CN108831158A - It disobeys and stops monitoring method, device and electric terminal - Google Patents
It disobeys and stops monitoring method, device and electric terminal Download PDFInfo
- Publication number
- CN108831158A CN108831158A CN201810946422.6A CN201810946422A CN108831158A CN 108831158 A CN108831158 A CN 108831158A CN 201810946422 A CN201810946422 A CN 201810946422A CN 108831158 A CN108831158 A CN 108831158A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- feature vector
- image data
- road
- similarity
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides a kind of disobey and stops monitoring method, device and electric terminal.Obtain the road image data in monitoring region；The road image data are subjected to match cognization, to identify the occupy-street-exploit area image in the road image data；Extract the monitoring feature vector in occupy-street-exploit area image；It compares the monitoring feature vector and preparatory standard feature vector to obtain the similarity of the monitoring feature vector Yu the standard feature vector；And the monitoring result of the road monitoring in the monitoring region is obtained according to the similarity.
Description
Technical field
The present invention relates to field of image processings, disobey in particular to one kind and stop monitoring method, device and electric terminal.
Background technique
It is directed to the monitoring of the illegal parking of urban road at present, checks generally by traffic police's patrol to judge in road
With the presence or absence of the behavior of illegal parking, based on manually being known otherwise, this mode relative efficiency is lower, and compares
Waste of manpower resource.
Summary of the invention
In view of this, a kind of disobey that be designed to provide of the embodiment of the present invention stops monitoring method, device and electric terminal.
A kind of disobey provided in an embodiment of the present invention stops monitoring method, including：
Obtain the road image data in monitoring region；
The road image data are subjected to match cognization, to identify the occupy-street-exploit area in the road image data
Image；
Extract the monitoring feature vector in occupy-street-exploit area image；
By the monitoring feature vector and preparatory standard feature vector compare to obtain the monitoring feature vector with
The similarity of the standard feature vector；And
The monitoring result of the road monitoring in the monitoring region is obtained according to the similarity.
The embodiment of the present invention also provides a kind of disobey and stops monitoring device, including：
Module is obtained, for obtaining the road image data in monitoring region；
Identification module, for the road image data to be carried out match cognization, to identify the road image data
In occupy-street-exploit area image；
Extraction module, for extracting the monitoring feature vector in occupy-street-exploit area image；
Contrast module, for comparing the monitoring feature vector and preparatory standard feature vector to obtain the prison
Survey the similarity of feature vector and the standard feature vector；
Module is obtained, the monitoring result of the road monitoring for obtaining the monitoring region according to the similarity.
The embodiment of the present invention also provides a kind of electric terminal, including memory, processor and is stored on the memory
And the computer program that can be run on the processor, the processor realize above-mentioned side when executing the computer program
The step of method.
Compared with prior art, the separated of the embodiment of the present invention stops monitoring method, by the road for the detection zone that will be obtained
Image data is handled to obtain monitoring feature vector, and monitoring feature vector is corresponding with there is no the road image in stopping time is disobeyed
Standard feature vector carries out judgement similarity, to obtain the monitoring result monitored to road, it is no longer necessary to manual identified road,
The efficiency to road monitoring can be improved, save human resources.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, special embodiment below, and appended by cooperation
Attached drawing is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the block diagram of electric terminal provided in an embodiment of the present invention.
Fig. 2 is the flow chart provided in an embodiment of the present invention disobeyed and stop monitoring method.
Fig. 3 is another separated flow chart for stopping monitoring method provided in an embodiment of the present invention.
Fig. 4 is the partial process view provided in an embodiment of the present invention disobeyed and stop monitoring method.
Fig. 5 is the functional block diagram provided in an embodiment of the present invention disobeyed and stop monitoring device.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should be noted that：Similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
As shown in Figure 1, being the block diagram of the electric terminal 100.The electric terminal 100 includes disobeying to stop monitoring dress
Set 110, memory 111, storage control 112, processor 113, Peripheral Interface 114, input-output unit 115, display unit
116.It will appreciated by the skilled person that structure shown in FIG. 1 is only to illustrate, not to the knot of electric terminal 100
It is configured to limit.For example, electric terminal 100 may also include the more perhaps less component than shown in Fig. 1 or have and figure
Different configuration shown in 1.
