, some are to pass through traffic
In the Regional patrolling that no parking to find to disobey parking, some are by artificial checking monitoring video, people by police or security personnel etc.
Whether to judge in the region that no parking against parking etc..However, above-mentioned mode inefficiency, accuracy also rely on
The sense of responsibility of personnel itself can not guarantee the unobstructed of channel very well
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of parking offense detection methods, it is intended to improve the effect that parking is disobeyed in discovery
Rate and accuracy guarantee the patency in channel.
To achieve the above object, the present invention provides a kind of parking offense detection method, which is characterized in that the parking offense
Detection method includes the following steps:
Obtain the coverage of monitoring device；
Demarcate the object detection area in the coverage；
Obtain corresponding at least two picture frame of the coverage；It defines each described image frame and corresponds to the target detection
The position in region is identification region；
Judge whether each described image frame takes vehicle image in its identification region；
When each described image frame takes vehicle image in its identification region, the monitoring of the monitoring device is determined
Region, which exists, disobeys parking.
Optionally, judge that the step of whether each described image frame takes vehicle image in its identification region includes:
Identify the vehicle's contour characteristic point in each described image frame；
According to each vehicle's contour characteristic point and its positional relationship of corresponding identification region, each described image frame is judged
Whether vehicle image is taken in its identification region.
Optionally, the vehicle's contour characteristic point includes Chinese herbaceous peony wheel characteristic point and/or back wheels of vehicle characteristic point, and the basis is each
The positional relationship of the vehicle's contour characteristic point and its corresponding identification region judges each described image frame in its identification region
The step of whether taking vehicle image include:
Judge whether the vehicle's contour characteristic point in each described image frame is located in its corresponding identification region；
When the vehicle's contour characteristic point is located in its corresponding identification region, the vehicle's contour characteristic point pair is determined
The picture frame answered takes vehicle image in its identification region；
When the vehicle's contour characteristic point is not located in its corresponding identification region, the vehicle's contour characteristic point is determined
Corresponding picture frame does not take vehicle image in its identification region.
Optionally, described according to each vehicle's contour characteristic point and its positional relationship of corresponding identification region, judgement
The step of whether each described image frame takes vehicle image in its identification region include:
The vehicle body region in each described image frame is determined according to the vehicle's contour characteristic point；
Judge whether the corresponding identification region in each vehicle body region intersects；
When the corresponding identification region intersection in the vehicle body region, determine the vehicle body region correspondence image frame at it
Vehicle image is taken in identification region；
When the corresponding identification region in the vehicle body region is non-intersecting, determine that the vehicle body region correspondence image frame exists
Vehicle image is not taken in its identification region.
Optionally, when the identification region corresponding when the vehicle body region intersects, determine the vehicle body region pair
The step of answering picture frame to take vehicle image in its corresponding identification region include:
When the corresponding identification region intersection in the vehicle body region, the corresponding identification in the vehicle body region is determined
The intersecting area in region；
When the intersecting area is greater than or equal to preset area, determine the corresponding picture frame in the vehicle body region in its knowledge
Vehicle image is taken in other region.
Optionally, after determining that the monitoring area of the monitoring device has the step of disobeying parking, further includes:
Determine the position of the monitoring device；
It is associated with the position and at least two picture frame and generates warning information.
Optionally, the step of object detection area demarcated in the coverage includes:
Determine the prohibition parking area domain in coverage；
Determine that potential disobey in the prohibition parking area domain stops region；
According to the potential object detection area disobeyed and stopped in region labeling coverage.
In addition, to achieve the goals above, the application also proposes a kind of peccancy parking detector, the parking offense inspection
Device is surveyed to include: memory, processor and be stored in the parking offense that can be run on the memory and on the processor
Program is detected, the parking offense detection program realizes as above described in any item parking offense inspections when being executed by the processor
The step of survey method.
In addition, to achieve the goals above, the application also proposes that a kind of monitoring device, the monitoring device include that image is adopted
Acquisition means and peccancy parking detector as described above, described image acquisition device and the peccancy parking detector connect
It connects.
In addition, to achieve the goals above, the application also proposes a kind of readable storage medium storing program for executing, on the readable storage medium storing program for executing
It is stored with parking offense detection program, the parking offense detection program is realized as above described in any item when being executed by processor
The step of parking offense detection method.
A kind of parking offense detection method that the embodiment of the present invention proposes, the spotting in the coverage of monitoring device
Detection zone, prohibition parking area domain is configured in the actual scene that object detection area is monitored according to monitoring device, target detection
Whether at least two picture frames that region decision obtains all take in its identification region, if having vehicle in each picture frame
Image then shows that prohibition parking area domain has vehicle commander's time to stop in actual scene that monitoring device is monitored, then may be used in identification region
Determine exist disobey parking, and spotting detection zone carry out prohibition parking area domain in it is separated stop identifying, can be improved disobey parking
The accuracy of judgement.It is detected automatically by above-mentioned image recognition mode and disobeys parking, improve efficiency and standard that parking is disobeyed in discovery
True property, guarantees the patency in channel.
Detailed description of the invention
Fig. 1 is the hardware structural diagram of the monitoring device of the embodiment of the present invention；
Fig. 2 is the hardware structural diagram of image collecting device in Fig. 1；
Fig. 3 is the flow diagram of the parking offense detection method first embodiment in the embodiment of the present invention；
Fig. 4 is the distribution signal in each region in the corresponding picture frame of coverage of the monitoring device in the embodiment of the present invention
Figure；
Fig. 5 is the flow diagram of the parking offense detection method second embodiment in the embodiment of the present invention；
Fig. 6 is the flow diagram of the parking offense detection method 3rd embodiment in the embodiment of the present invention；
Fig. 7 is the flow diagram of the parking offense detection method fourth embodiment in the embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are: obtaining the coverage of monitoring device；Demarcate the coverage
In object detection area；Obtain corresponding at least two picture frame of the coverage；Judge each described image frame in its knowledge
Whether vehicle image is taken in other region；When each described image frame takes vehicle image in its identification region, when
When each described image frame takes vehicle image in its identification region, determines that the position of the monitoring device exists and disobey
Parking.
Since the prior art differentiates that prohibition parking area domain inefficiency, accuracy also rely on personnel itself by artificial mode
Sense of responsibility, can not guarantee the unobstructed of channel very well.
The present invention provides a solution, and parking is disobeyed in detection automatically by way of image recognition, improves discovery and disobeys
The efficiency and accuracy of parking, guarantee the patency in channel.
The present invention proposes a kind of monitoring device, is specifically used for detection parking offense, is particularly applicable to public place (such as road
Road or community channel etc.) prohibition parking area domain parking offense detection.
In the present embodiment, referring to Fig.1, monitoring device specifically includes image collecting device 100 and parking offense detection dress
Set 200.Image collecting device 100 is connect with peccancy parking detector 200, and peccancy parking detector 200 can be adopted from image
Acquisition means 100 obtain image data.Image collecting device 100 can specifically be set to the scene where the domain of prohibition parking area, image collector
100 shooting direction is set towards prohibition parking area domain, with the picture frame of scene where acquiring prohibition parking area domain.Wherein, image collecting device
100 maximum region that can be taken is the coverage of monitoring device, and the prohibition parking area domain is located at the monitoring device
In coverage.
As shown in Fig. 2, the peccancy parking detector 200 may include: processor 2001, such as CPU, memory
2002.Memory 2002 can be high speed RAM memory, be also possible to stable memory (non-volatile memory),
Such as magnetic disk storage.Memory 2002 optionally can also be the storage device independently of aforementioned processor 2001.
Processor 2001 is connect with memory 2002, image collecting device 100 respectively.Processor 2001 obtains Image Acquisition
100 acquired image frame of device, and after it can determine that monitoring device position exists and disobeys parking, the picture frame that will acquire
It is stored.
It will be understood by those skilled in the art that the restriction of apparatus structure shown in Figure 2 not structure twin installation, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Fig. 2, as may include parking offense detection journey in a kind of memory 2002 of computer storage medium
Sequence.
In device shown in Fig. 2, processor 2001 can be used for that the parking offense stored in memory 2002 is called to examine
Ranging sequence, and execute the correlation step operation of parking offense detection method in following embodiment.
In addition, the embodiment of the present invention also proposes a kind of readable storage medium storing program for executing, it is stored on the readable storage medium storing program for executing violating the regulations
Parking detection program, the parking offense detection program realize the correlation of following parking offense detection method when being executed by processor
Step operation.
Referring to Fig. 3, the embodiment of the present invention provides a kind of parking offense detection method, the parking offense detection method packet
It includes:
Step S10 obtains the coverage of monitoring device；
The maximum region that can be taken of image collecting device 100 is the coverage of monitoring device.Specifically, step
The detection presetting bit that the monitoring device can be obtained before S10, adjusts the monitoring device according to the detection presetting bit of acquisition
The prohibition parking area domain of shooting direction, the scene for monitoring monitoring device is located in the coverage.Wherein, here detection is pre-
Set can be determined by obtaining the setting parameter of monitoring personnel.