In the present embodiment, the electric terminal 100 can be television set etc. and show equipment.
The memory 111, storage control 112, processor 113, Peripheral Interface 114, input-output unit 115 and aobvious
Show that each element of unit 116 is directly or indirectly electrically connected between each other, to realize the transmission or interaction of data.For example, these
Element can be realized by one or more communication bus or signal wire be electrically connected between each other.Described disobey stops monitoring device 110
The electricity can be stored in the memory 111 or is solidificated in including at least one in the form of software or firmware (Firmware)
Software function module in the operating system (Operating System, OS) of sub- terminal 100.The processor 113 is for holding
The executable module stored in line storage, such as described disobey stop the software function module or computer that monitoring device 110 includes
Program.
Wherein, the memory 111 may be, but not limited to, random access memory (Random Access
Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable
Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only
Memory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only
Memory, EEPROM) etc..Wherein, memory 111 is for storing program, the processor 113 after receiving and executing instruction,
Described program is executed, method performed by the electric terminal 100 that the process that any embodiment of the embodiment of the present invention discloses defines can
To be applied in processor 113, or realized by processor 113.
The processor 113 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor
113 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processes
Device (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (DSP), specific integrated circuit
(ASIC), field programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor can be microprocessor or the processor is also possible to any conventional processor etc..
Various input/output devices are couple processor 113 and memory 111 by the Peripheral Interface 114.Some
In embodiment, Peripheral Interface 114, processor 113 and storage control 112 can be realized in one single chip.Other one
In a little examples, they can be realized by independent chip respectively.
The input-output unit 115 is for being supplied to user input data.The input-output unit 115 can be,
But it is not limited to, mouse and keyboard etc..
The display unit 116 provided between the electric terminal 100 and user an interactive interface (such as user behaviour
Make interface) or for display image data give user reference.In the present embodiment, the display unit can be liquid crystal display
Or touch control display.It can be the capacitance type touch control screen or resistance of support single-point and multi-point touch operation if touch control display
Formula touch screen etc..Single-point and multi-point touch operation is supported to refer to that touch control display can sense on the touch control display one
Or the touch control operation generated simultaneously at multiple positions, and the touch control operation that this is sensed transfers to processor to be calculated and located
Reason.
Further, in this embodiment electric terminal 100 can be used for executing each step in following embodiment of the method.
Referring to Fig. 2, being that electric terminal shown in FIG. 1 separated provided in an embodiment of the present invention that be applied to stops monitoring method
Flow chart.Detailed process shown in Fig. 2 will be described in detail below.
Step S101 obtains the road image data in monitoring region.
In the present embodiment, the road image can be the image collected by unmanned plane.The unmanned plane can incite somebody to action
It is whole that the road image data in the monitoring region collected are sent to the electronics in real time or according to the time rule of setting
End.Certainly, other acquisition equipment acquisitions can be used in the road image data, and it is, for example, possible to use video cameras, monitoring camera
The equipment that head, mobile phone etc. can be realized image data acquiring.
Further, the road image data are also possible to acquire and be stored in the memory of the electric terminal in advance
In or specified database in, can be from the memory or database when needing to handle the road image data
Obtain data.
The road image data are carried out match cognization, to identify in the road image data by step S102
Occupy-street-exploit area image.
In the present embodiment, occupy-street-exploit area image can indicate the road that may be easy the section of car owner's illegal parking
Image.For example, the section of easy car owner's illegal parking can be restaurant doorway, hidden path region etc..
Step S103 extracts the monitoring feature vector in occupy-street-exploit area image.
In the present embodiment, it is described obtain monitoring region in road image data the step of before, as shown in figure 3, described
Method further includes：Step S201 receives the selection operation to monitoring region, to select the characteristic indication in occupy-street-exploit area.
The step S103 could alternatively be step S202, search the characteristic indication image in the road image data,
Go out the major trunk roads in the road image data according to the characteristic indication images match, is cut further according to the position of the major trunk roads
Take occupy-street-exploit area image.