Step S20 demarcates the object detection area in the coverage；
Prohibition parking area domain in the scene monitored according to monitoring device the spotting detection zone in coverage.Target
The area of detection zone is less than prohibition parking area domain.
The setting parameter that the calibration of object detection area can directly acquire monitoring personnel is configured.In addition, prohibition parking area domain
It may particularly include traffic areas and potential disobey stop region, for example, the channel in coverage is defined as prohibition parking area domain, in channel
Portion may be defined as traffic areas, and the two sides or the side in two sides in channel may be defined as potential disobey and stop region.When vehicle is in passage
When being stopped in region, it is believed that be due to traffic jam, traffic instruction or vehicle damage caused by；When vehicle enters potential disobey
When stopping region and stopping, it is believed that be caused by being stopped vehicle violation.Therefore, the target in the coverage is demarcated
The step of detection zone, may also include that
Step S21 determines the prohibition parking area domain in coverage；
Step S22 determines that potential disobey in the prohibition parking area domain stops region；
Step S23, according to the potential object detection area disobeyed and stopped in region labeling coverage.
Specifically, potential separated region of stopping can be set by obtaining the setting parameter of monitoring personnel.In addition, can also basis
After image collecting device 100 is adjusted to detection presetting bit by the setting parameter of monitoring personnel, the bat of image collecting device 100 is obtained
Picture frame corresponding to range is taken the photograph, the range in channel is identified in the picture frame of acquisition and is defined as prohibition parking area domain, according to default
The prohibition parking area domain is divided into traffic areas to width direction of the area ratio along channel and potential disobey stops region.In coverage
It is middle that the potential separated location for stopping region is demarcated as object detection area.
Object detection area is the fixed area in the coverage of image collecting device 100, will not be with image collector
The difference of picture frame acquired in setting 100 and change.Specifically, the edge according to object detection area generates visualization side
Frame determines object detection area in acquired image after image collecting device 100 obtains the corresponding picture frame of coverage
Position in frame adds above-mentioned visualization frame in identified position and generates monitoring image.Peccancy parking detector can
Monitoring image is sent in display equipment and is shown, monitoring image can also be stored.
Step S30 obtains corresponding at least two picture frame of the coverage；It defines described in each described image frame correspondence
The position of object detection area is identification region；
The corresponding video data of the sustainable acquisition coverage of image collecting device 100.It is adopted in image collecting device 100
In the video data of collection, can obtain image collecting device 100 the first moment coverage collected it is corresponding at least one
Picture frame, and image collecting device 100 is obtained at least one corresponding picture frame of the second moment coverage collected.The
Preset time is spaced between one moment and the second moment, the length of preset time can be arranged according to actual needs.For example, when default
Between can be chosen for 5 minutes.
In addition, also can recognize that each picture frame collected of image collecting device 100 or interval setting duration identify image
Whether vehicle image is taken in its identification region in 100 acquired image frame of acquisition device, recognizes picture frame in its knowledge
When other region takes vehicle image, the acquisition time of the picture frame was defined as the first moment.The timing since the first moment,
It reached for the second moment by above-mentioned preset time, obtains image collecting device 100 in the second moment coverage collected
Corresponding picture frame.
Step S40, judges whether each described image frame takes vehicle image in its identification region；
Whether the picture frame for judging that the first moment obtained takes vehicle image in its identification region, and judges for the second moment
Whether the picture frame of acquisition takes vehicle image in its identification region.Here vehicle image may particularly include the vehicle of vehicle
The topography of image or vehicle.
When each described image frame takes vehicle image in its identification region, step S50 is executed；When each figure
When taking vehicle image in its identification region as frame, step S60 is executed.
When the picture frame that the first moment obtained takes vehicle image in its identification region, and the acquisition of the second moment
Picture frame executes step S50 when its identification region takes vehicle image；When the picture frame that the first moment obtained is in its identification
When being not picked up by vehicle image in region, and/or, the picture frame that the second moment obtained is not picked up by its identification region
When vehicle image, step S60 is executed.
Specifically, the step of whether each described image frame takes vehicle image in its identification region judged can include:
It identifies with the presence or absence of vehicles identifications object image (such as car door, car light, wheel) in the identification region of each picture frame, if an image
There are vehicles identifications object images in its identification region for frame, then can determine that and take vehicle figure in the identification region of the picture frame
Picture can determine that the picture frame in its identification region if vehicles identifications object image is not present in a picture frame in its identification region
Inside it is not picked up by vehicle image.
Further, since possible imperfect or due to shooting angle the influence of vehicles identifications object image in identification region causes
The identification of vehicles identifications object is not accurate enough in identification region, therefore judges whether each described image frame shoots in its identification region
It may also include that the step of vehicle image
Step S41 identifies vehicle's contour characteristic point in each picture frame；
Step S42 judges each institute according to each vehicle's contour characteristic point and its positional relationship of corresponding identification region
State whether picture frame takes vehicle image in its identification region.
Here vehicle's contour characteristic point be picture frame in vehicle vehicle image profile on some or all of point.Tool
Body, the corresponding picture frame of vehicle's contour characteristic point can be determined in its cog region when above-mentioned positional relationship meets preset condition
Vehicle image is taken in domain；When above-mentioned positional relationship is unsatisfactory for preset condition, the corresponding figure of vehicle's contour characteristic point is determined
As frame is not picked up by vehicle image in its identification region.It should be noted that if identification is less than vehicle's contour in picture frame
Characteristic point then shows that picture frame is not picked up by vehicle image, there is no disobeying to stop possibility, then step S60 can be performed.
Step S50 determines that the monitoring area of the monitoring device exists and disobeys parking；
Step S60 determines that the monitoring area of the monitoring device is not present and disobeys parking.
Further, it when each described image frame takes vehicle image in its identification region, can further determine that each
Whether vehicle image of the picture frame in its identification region belongs to same vehicle.Specifically, vehicle figure in identification region can be analyzed
The characteristic parameters such as color, the distribution of picture judge whether the characteristic parameter of vehicle image of each image in its identification region is consistent,
If consistent, step S50 is just executed if inconsistent and returns to step S30.
Wherein, monitoring area here is the region in actual scene corresponding to the coverage of monitoring device.
It is picture frame corresponding to the coverage of image collecting device 100 shown in Fig. 4, wherein 01,02 referring to Fig. 4
For vehicle in picture frame two positions that may be present, 03 is prohibition parking area domain, and 031 is traffic areas, and 032 is the potential area Wei Ting
Domain, 04 is object detection area corresponding identification region in picture frame.Specifically, when vehicle is located at 01 position, picture frame
Identification region in be not picked up by vehicle image, when vehicle is located at 02 position, take vehicle in the identification region of picture frame
Image.
A kind of parking offense detection method proposed in the present embodiment, the spotting in the coverage of monitoring device
Detection zone, prohibition parking area domain is configured in the actual scene that object detection area is monitored according to monitoring device, target detection
Whether at least two picture frames that region decision obtains all take in its identification region, if having vehicle in each picture frame
Image then shows that prohibition parking area domain has vehicle commander's time to stop in actual scene that monitoring device is monitored, then may be used in identification region
Determine exist disobey parking, and spotting detection zone carry out prohibition parking area domain in it is separated stop identifying, can be improved disobey parking
The accuracy of judgement.It is detected automatically by above-mentioned image recognition mode and disobeys parking, improve efficiency and standard that parking is disobeyed in discovery
True property, guarantees the patency in channel.
Specifically, being based on above-mentioned first embodiment, parking offense detection method second embodiment of the present invention is proposed, second
In embodiment, it can recognize the point of wheel portion in the profile of vehicle image as vehicle's contour characteristic point.Vehicle's contour characteristic point
It may include Chinese herbaceous peony wheel characteristic point and/or back wheels of vehicle characteristic point.Referring to Fig. 5, it is described according to each vehicle's contour characteristic point and its
The positional relationship of corresponding identification region, judges whether each described image frame takes the step of vehicle image in its identification region
Suddenly include:
Step S421, judges whether the vehicle's contour characteristic point in each described image frame is located at its corresponding identification region
It is interior；
When the vehicle's contour characteristic point is located in its corresponding identification region, step S4211 is executed；When the vehicle
When contour feature point is not located in its corresponding identification region, step S4212 is executed.
Specifically, can determine that the Chinese herbaceous peony wheel characteristic point in the picture frame successively got and the whether equal position of back wheels of vehicle characteristic point
In in the corresponding identification region of device, if so, S4211 is thened follow the steps, if it is not, thening follow the steps S4212.