In one embodiment, Scale invariant features transform (Scale-invariant feature can be used
Transform, referred to as：SIFT) method finds out the characteristic indication image in major trunk roads, to position to major trunk roads.Into one
Step ground, by the relative position in occupy-street-exploit area and major trunk roads, the position in the available occupy-street-exploit area, further,
The occupy-street-exploit area image described in the road image data cutout.In the present embodiment, the occupy-street-exploit area can be just
It is major trunk roads.
Step S104 compares the monitoring feature vector and preparatory standard feature vector to obtain the monitoring spy
Levy the similarity of vector and the standard feature vector.
In the present embodiment, monitoring feature vector image corresponding with preparatory standard feature vector is to same position
It sets, same shooting angle obtains shooting image.Wherein, the corresponding image of the standard feature vector is (not deposit under normal condition
In the case where illegal parking) shooting image.The corresponding image of the monitoring feature vector is to shoot in monitoring time section
Image.
In the present embodiment, the spy that is extracted in the image data when standard feature vector can be by normal road state
Levy vector.
Further, the angle of standard feature vector image corresponding with the monitoring feature vector is identical.
For example, standard feature vector image corresponding with the monitoring feature vector may each be same position and direction with
What ground was shot in 45 degree of angles.
Further, standard feature vector image corresponding with the monitoring feature vector, corresponding shooting figure
The model of the acquisition equipment of picture is identical.
What the data that the shooting by comparing equal angular obtains judged incorrectly caused by can reducing because angle is different
Situation.
Step S105 obtains the monitoring result of the road monitoring in the monitoring region according to the similarity.
In the present embodiment, the step S105, including：Judge whether the similarity is less than preset threshold, when the phase
When being less than preset threshold like degree, determine that there are illegal parkings on the corresponding road of the road image data.
The preset threshold can be arranged as desired, for example, the preset threshold can be the numerical value such as 90%, 80%.
It, can rule of thumb preset threshold described in standard setting it is appreciated that those skilled in the art is when need to use.
The separated of the embodiment of the present invention stops monitoring method, by handling the road image data of the detection zone of acquisition
Monitoring feature vector is obtained, monitoring feature vector standard feature vector corresponding with there is no the road image in stopping time is disobeyed is carried out
Similarity is judged, to obtain the monitoring result monitored to road, it is no longer necessary to which manual identified road can be improved and supervise to road
The efficiency of survey saves human resources.
Further, after the step of there are illegal parkings on the corresponding road of the determination road image data,
The method also includes：Issue warning note message.For example, alarm voice message can be issued.For example, " the currently monitored road
There are illegal parkings for section ".For another example can show text prompt message on the display interface of electric terminal.In another example described
Electric terminal can send warning message to specified account, and the content of the warning message may include the position that illegal parking occurs
It sets, the license plate number of illegal parking etc..
Further, after the step of there are illegal parkings on the corresponding road of the determination road image data,
The method also includes：It is judged as the abnormal mark of position setting of illegal parking in the road image data.The exception
Mark can be label character, be also possible to color mark, can also be wire frame mark etc..
In the present embodiment, the step S103 includes：Extract Gabor characteristic, the part two of occupy-street-exploit area image
Multilevel mode feature, any one of HOG feature or any combination are as monitoring feature vector.
The extracting mode of three kinds of features is described in detail separately below.
Wherein, Gabor transformation belongs to windowed FFT, and Gabor function can be in frequency domain different scale, different directions
It is upper to extract relevant feature.
Gabor wavelet and the visual stimulus response of simple cell in human visual system are closely similar.It is extracting target
Local space and frequency-domain information in terms of have good characteristic.Although Gabor wavelet itself can not constitute orthogonal basis,
It may make up tight frame under special parameter.Gabor wavelet for the edge sensitive of image, be capable of providing good direction selection and
Scale selection characteristic, and it is insensitive for illumination variation, it is capable of providing to the good adaptability of illumination variation.