In addition, also can determine that whether are Chinese herbaceous peony wheel characteristic point in picture frame that the first moment got or back wheels of vehicle characteristic point
In its corresponding identification region, if Chinese herbaceous peony wheel characteristic point or back wheels of vehicle characteristic point are located in its corresponding identification region,
It is right further to judge whether Chinese herbaceous peony wheel characteristic point and back wheels of vehicle characteristic point in picture frame that the second moment got are respectively positioned on its
In the identification region answered, if Chinese herbaceous peony wheel characteristic point and back wheels of vehicle characteristic point are respectively positioned in its corresponding identification region, step is executed
Rapid S4211；If it is corresponding not to be located at its for Chinese herbaceous peony wheel characteristic point and back wheels of vehicle characteristic point in the picture frame that the first moment got
It is right not to be located at its for Chinese herbaceous peony wheel characteristic point and/or back wheels of vehicle characteristic point in identification region or in picture frame that the second moment got
In the identification region answered, S4212 is thened follow the steps.
Step S4211 determines that the corresponding picture frame of the vehicle's contour characteristic point takes vehicle in its identification region
Image；
Step S4212 determines that the corresponding picture frame of the vehicle's contour characteristic point is not picked up by its identification region
Vehicle image.
In the present embodiment, by Chinese herbaceous peony wheel characteristic point and/or back wheels of vehicle characteristic point as vehicle's contour characteristic point, and lead to
Cross the positional relationship characterization picture frame between analysis Chinese herbaceous peony wheel characteristic point and/or the corresponding identification region of back wheels of vehicle characteristic point
In vehicle position of the vehicle image relative to identification region, even if without complete vehicles identifications object image in identification region
Or vehicles identifications object image is not recognized, the identification of vehicle image in identification region can also be realized, so that accurately characterization is each
Whether picture frame takes vehicle image in its identification region.
In addition, being based on above-mentioned first embodiment, parking offense detection method 3rd embodiment of the present invention is proposed, in third reality
It applies in example, described according to each vehicle's contour characteristic point and its positional relationship of corresponding identification region referring to Fig. 6, judgement
The step of whether each described image frame takes vehicle image in its identification region include:
Step S422 determines the vehicle body region in each described image frame according to the vehicle's contour characteristic point；
When whole points on the profile for the vehicle image that vehicle's contour characteristic point is vehicle in picture frame or between profile
When multiple of distribution, vehicle body region may be defined as by the closed figure that vehicle's contour characteristic point is fitted.According to each
Vehicle's contour characteristic point in picture frame determines the vehicle body region that vehicle is occupied in coverage in the picture frame.For example,
Four wheel characteristics points of vehicle image in extractable picture frame, the closed figure that four vehicle characteristics point lines are formed as
Vehicle body region.
Step S423, judges whether each vehicle body region and its corresponding identification region intersect；
When the vehicle body region and its corresponding identification region intersect, step S4231 is executed；When the vehicle body region and
When its corresponding identification region is non-intersecting, step S4232 is executed.
Step S4231 determines that the corresponding picture frame in the vehicle body region takes vehicle image in its identification region；
Step S4232 determines that the corresponding picture frame in the vehicle body region does not take vehicle image in its identification region.
When in a picture frame vehicle body region and identification region it is completely overlapped or when partly overlapping, i.e. vehicle body region is right with it
The identification region intersection answered, step S4231 can be performed at this time, determine that the picture frame takes vehicle figure in its identification region
Picture；When the vehicle region in a picture frame is not completely be overlapped with identification region, i.e. vehicle body region and its corresponding identification region
When non-intersecting, step S4232 can be performed at this time, determine that the picture frame is not picked up by vehicle image in its identification region.It is right
Each picture frame is performed both by above-mentioned judgement, can judge whether each picture frame takes vehicle image in its identification region.
In the present embodiment, by the vehicle body region in each picture frame of determination, analyze vehicle body region and identification region it
Between positional relationship characterization picture frame in vehicle position of the vehicle image relative to object detection area, even if identification region
Interior no complete vehicles identifications object image does not recognize vehicles identifications object image, can also realize vehicle figure in identification region
The identification of picture, to accurately characterize whether each picture frame takes vehicle image in its identification region.
Further, it is based on above-mentioned 3rd embodiment, proposes parking offense detection method fourth embodiment of the present invention, the
In four embodiments, referring to Fig. 7, when the identification region corresponding when the vehicle body region intersects, the vehicle body area is determined
The step of domain correspondence image frame takes vehicle image in its identification region include:
Step S4231a, when the vehicle body region it is corresponding identification region intersection when, determine the vehicle body region with
The intersecting area of its corresponding identification region；
Here intersecting area refers to the area size in vehicle body region and identification region lap in same picture frame.
Step S4231b determines that the vehicle body region is corresponding when the intersecting area is greater than or equal to preset area
Picture frame takes vehicle image in its identification region.
Preset area can be set according to the actual situation.When the corresponding identification region in vehicle body region in a picture frame
Intersecting area when being greater than or equal to preset area, it may be determined that the picture frame is taken in its identification region against stopping possibility
Suspect vehicle image, when the identification region of each picture frame takes suspect vehicle image, then can determine that it is described monitoring set
Standby monitoring area, which exists, disobeys parking.When the intersecting area of the corresponding identification region in vehicle body region in a picture frame is less than
When preset area, then show that the vehicle in the picture frame may be strayed into potential disobey during traffic areas is current and stop region, and
Cause the vehicle region in picture frame Chong Die with identification region, can determine that the picture frame is not shot in its identification region at this time
To vehicle image.
In the present embodiment, it is greater than or equal to preset area in the intersecting area of the corresponding identification region in vehicle body region
When, just determine that the corresponding picture frame in vehicle body region takes vehicle image in its identification region.By the above-mentioned means, can make to disobey
The judgement of parking is more accurate, avoids being strayed into the testing result that the potential separated vehicle for stopping region influences separated parking.
Further, based on above-mentioned first embodiment to fourth embodiment, determine the monitoring area of the monitoring device
After the step of there are separated parkings, further includes:
Step S70 determines the position of the monitoring device；
In a predeterminable area (such as residential quarters or administrative region), it can need according to road management in different positions
Monitoring device is installed, and each monitoring device and its position are associated.Therefore, it can determine that monitoring is set according to above-mentioned association
Standby position.
Step S80 is associated with the position and at least two picture frame and generates warning information.
The position of monitoring device is associated with at least two above-mentioned picture frames, and according to after association position and figure
As frame generates warning information.Warning information can be stored after generating, so that monitoring personnel, which can consult relevant disobey, stops evidence.This
Outside, warning information also can be transmitted to the mobile terminal of management platform or administrative staff after generating and prompt, so that related personnel
The vehicle that the position can be handled in time, which is disobeyed, stops situation.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of parking offense detection method, which is characterized in that detection method includes the following steps for the parking offense:
Obtain the coverage of monitoring device；
Demarcate the object detection area in the coverage；
Obtain corresponding at least two picture frame of the coverage；It defines each described image frame and corresponds to the object detection area
Position be identification region；
Judge whether each described image frame takes vehicle image in its identification region；
When each described image frame takes vehicle image in its identification region, the monitoring area of the monitoring device is determined
There are separated parkings.
2. parking offense detection method as described in claim 1, which is characterized in that judge each described image frame in its cog region
The step of whether taking vehicle image in domain include:
Identify the vehicle's contour characteristic point in each described image frame；
According to each vehicle's contour characteristic point and its positional relationship of corresponding identification region, judge each described image frame at it
Whether vehicle image is taken in identification region.
3. parking offense detection method as claimed in claim 2, which is characterized in that the vehicle's contour characteristic point includes Chinese herbaceous peony
Take turns characteristic point and/or back wheels of vehicle characteristic point, the position according to each vehicle's contour characteristic point and its corresponding identification region
Relationship is set, judges that the step of whether each described image frame takes vehicle image in its identification region includes:
Judge whether the vehicle's contour characteristic point in each described image frame is located in its corresponding identification region；
When the vehicle's contour characteristic point is located in its corresponding identification region, determine that the vehicle's contour characteristic point is corresponding
Picture frame takes vehicle image in its identification region；
When the vehicle's contour characteristic point is not located in its corresponding identification region, determine that the vehicle's contour characteristic point is corresponding
Picture frame do not take vehicle image in its identification region.
4. parking offense detection method as claimed in claim 2, which is characterized in that described according to each vehicle's contour feature
The positional relationship of point and its corresponding identification region, judges whether each described image frame takes vehicle figure in its identification region
As the step of include:
The vehicle body region in each described image frame is determined according to the vehicle's contour characteristic point；
Judge whether the corresponding identification region in each vehicle body region intersects；
When the corresponding identification region intersection in the vehicle body region, determine the vehicle body region correspondence image frame in its identification
Vehicle image is taken in region；
When the corresponding identification region in the vehicle body region is non-intersecting, determine the vehicle body region correspondence image frame in its knowledge
Vehicle image is not taken in other region.