Compared with traditional Fourier transform, Gabor wavelet transformation has good Time-Frequency Localization characteristic.Hold very much
The direction for adjusting Gabor filter, fundamental frequency bandwidth and the centre frequency of changing places so as to it is best take into account signal in time-space domain and
Resolution capability in frequency domain；Gabor wavelet transformation has multi-resolution characteristics, that is, zoom capabilities.Use multi-channel filter skill
Art converts one group of Gabor wavelet with different time-frequency domain characteristics applied to image, and each channel can access input figure
Certain local characteristics of picture, can according to need analyze image in different thicknesses granularity in this way.In addition, in feature extraction side
Face, Gabor wavelet convert compared with other methods：On the one hand the data volume of its processing is less, and the real-time for being able to satisfy system is wanted
It asks；On the other hand, wavelet transformation is insensitive to illumination variation, and can tolerate a degree of image rotation and deformation, works as use
When being identified based on Euclidean distance, feature mode and feature to be measured do not need stringent corresponding, therefore can improve feature identification
Robustness.
Under type realization can be passed to by extracting Gabor characteristic by Gabor function：
Real number form first is carried out to the occupy-street-exploit area image I (x, y) for needing to extract feature in road image data
Gabor transformation, the image that obtains that treated.
For example, it is desired to which the occupy-street-exploit area image size of processing can be 128*128, transformation can be first passed through and handled
Image afterwards, size are also 128*128.If directly extracting feature, intrinsic dimensionality is too high, is unfavorable for subsequent processing.It can be right
Image carries out piecemeal, both horizontally and vertically takes 16 equal parts respectively, whole image is divided into the subgraph of 64 16*16 sizes
Block.
Then the corresponding energy of each subimage block is calculated, wherein the corresponding energy of each piece of subimage block can indicate
For：
Wherein, e (k) indicates the energy of subimage block；A (k) indicates the energy of the pixel in subimage block；
Finally by energy matrix dimensionality reduction at the row vector of 1*64, as original image after a direction and change of scale
Feature vector.
Wherein, original LBP operator definitions are in the neighborhood of pixel 3*3, using centre of neighbourhood pixel as threshold value, adjacent 8
The gray value of a pixel is compared with the pixel value of the centre of neighbourhood, if surrounding pixel is greater than center pixel value, the pixel
Position be marked as 1, be otherwise 0.In this way, 8 points in 3*3 neighborhood can produce 8 bits by comparing, by this 8
Bit is arranged successively to form a binary digit, this binary digit is exactly the LBP value of center pixel, LBP value
2828 kinds of possibility are shared, therefore LBP value there are 256 kinds, the LBP value of center pixel reflects the texture letter of the pixel peripheral region
Breath.The monitoring feature vector of occupy-street-exploit area image can be extracted by above-mentioned processing mode.
Wherein：The image for calculating LBP feature must be grayscale image, if it is cromogram, need the occupy-street-exploit first
Area's image is converted into grayscale image.
It is characterized in histogram of gradients (Histogram of Oriented Gradient, HOG) a kind of in computer view
The Feature Descriptor felt and be used to carry out object detection in image procossing.It is by calculating the gradient with statistical picture regional area
Direction histogram carrys out constitutive characteristic.Hog feature combination SVM classifier has been widely used in image recognition, is especially expert at
Great success is obtained in people's detection.
In a sub-picture, the presentation and shape (appearance and shape) of localized target can be by gradient or sides
The direction Density Distribution of edge describes well.(essence：The statistical information of gradient, and gradient is primarily present in the place at edge).
Under type realization can be passed to by extracting HOG feature：
Firstly, occupy-street-exploit area image is divided into small connected region, we are cell factory it.Then it acquires
In cell factory the gradient of each pixel or edge direction histogram.It finally altogether can structure these set of histograms
At profiler.
Further, these local histograms in the bigger range of image (we are section or block it)
Degree of comparing normalizes (contrast-normalized), and used method is：Each histogram is first calculated in this section
(block) then the density in normalizes each cell factory in section according to this density.It is normalized by this
Afterwards, better effect can be obtained to illumination variation and shade.
Compared with other character description methods, HOG has many good qualities.Firstly, since HOG is the local grid in image
It is operated on unit, so it can keep good invariance to image geometry and optical deformation, both deformation only can
It appears on bigger space field.Secondly, returning in thick airspace sampling, fine direction sampling and stronger indicative of local optical
Under the conditions of one change etc., as long as pedestrian is generally able to maintain erect posture, pedestrian can be allowed there are some subtle limbs dynamic
Make, these subtle movements can be ignored without influencing detection effect.Therefore HOG feature is particularly suitable for doing in image
Human testing.