5. parking offense detection method as claimed in claim 4, which is characterized in that described when the vehicle body region is corresponding
Identification region intersection when, determine that the vehicle body region correspondence image frame takes vehicle image in its corresponding identification region
The step of include:
When the corresponding identification region intersection in the vehicle body region, the corresponding identification region in the vehicle body region is determined
Intersecting area；
When the intersecting area is greater than or equal to preset area, determine the corresponding picture frame in the vehicle body region in its cog region
Vehicle image is taken in domain.
6. parking offense detection method as described in claim 1, which is characterized in that determine the monitoring area of the monitoring device
After the step of there are separated parkings, further includes:
Determine the position of the monitoring device；
It is associated with the position and at least two picture frame and generates warning information.
7. such as parking offense detection method described in any one of claims 1 to 6, which is characterized in that the calibration bat
The step of object detection area taken the photograph in range includes:
Determine the prohibition parking area domain in coverage；
Determine that potential disobey in the prohibition parking area domain stops region；
According to the potential object detection area disobeyed and stopped in region labeling coverage.
8. a kind of peccancy parking detector, which is characterized in that the peccancy parking detector includes: memory, processor
And it is stored in the parking offense detection program that can be run on the memory and on the processor, the parking offense detection
The step of parking offense detection method as described in any one of claims 1 to 7 is realized when program is executed by the processor.
9. a kind of monitoring device, which is characterized in that the monitoring device includes image collecting device and as claimed in claim 8
Peccancy parking detector, described image acquisition device are connected with the peccancy parking detector.
10. a kind of readable storage medium storing program for executing, which is characterized in that parking offense detection program is stored on the readable storage medium storing program for executing,
The parking offense detection program realizes the parking offense inspection as described in any one of claims 1 to 7 when being executed by processor
The step of survey method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552208.9A CN109559519A (en) | 2018-12-18 | 2018-12-18 | Monitoring device and its parking offense detection method, device, readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552208.9A CN109559519A (en) | 2018-12-18 | 2018-12-18 | Monitoring device and its parking offense detection method, device, readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109559519A true CN109559519A (en) | 2019-04-02 |
Family
ID=65870418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811552208.9A Pending CN109559519A (en) | 2018-12-18 | 2018-12-18 | Monitoring device and its parking offense detection method, device, readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109559519A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110491135A (en) * | 2019-08-20 | 2019-11-22 | 深圳市商汤科技有限公司 | Detect the method and relevant apparatus of parking offense |
| CN110491132A (en) * | 2019-07-11 | 2019-11-22 | 平安科技（深圳）有限公司 | Vehicle based on video frame picture analyzing, which is disobeyed, stops detection method and device |
| CN110599796A (en) * | 2019-09-06 | 2019-12-20 | 北京筑梦园科技有限公司 | Parking space state judgment method, server and parking management system |
| CN111951601A (en) * | 2020-08-05 | 2020-11-17 | 智慧互通科技有限公司 | Method and device for identifying parking positions of distribution vehicles |
| CN112232441A (en) * | 2020-11-18 | 2021-01-15 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
| WO2021051621A1 (en) * | 2019-09-16 | 2021-03-25 | 平安科技（深圳）有限公司 | Parking space determination method, terminal device and computer readable storage medium |
| CN113380047A (en) * | 2021-06-22 | 2021-09-10 | 重庆盛海科技发展有限公司 | Illegal parking detection method based on traditional camera |
| CN114141055A (en) * | 2020-08-13 | 2022-03-04 | 纵目科技（上海）股份有限公司 | Parking space detection device and detection method of intelligent parking system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116984A (en) * | 2013-01-21 | 2013-05-22 | 信帧电子技术（北京）有限公司 | Method to detect illegal parking |
| CN104318206A (en) * | 2014-09-30 | 2015-01-28 | 东软集团股份有限公司 | Barrier detection method and apparatus |
| US20150102946A1 (en) * | 2013-10-10 | 2015-04-16 | Safer Place Ltd. | System and method for enforcing parking rules |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN108257410A (en) * | 2017-12-25 | 2018-07-06 | 陈飞 | The accurate air navigation aid in parking stall that a kind of on-site supervision cooperates with navigation system |