HOG feature extracting method exactly performs the following operation occupy-street-exploit area image：
1) gray processing (regarding image as an x, the 3-D image of y, z (gray scale))；
2) standardization (normalization) of color space is carried out to input picture using Gamma correction method；Purpose is adjusting figure
The contrast of picture, reduce image local shade and illumination variation caused by influence, while the interference of noise can be inhibited；
3) gradient (including size and Orientation) of each pixel of image is calculated；Primarily to capture profile information, simultaneously
The interference that further weakened light shines；
4) small cells (such as 6*6 pixel/cell) is divided an image into；
5) histogram of gradients (numbers of different gradients) for counting each cell, can form each cell's
descriptor；
6) block (such as 3*3 cell/block), all cell in a block will be formed per several cell
Feature descriptor be together in series and just obtain the HOG feature descriptor of the block.
7) the HOG feature descriptor of all block in image image is together in series can be obtained by this
The HOG feature descriptor of image (your target to be detected).
In the present embodiment, the step S104 includes：By the monitoring feature vector of each type and corresponding standard feature
Vector is compared to obtain respectively the sub- similarity under the feature vector of each type；By the sub- phase under each type feature vector
It is combined to form the similarity like degree.
In detail, can by monitoring feature vector Gabor characteristic and the standard feature vector Gabor characteristic into
Row comparison obtains sub- similarity；Can by monitoring feature vector LBP feature and the standard feature vector LBP feature into
Row comparison obtains sub- similarity；The HOG feature of HOG feature and the standard feature vector in monitoring feature vector is carried out pair
Than obtaining sub- similarity.
The similarity is obtained it is possible to further calculate the sum of each sub- similarity；It can also be according to preset each
Sub- similarity proportion is to be calculated the similarity.For example, sub- similarity A and sub- similarity B is calculated, then it is described
Similarity may be calculated 50% (A+B)；Similarity also may be calculated 30%A+70%B.
The recognition accuracy that monitoring can be improved and obtain is compared respectively by extracting a plurality of types of feature vectors.
In the present embodiment, before step S104, the method also includes following steps.
Step S301 is obtained and the standard road image data under the road normal condition in the monitoring region.
Step S302 extracts the standard feature vector in the standard road image data.
In the present embodiment, step S302 can be the image in occupy-street-exploit area in the standard road image data of extraction
Standard feature vector.Therefore, it may also include before executing step S302 from standard road image data and intercept occupy-street-exploit
The image in area.
In the present embodiment, Scale invariant features transform (Scale-invariant feature also can be used
Transform, referred to as：SIFT) method finds out the characteristic indication image in the major trunk roads in the standard road image data, from
And major trunk roads are positioned.Further, pass through the relative position in occupy-street-exploit area and major trunk roads, the available road occupying
The position of operating area, it is possible to further the occupy-street-exploit area image described in the road image data cutout.The present embodiment
In, the occupy-street-exploit area can be exactly major trunk roads.
In the present embodiment, the extraction of the standard feature vector can be with the extracting mode phase of the monitoring feature vector
Together, specifically can be with reference to about the implementation for extracting monitoring feature vector, details are not described herein.
In the present embodiment, the standard road image data and the road image data are the acquisition equipment of same model
The image data of acquisition.
Referring to Fig. 5, being the separated functional module signal for stopping monitoring device 110 shown in FIG. 1 provided in an embodiment of the present invention
Figure.Separated monitoring device 110 of stopping in the present embodiment is for executing each step in above method embodiment.Described disobey stops monitoring
Device 110 includes：It obtains module 1101, identification module 1102, extraction module 1103, contrast module 1104 and obtains module
1105。
The acquisition module 1101, for obtaining the road image data in monitoring region.
The identification module 1102, for the road image data to be carried out match cognization, to identify the road
Occupy-street-exploit area image in image data.
The extraction module 1103, for extracting the monitoring feature vector in occupy-street-exploit area image.
The contrast module 1104, for comparing the monitoring feature vector and preparatory standard feature vector
To the similarity of the monitoring feature vector and the standard feature vector.
It is described to obtain module 1105, the monitoring knot of the road monitoring for obtaining the monitoring region according to the similarity
Fruit.
In the present embodiment, the module 1105 that obtains is also used to judge whether the similarity is less than preset threshold, works as institute
When stating similarity less than preset threshold, determine that there are illegal parkings on the corresponding road of the road image data.
In the present embodiment, described disobey stops monitoring device 110 and further includes：Alarm module, for issuing warning note message.
In the present embodiment, described disobey stops monitoring device 110 and further includes：Labeling module, in the road image data
In be judged as the abnormal mark of position setting of illegal parking.
In the present embodiment, the extraction module 1103 is also used to extract the Gabor characteristic of occupy-street-exploit area image, office
Portion's binary mode characteristic, any one of HOG feature or any combination are as monitoring feature vector.
In the present embodiment, the contrast module 1104 is also used to the monitoring feature vector of each type and corresponding standard
Feature vector is compared to obtain respectively the sub- similarity under the feature vector of each type, will be under each type feature vector
Sub- similarity is combined to form the similarity.
In the present embodiment, described disobey stops monitoring device 110 and further includes：Receiving module, for receiving the choosing to monitoring region
Operation is selected, to select the characteristic indication in occupy-street-exploit area.
In the present embodiment, the identification module 1102 is also used to search the characteristic indication figure in the road image data
Picture goes out the major trunk roads in the road image data according to the characteristic indication images match, further according to the position of the major trunk roads
Set interception occupy-street-exploit area image.
In the present embodiment, described disobey stops monitoring device 110 and includes：Standard extraction module, for obtaining and the monitoring section
Standard road image data under the road normal condition in domain, extract standard feature in the standard road image data to
Amount.
In the present embodiment, the standard road image data and the road image data are the acquisition equipment of same model
The image data of acquisition.
Other details about the present embodiment can be further with reference to the description in above method embodiment, herein no longer
It repeats.
The separated of the embodiment of the present invention stops monitoring device, by handling the road image data of the detection zone of acquisition
Monitoring feature vector is obtained, monitoring feature vector standard feature vector corresponding with there is no the road image in stopping time is disobeyed is carried out
Similarity is judged, to obtain the monitoring result monitored to road, it is no longer necessary to which manual identified road can be improved and supervise to road
The efficiency of survey saves human resources.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should be noted that：Similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (10)
1. one kind, which is disobeyed, stops monitoring method, which is characterized in that including：
Obtain the road image data in monitoring region；
The road image data are subjected to match cognization, to identify the occupy-street-exploit area figure in the road image data
Picture；
Extract the monitoring feature vector in occupy-street-exploit area image；
By the monitoring feature vector and preparatory standard feature vector compare to obtain the monitoring feature vector with it is described
The similarity of standard feature vector；And
The monitoring result of the road monitoring in the monitoring region is obtained according to the similarity.
2. as described in claim 1 disobey stops monitoring method, which is characterized in that described to obtain the monitoring according to the similarity
The step of monitoring result of the road monitoring in region, including：
Judge whether the similarity is less than preset threshold；
When the similarity is less than preset threshold, determine that there are illegal parkings on the corresponding road of the road image data.
3. as claimed in claim 2 disobey stops monitoring method, which is characterized in that the determination road image data are corresponding
After the step of there are illegal parkings on road, the method also includes：
Issue warning note message；And/or
It is judged as the abnormal mark of position setting of illegal parking in the road image data.
4. as claimed in any one of claims 1-3 disobey stops monitoring method, which is characterized in that described to extract the occupy-street-exploit
The step of monitoring feature vector in area's image, including：
Extract the Gabor characteristic of occupy-street-exploit area image, partial binary mode characteristic, HOG feature any one or
Any combination is as monitoring feature vector.
5. as claimed in claim 4 disobey stops monitoring method, which is characterized in that it is described by the monitoring feature vector with obtain in advance
The standard feature vector taken compares to obtain the monitoring feature vector the step of similarity with the standard feature vector,
Including：
The monitoring feature vector of each type is compared to obtain the spy of each type respectively with corresponding standard feature vector
Levy the sub- similarity under vector；
It is combined the sub- similarity under each type feature vector to form the similarity.
6. as claimed in claim 1 or 2 disobey stops monitoring method, which is characterized in that the mileage chart obtained in monitoring region
Before as the step of data, the method also includes：
The selection operation to monitoring region is received, to select the characteristic indication in occupy-street-exploit area；
It is described that the road image data are subjected to match cognization, to identify the occupy-street-exploit area in the road image data
The step of image includes：The characteristic indication image in the road image data is searched, according to the characteristic indication images match
Major trunk roads in the road image data out intercept occupy-street-exploit area image further according to the position of the major trunk roads.
7. as claimed in claim 1 or 2 disobey stops monitoring method, which is characterized in that it is described by the monitoring feature vector with
The standard feature vector obtained in advance compares to obtain the similarity of the monitoring feature vector Yu the standard feature vector
The step of before, the method also includes：
It obtains and the standard road image data under the road normal condition in the monitoring region；
Extract the standard feature vector in the standard road image data.
8. as claimed in claim 7 disobey stops monitoring method, which is characterized in that the standard road image data and the road
Image data is the image data of the acquisition equipment acquisition of same model.
9. one kind, which is disobeyed, stops monitoring device, which is characterized in that including：
Module is obtained, for obtaining the road image data in monitoring region；
Identification module, for the road image data to be carried out match cognization, to identify in the road image data
Occupy-street-exploit area image；
Extraction module, for extracting the monitoring feature vector in occupy-street-exploit area image；
Contrast module obtains the monitoring spy for comparing the monitoring feature vector and preparatory standard feature vector
Levy the similarity of vector and the standard feature vector；
Module is obtained, the monitoring result of the road monitoring for obtaining the monitoring region according to the similarity.
10. a kind of electric terminal, including memory, processor and it is stored on the memory and can transports on the processor
Capable computer program, which is characterized in that the processor realizes the claims 1 to 8 when executing the computer program
Any one of described in method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946422.6A CN108831158A (en) | 2018-08-20 | 2018-08-20 | It disobeys and stops monitoring method, device and electric terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946422.6A CN108831158A (en) | 2018-08-20 | 2018-08-20 | It disobeys and stops monitoring method, device and electric terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108831158A true CN108831158A (en) | 2018-11-16 |
Family
ID=64150364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810946422.6A Pending CN108831158A (en) | 2018-08-20 | 2018-08-20 | It disobeys and stops monitoring method, device and electric terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108831158A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635762A (en) * | 2018-12-18 | 2019-04-16 | 正元地理信息有限责任公司 | A kind of city management method, system and device |
| CN109918291A (en) * | 2019-01-17 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Software interface detection method, device, computer equipment and storage medium |
| CN113593250A (en) * | 2021-07-12 | 2021-11-02 | 浙江工贸职业技术学院 | Illegal parking detection system based on visual identification |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080068959A (en) * | 2007-01-22 | 2008-07-25 | 뷰웨이 주식회사 | Robust face recognition using aam and gabor feature vectors |
| CN102034212A (en) * | 2010-06-21 | 2011-04-27 | 艾浩军 | City management system based on video analysis |
| CN103021183A (en) * | 2012-12-07 | 2013-04-03 | 北京中邮致鼎科技有限公司 | Method for detecting regulation-violating motor vehicles in monitoring scene |
| CN103207910A (en) * | 2013-04-08 | 2013-07-17 | 河南大学 | Image retrieval method based on hierarchical features and genetic programming relevance feedback |
| CN103313018A (en) * | 2012-03-15 | 2013-09-18 | 欧姆龙株式会社 | Registration determination device, control method thereof, and electronic apparatus |
| CN103325259A (en) * | 2013-07-09 | 2013-09-25 | 西安电子科技大学 | Illegal parking detection method based on multi-core synchronization |
| CN104407351A (en) * | 2014-12-05 | 2015-03-11 | 北京公科飞达交通工程发展有限公司 | Vehicle window position identification method |
| CN105354405A (en) * | 2014-08-20 | 2016-02-24 | 中国科学院上海高等研究院 | Machine learning based immunohistochemical image automatic interpretation system |
| CN105427606A (en) * | 2015-12-24 | 2016-03-23 | 重庆云途交通科技有限公司 | Pavement condition information acquisition and release method |
-
2018
- 2018-08-20 CN CN201810946422.6A patent/CN108831158A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080068959A (en) * | 2007-01-22 | 2008-07-25 | 뷰웨이 주식회사 | Robust face recognition using aam and gabor feature vectors |
| CN102034212A (en) * | 2010-06-21 | 2011-04-27 | 艾浩军 | City management system based on video analysis |
| CN103313018A (en) * | 2012-03-15 | 2013-09-18 | 欧姆龙株式会社 | Registration determination device, control method thereof, and electronic apparatus |
| CN103021183A (en) * | 2012-12-07 | 2013-04-03 | 北京中邮致鼎科技有限公司 | Method for detecting regulation-violating motor vehicles in monitoring scene |
| CN103207910A (en) * | 2013-04-08 | 2013-07-17 | 河南大学 | Image retrieval method based on hierarchical features and genetic programming relevance feedback |
| CN103325259A (en) * | 2013-07-09 | 2013-09-25 | 西安电子科技大学 | Illegal parking detection method based on multi-core synchronization |
| CN105354405A (en) * | 2014-08-20 | 2016-02-24 | 中国科学院上海高等研究院 | Machine learning based immunohistochemical image automatic interpretation system |
| CN104407351A (en) * | 2014-12-05 | 2015-03-11 | 北京公科飞达交通工程发展有限公司 | Vehicle window position identification method |
| CN105427606A (en) * | 2015-12-24 | 2016-03-23 | 重庆云途交通科技有限公司 | Pavement condition information acquisition and release method |
Non-Patent Citations (2)
| Title |
|---|
| 姜慧伟: "利用多特征融合的面相对象的高分辨率遥感影像变化检测", 《陕西理工学院学报（自然科学版）》 * |
| 郑耀: "违章停车取证关键技术研究", 《中国游戏硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635762A (en) * | 2018-12-18 | 2019-04-16 | 正元地理信息有限责任公司 | A kind of city management method, system and device |
| CN109918291A (en) * | 2019-01-17 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Software interface detection method, device, computer equipment and storage medium |
| CN113593250A (en) * | 2021-07-12 | 2021-11-02 | 浙江工贸职业技术学院 | Illegal parking detection system based on visual identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740478B (en) | Vehicle detection and identification method, device, computer equipment and readable storage medium | |
| US20210065384A1 (en) | Target tracking method, device, system and non-transitory computer readable storage medium | |
| Zhou et al. | Principal visual word discovery for automatic license plate detection | |
| CN111797653B (en) | Image labeling method and device based on high-dimensional image | |
| US8792722B2 (en) | Hand gesture detection | |
| US8750573B2 (en) | Hand gesture detection | |
| CN104517104B (en) | A kind of face identification method and system based under monitoring scene | |
| Marciniak et al. | Influence of low resolution of images on reliability of face detection and recognition | |
| CN105335722A (en) | Detection system and detection method based on depth image information | |
| CN101980242B (en) | Human face discrimination method and system and public safety system | |
| US10445602B2 (en) | Apparatus and method for recognizing traffic signs | |
| US20130170711A1 (en) | Edge detection image capture and recognition system | |
| Sikandar et al. | ATM crime detection using image processing integrated video surveillance: a systematic review | |
| CN103530648A (en) | Face recognition method based on multi-frame images | |
| CN109145812A (en) | Squatter building monitoring method and device | |
| CN111144366A (en) | Strange face clustering method based on joint face quality assessment | |
| WO2018210047A1 (en) | Data processing method, data processing apparatus, electronic device and storage medium | |
| Tao et al. | Smoke vehicle detection based on multi-feature fusion and hidden Markov model | |
| CN108831158A (en) | It disobeys and stops monitoring method, device and electric terminal | |
| US20170213074A1 (en) | Decoy-based matching system for facial recognition | |
| CN111353491A (en) | Character direction determining method, device, equipment and storage medium | |
| CN112052731A (en) | Intelligent portrait recognition card punching attendance system and method | |
| CN115841651B (en) | Constructor intelligent monitoring system based on computer vision and deep learning | |
| CN110222660B (en) | Signature authentication method and system based on dynamic and static feature fusion | |
| CN108960246B (en) | Binarization processing device and method for image recognition |
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 |
Application publication date: 20181116 |
|
| RJ01 | Rejection of invention patent application after publication |