| CN108269312A (en) * | 2018-03-21 | 2018-07-10 | 厦门华方软件科技有限公司 | A kind of illegal parking monitoring system and method |
| CN108491827A (en) * | 2018-04-13 | 2018-09-04 | 腾讯科技（深圳）有限公司 | A kind of vehicle checking method, device and storage medium |
-
2018
- 2018-12-18 CN CN201811552208.9A patent/CN109559519A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116984A (en) * | 2013-01-21 | 2013-05-22 | 信帧电子技术（北京）有限公司 | Method to detect illegal parking |
| US20150102946A1 (en) * | 2013-10-10 | 2015-04-16 | Safer Place Ltd. | System and method for enforcing parking rules |
| CN104318206A (en) * | 2014-09-30 | 2015-01-28 | 东软集团股份有限公司 | Barrier detection method and apparatus |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN108257410A (en) * | 2017-12-25 | 2018-07-06 | 陈飞 | The accurate air navigation aid in parking stall that a kind of on-site supervision cooperates with navigation system |
| CN108269312A (en) * | 2018-03-21 | 2018-07-10 | 厦门华方软件科技有限公司 | A kind of illegal parking monitoring system and method |
| CN108491827A (en) * | 2018-04-13 | 2018-09-04 | 腾讯科技（深圳）有限公司 | A kind of vehicle checking method, device and storage medium |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110491132A (en) * | 2019-07-11 | 2019-11-22 | 平安科技（深圳）有限公司 | Vehicle based on video frame picture analyzing, which is disobeyed, stops detection method and device |
| CN110491135A (en) * | 2019-08-20 | 2019-11-22 | 深圳市商汤科技有限公司 | Detect the method and relevant apparatus of parking offense |
| CN110491135B (en) * | 2019-08-20 | 2021-10-22 | 深圳市商汤科技有限公司 | Method and related device for detecting illegal parking |
| CN110599796A (en) * | 2019-09-06 | 2019-12-20 | 北京筑梦园科技有限公司 | Parking space state judgment method, server and parking management system |
| WO2021051621A1 (en) * | 2019-09-16 | 2021-03-25 | 平安科技（深圳）有限公司 | Parking space determination method, terminal device and computer readable storage medium |
| CN111951601A (en) * | 2020-08-05 | 2020-11-17 | 智慧互通科技有限公司 | Method and device for identifying parking positions of distribution vehicles |
| CN114141055A (en) * | 2020-08-13 | 2022-03-04 | 纵目科技（上海）股份有限公司 | Parking space detection device and detection method of intelligent parking system |
| CN114141055B (en) * | 2020-08-13 | 2024-04-16 | 纵目科技（上海）股份有限公司 | Parking space detection device and method of intelligent parking system |
| CN112232441A (en) * | 2020-11-18 | 2021-01-15 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
| CN112232441B (en) * | 2020-11-18 | 2023-06-06 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
| CN113380047A (en) * | 2021-06-22 | 2021-09-10 | 重庆盛海科技发展有限公司 | Illegal parking detection method based on traditional camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109559519A (en) | Monitoring device and its parking offense detection method, device, readable storage medium storing program for executing | |
| CN113284366A (en) | Vehicle blind area early warning method, early warning device, MEC platform and storage medium | |
| WO2020022042A1 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| US10803340B2 (en) | Method and apparatus for license plate recognition using multiple fields of view | |
| CN107464446B (en) | Inspection method and device for vertical parking space parking information | |
| WO2016107302A1 (en) | Method and system for inspecting moving vehicles | |
| JP2019192209A (en) | Learning target image packaging device and method for artificial intelligence of video movie | |
| CN109446926A (en) | A kind of traffic monitoring method and device, electronic equipment and storage medium | |
| CN113240880A (en) | Fire detection method and device, electronic equipment and storage medium | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| KR20170096437A (en) | System and method for providing traffic information using image processing | |
| Pyykönen et al. | Multi-camera-based smoke detection and traffic pollution analysis system | |
| CN106571040A (en) | Suspicious vehicle confirmation method and equipment | |
| CN103886761B (en) | Intelligent bayonet system and the operation method thereof of road exception parking can be found fast | |
| JP5049551B2 (en) | ETC communication monitoring apparatus and ETC communication monitoring method | |
| CN111768630A (en) | Violation waste image detection method and device and electronic equipment | |
| CN111243024A (en) | Parking area identification system and method, detection system and method and security system | |
| CN110909641A (en) | Method, device and system for detecting overload of motorcycle | |
| CN112215038A (en) | Specific vehicle identification system, method, and storage medium | |
| JP2019192201A (en) | Learning object image extraction device and method for autonomous driving | |
| KR102319938B1 (en) | A method and system for providing a blacklist to block the use of illegal vehicle license plates in parking lots | |
| CN105469091B (en) | A kind of vehicle identification method and device | |
| KR102121423B1 (en) | Server and method for recognizing road line using camera image | |
| CN109508632B (en) | Image processing method, device, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |