CN109145862A - A kind of super anti-theft monitoring system of quotient - Google Patents
A kind of super anti-theft monitoring system of quotient Download PDFInfo
- Publication number
- CN109145862A CN109145862A CN201811031988.2A CN201811031988A CN109145862A CN 109145862 A CN109145862 A CN 109145862A CN 201811031988 A CN201811031988 A CN 201811031988A CN 109145862 A CN109145862 A CN 109145862A
- Authority
- CN
- China
- Prior art keywords
- pixel
- face
- facial image
- feature vector
- gray
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19645—Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Abstract
The invention discloses a kind of super anti-theft monitoring systems of quotient, the system includes being respectively arranged at each point to be monitored, facial image candid photograph and real-time video capture are carried out for treating monitoring point crowd, and by image and vision signal real-time Transmission to processor video camera, be used to carry out processing identification to the facial image signal that camera transmissions come, judge face processor whether corresponding with the face in processor black list database and display terminal in image.The super anti-theft monitoring system of quotient of the invention is by entering and leaving bayonet, key area intelligent camera in key, the face head portrait for carrying out discrepancy crowd is captured, by carrying out recognition of face to the image of candid photograph, obtain face characteristic data, it is compared with the human face data of the thief imported in black list database, thief can be quickly and effectively screened, timely and effective prevention and the pilferage behavior of prevention thief occur.
Description
Technical field
The present invention relates to supermarket's field of intelligent monitoring, and in particular to a kind of super anti-theft monitoring system of quotient.
Background technique
As urban life rhythm gradually becomes faster, large supermarket multiple functional, that the source of goods is complete has gradually replaced traditional
Department stores become the major consumers place of urban human fast pace life.Large supermarket has considerable scale, carries out nobody and sells
Goods provides free good environment for customer.But it is creating the complete purchase of comfortable light, safety clean, the source of goods for customer
While substance environment, and the problem of bring a headache to businessman --- merchandise theft exists with fashion chain store and free supermarket
Domestic is increasingly prevailing, and commodity Loss is also on the rise, and how to prevent commodity stolen, and protection market safety is by more next
The concern of more retailers.Enterprise takes a large amount of time and manpower and money and goes tracking pilferage situation similar with prevention
Occur.
In the super antitheft link of quotient, the prevention of habitual offender, confirmed thief seem even more important.In traditional supermarket's monitoring, generally
It is guard using the shortcomings that bayonet, important area install camera, and monitoring room artificially stares at the mode kept, this mode
It is difficult effectively to screen thief, is stolen along with quotient is extra small and often flee about to commit crimes, be good at pretending, caregiver is more helpless.Quotient
Super monitoring field is badly in need of a kind of intelligent anti-theft monitoring system, avoids property loss.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of super anti-theft monitoring system of quotient, pass through people to solve traditional monitor mode
Member guard can not effectively screen commodity loss, property loss problem caused by thief.
The purpose of the present invention is realized using following technical scheme:
A kind of super anti-theft monitoring system of quotient, the anti-theft monitoring system include video camera, processor and display terminal, described to take the photograph
Camera carries out facial image candid photograph and real-time video capture for being arranged at each point to be monitored, to treat monitoring point crowd, and
Give facial image and vision signal real-time Transmission to the processor；The processor is for passing through the face to camera transmissions
Image carries out processing identification, judges whether the face in facial image is corresponding with the face in processor black list database, such as
Fruit is corresponding, then determines that the face is to identify target, its corresponding identity information is transferred to display terminal；The display terminal
For being arranged at monitoring backstage, the identity information for the identification target that the processor is sent is received, and carry out real-time display.
The utility model has the advantages that (1) the present invention is based on the super anti-theft monitoring systems of the quotient of recognition of face by entering and leaving bayonet, again in key
Video camera is installed in point region, and the face head portrait for carrying out discrepancy crowd is captured, and by carrying out recognition of face to the image of candid photograph, is obtained
Face characteristic data are compared with the human face data of the thief imported in black list database, can quickly and effectively screen small
Steathily, timely and effective prevention and the pilferage behavior of prevention thief occur.The system improves small compared with traditional supermarket's monitor mode
The efficiency and accuracy identified steathily, realizes that quotient is super and the intelligence of other commercial buildings is antitheft, to the intelligence of a suspect
Recognition of face greatly improves commercial space anti-theft horizontal and efficiency.
(2) increase the generation function of warning message in processor, and warning message is exported to display terminal and shown
Alarm is popped up on interface, can more rapidly be found thief's information that monitoring information identifies, be played the role of fright to thief.
(3) video information number that processor can also simultaneously carry out all camera transmissions is analyzed, and obtains signal mesh
Target real time position and mobile trajectory data are realized automatically tracking for track, and are exported to display terminal, after identifying thief
In the video pictures and action trail figure of display terminal real-time display thief, efficiency is further improved.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structure chart of the super anti-theft monitoring system of quotient of the present invention；
Fig. 2 is the frame construction drawing of processor；
Fig. 3 is the frame construction drawing of human face analysis module 4.
Appended drawing reference: video camera 1；Processor 2；Display terminal 3；Human face analysis module 4；Face characteristic contrast module 5；It is black
List data library 6；Alarm module 7；Video analysis tracing module 8；Facial image pre-processes submodule 9；Facial image feature mentions
Take submodule 10；Gray processing unit 11；Denoise unit 12；Enhancement unit 13.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of super anti-theft monitoring system of quotient, the anti-theft monitoring system includes camera shooting, and 1, processor 2 and display are eventually
End 3, the video camera 1 for be arranged at each point to be monitored, with treat monitoring point crowd carry out facial image candid photograph and in real time
Video capture, and give facial image and vision signal real-time Transmission to the processor 2；The processor 2 is used for by taking the photograph
The facial image that camera 1 transmits carries out processing identification, judge face in facial image whether with 2 black list database of processor
In face it is corresponding, if it does correspond, then determining that the face is to identify target, its corresponding identity information is transferred to display eventually
End 3；The display terminal 3 receives the identity letter for the identification target that the processor 2 is sent for being arranged at monitoring backstage
Breath, and carry out real-time display.
The utility model has the advantages that (1) the present invention is based on the super anti-theft monitoring systems of the quotient of recognition of face by entering and leaving bayonet, again in key
Video camera is installed in point region, and the face head portrait for carrying out discrepancy crowd is captured, and by carrying out recognition of face to the image of candid photograph, is obtained
Face characteristic data are compared with the human face data of the thief imported in black list database, can quickly and effectively screen small
Steathily, timely and effective prevention and the pilferage behavior of prevention thief occur.The system improves small compared with traditional supermarket's monitor mode
The efficiency and accuracy identified steathily, realizes that quotient is super and the intelligence of other commercial buildings is antitheft, to the intelligence of a suspect
Recognition of face greatly improves commercial space anti-theft horizontal and efficiency.
(2) increase the generation function of warning message in processor, and warning message is exported to display terminal and shown
Alarm is popped up on interface, can more rapidly be found thief's information that monitoring information identifies, be played the role of fright to thief.
(3) video information number that processor can also simultaneously carry out all camera transmissions is analyzed, and obtains signal mesh
Target real time position and mobile trajectory data are realized automatically tracking for track, and are exported to display terminal, after identifying thief
In the video pictures and action trail figure of display terminal real-time display thief, efficiency is further improved.
Preferably, referring to fig. 2, the processor includes human face analysis module 4, face characteristic contrast module 5, blacklist number
According to library 6, alarm module 7 and video analysis tracing module 8；
The human face analysis module 4, is analyzed for the facial image to camera transmissions, obtains the facial image
Face feature vector；
The black list database 6, for storing the face feature vector of stealing personnel；
The face characteristic contrast module 5, for obtained face feature vector and the black list database 6 will to be extracted
In the face feature vector that prestores be compared, judge the face whether with the face pair that is prestored in the black list database 6
It answers, if it does correspond, then determining that the face is to identify target, and its corresponding identity information is transferred to display terminal；
The alarm module 7 for generating warning message after obtaining the identification target, and is exported to display terminal 3；
The video analysis tracking module 8, the vision signal for coming to all camera transmissions are analyzed, and are obtained and are known
The real time position and mobile trajectory data of other target, and export to display terminal.
Preferably, referring to Fig. 3, the human face analysis module 4 includes that facial image pretreatment submodule 9 and facial image are special
Levy extracting sub-module 10.The facial image pre-processes submodule 9, and the facial image for transmitting to video camera 1 is located in advance
Reason；The facial image feature extraction submodule 10, for being extracted in the facial image from pretreated facial image
Face feature vector.
Preferably, the facial image pretreatment submodule 9 includes gray processing unit 11, denoising unit 12 and enhancement unit
13；
The gray processing unit 11, the facial image for transmitting to video camera 1 carry out gray processing processing；The denoising is single
Member 12, for removing the random noise in the facial image after gray processing；The enhancement unit 12, for the face after denoising
Image carries out enhancing processing.
Preferably, the random noise in the facial image after the removal gray processing, specifically:
(1) centered on pixel A (x, y), the rectangular window that a size is (2M+1,2M+1) is chosen, institute is calculated separately
Gray scale absolute difference in facial image after stating gray processing in pixel B (x, y) and rectangular window between residual pixel point,
In, the gray scale absolute difference between pixel A (x, y) and pixel B (m, n) can be calculated using following formula:
In formula, DABIt is the gray scale absolute difference between pixel A and pixel B,For pixel A
With the Gauss weighted euclidean distance of pixel B, α is the standard deviation of Gaussian function, and h is the smoothing parameter of setting, and x, y are respectively picture
The abscissa and ordinate of vegetarian refreshments A, m, n are respectively the abscissa and ordinate of pixel B, and g (A) is the gray value of pixel A,
G (B) is the gray value of pixel B, and Θ is the set that the residual pixel point in rectangular window not comprising pixel B is constituted；
(2) the gray scale absolute difference in obtained pixel A (x, y) and rectangular window between residual pixel point is risen
Sequence arrangement, obtains the set of ascending order arrangementWherein, hkFor gray scale absolute difference
In k-th the smallest element, a new absolute difference order is determined according to set H:
In formula, Q is the positive integer being manually set, and value range is: 2≤Q≤(2M+1)2- 1, Sq (A) are about pixel
The new absolute difference order of point A；
(3) according to obtained new absolute difference order, the contribution degree of pixel A is calculated:
In formula, λ1、λ2It is grand for preset threshold value length, and meet λ1> λ2, T (A) is the contribution degree of pixel A, the contribution degree
For measuring the degree that the pixel belongs to noise spot, η is the exponential factor of setting, meets 2≤η≤4, as T (A)=0,
Showing pixel A certainly is noise pixel point, and as T (A)=1, showing pixel A not is noise pixel point；
(4) according to the contribution degree of pixel A, the denoising estimated value of pixel A is calculated using following formula,
In formula,For the denoising estimated value of pixel A,For centered on pixel A, size is (2M+1,2M
+ 1) average gray value of all pixels point in rectangular window, g (A) are the gray value of pixel A；
All pixels point in facial image after traversing gray processing, and estimated with the denoising for each pixel being calculated
The gray value of value replacement respective pixel point, the set that replaced all pixels point is constituted are the facial image after denoising.
The utility model has the advantages that measuring each pixel in the facial image after gray processing by customized contribution degree calculation formula
Contribution degree, and then measure size a possibility that each pixel belongs to noise spot, realize and estimated value is denoised to each pixel
Calculating, the gray value of each pixel, the algorithm not only allow for pixel p and its in the facial image after obtaining gray processing
The influence of Gauss weighted euclidean distance in rectangular window between residual pixel point, it is also contemplated that pixel p and its rectangular window
The influence of space length between interior residual pixel point, and then realize that whether there is or not the accurate inspections by noise pollution to pixel D
It surveys, completes to improve denoising effect to the accurate estimation of the denoising estimated value of each pixel.
Preferably, the facial image after described pair of denoising carries out enhancing processing, specifically:
(1) facial image after denoising is transformed from a spatial domain into fuzzy field using customized subordinating degree function, wherein
Customized subordinating degree function are as follows:
In formula, eijIt is subordinate to angle value, G for the pixel that coordinate in the facial image after denoising is (i, j)minAfter denoising
Facial image minimum gradation value, GmaxFor the maximum gradation value of the facial image after denoising, GijFor the facial image after denoising
Middle coordinate is the gray value of the pixel of (i, j), and θ, γ are the Fuzzy tuning factor, for according to people in the facial image after denoising
The minutia in face region is modified subordinating degree function；
(2) in fuzzy field to being subordinate to angle value eijIt is modified, obtains the person in servitude for the pixel that revised coordinate is (i, j)
Belong to angle value e 'ij；
(3) to obtained e 'ijInverse transformation is carried out, the facial image after denoising is transformed into spatial domain from fuzzy field, it is inverse
Transformation for mula are as follows:
In formula, G 'ijCoordinate to obtain through inverse transformation is the gray value of the pixel of (i, j)；
Traverse all pixels point in fuzzy field, all G 'ifThe set of composition is to enhance treated facial image.
The utility model has the advantages that the gray level image after denoising is changed to fuzzy field by transform of spatial domain, and to each in fuzzy field
The angle value that is subordinate to of pixel is modified, and then has achieved the purpose that image enhancement in fuzzy field, maintains the bright of image itself
Degree can also inhibit noise remaining in the facial image after denoising well.
Preferably, in fuzzy field to being subordinate to angle value eijIt is modified, obtains the pixel that revised coordinate is (i, j)
Be subordinate to angle value e 'ij, specifically:
(1) in fuzzy field, centered on pixel C (i, j), the window W that a size is N × N is chosenN(i, j),
A customized fuzzy contrast, the expression formula of fuzzy contrast on the window are as follows:
In formula, ConfFor fuzzy contrast angle value, eijIt is that pixel C (i, j) is subordinate to angle value,For neighborhood territory pixel in window
The average value for being subordinate to angle value of point, emaxFor the maximum value for being subordinate to angle value in window, eminFor the minimum value for being subordinate to angle value in window；
(2) obtained fuzzy contrast is subjected to nonlinear transformation, nonlinear transformation formula are as follows:
In formula, Con 'fFor ConfThe fuzzy contrast correction value obtained after nonlinear transformation, k1、k2For weight coefficient,
And meet k1>=0, k2>=0, k1+k2=1, v are the customized parameter regulation factor；
(3) according to obtained Con 'f, using following formula to being subordinate to angle value eijIt is modified:
In formula, e 'ijIt is subordinate to angle value, E for revised pixel C (i, j)cFor customized fuzzy membership threshold value.
The utility model has the advantages that by eijIt is modified, and then reaches and the facial image after denoising is increased in fuzzy field
Strong purpose, this algorithm determines the fuzzy contrast angle value of central pixel point in the window by selecting a window first, secondly right
Obtained fuzzy contrast angle value is modified, and is finally realized using revised fuzzy contrast angle value to being subordinate to angle value eijMore
Newly, by second-order correction algorithm, the useful information in the facial image after denoising in fuzzy field can be highlighted and further suppressed
Residual noise in image improves the visual effect of image, convenient for accurately identifying for the subsequent facial image to candid photograph, effectively discriminates
Not Chu thief identity, and then effectively prevent and prevents thief steal behavior generation.
Preferably, the face characteristic that obtained face feature vector will be extracted and prestored in the black list database
Vector is compared, and judges whether the face is corresponding with the face prestored in the black list database, if it does correspond, then determining
The face is to identify target, and its corresponding identity information is transferred to display terminal, specifically: the face for obtaining extraction
Feature vectorWith the face feature vector prestored in the black list databaseIt is compared, if metThen judge that the face is to identify target, and its corresponding identity information is transferred to display terminal, whereinFor the face feature vector of the facial image of camera transmissions,For the face characteristic that is prestored in the black list database to
Amount, δ are the customized similarity factor.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of super anti-theft monitoring system of quotient, which is characterized in that including video camera, processor and display terminal, the video camera
For being arranged at each point to be monitored, facial image candid photograph and real-time video capture are carried out to treat monitoring point crowd, and by people
Face image and vision signal real-time Transmission give the processor；The processor is for passing through the facial image to camera transmissions
Processing identification is carried out, judges whether the face in facial image is corresponding with the face in processor black list database, if right
It answers, then determines that the face is to identify target, its corresponding identity information is transferred to display terminal；The display terminal is used for
Setting receives the identity information for the identification target that the processor is sent at monitoring backstage, and carries out real-time display.
2. the super anti-theft monitoring system of quotient according to claim 1, which is characterized in that the processor includes human face analysis mould
Block, face characteristic contrast module, black list database, alarm module and video analysis tracing module；
The human face analysis module, is analyzed for the facial image to camera transmissions, obtains the people of the facial image
Face feature vector；
The black list database, for storing the face feature vector of stealing personnel；
The face characteristic contrast module, for will extract obtained face feature vector and prestored in the black list database
Face feature vector be compared, judge whether the face corresponding with the face prestored in the black list database, if
It is corresponding, then determine that the face is to identify target, and its corresponding identity information is transferred to display terminal；
The alarm module for generating warning message after obtaining the identification target, and is exported to display terminal；
The video analysis tracking module, the vision signal for coming to all camera transmissions are analyzed, and identification mesh is obtained
Target real time position and mobile trajectory data, and export to display terminal.
3. the super anti-theft monitoring system of quotient according to claim 2, which is characterized in that the human face analysis module includes face
Image preprocessing submodule and facial image feature extraction submodule；
The facial image pre-processes submodule, pre-processes for the facial image to camera transmissions；
The facial image feature extraction submodule, for from the people extracted in pretreated facial image in the facial image
Face feature vector.
4. the super anti-theft monitoring system of quotient according to claim 3, which is characterized in that the facial image pre-processes submodule
Including gray processing unit, denoising unit and enhancement unit；
The gray processing unit carries out gray processing processing for the facial image to camera transmissions；
The denoising unit, for removing the random noise in the facial image after gray processing；
The enhancement unit, for carrying out enhancing processing to the facial image after denoising.
5. the super anti-theft monitoring system of quotient according to claim 4, which is characterized in that the face figure after the removal gray processing
Random noise as in, specifically:
(1) centered on pixel A (x, y), the rectangular window that a size is (2M+1,2M+1) is chosen, the ash is calculated separately
Gray scale absolute difference in facial image after degreeization in pixel B (x, y) and rectangular window between residual pixel point, wherein
Gray scale absolute difference between pixel A (x, y) and pixel B (m, n) can be calculated using following formula:
In formula, DABIt is the gray scale absolute difference between pixel A and pixel B,α is pixel A and picture
The Gauss weighted euclidean distance of vegetarian refreshments B, α are the standard deviation of Gaussian function, and h is the smoothing parameter of setting, and x, y are respectively pixel
The abscissa and ordinate of A, m, n are respectively the abscissa and ordinate of pixel B, and g (A) is the gray value of pixel A, g (B)
For the gray value of pixel B, Θ is the set that the residual pixel point in rectangular window not comprising pixel B is constituted；
(2) the gray scale absolute difference in obtained pixel A (x, y) and rectangular window between residual pixel point is subjected to ascending order row
Column obtain the set of ascending order arrangementWherein, hkFor kth in gray scale absolute difference
A the smallest element determines a new absolute difference order according to set H:
In formula, Q is the positive integer being manually set, and value range is: 2≤Q≤(2M+1)2- 1, Sq (A) are about pixel A's
New absolute difference order；
(3) according to obtained new absolute difference order, the contribution degree of pixel A is calculated:
In formula, λ1、λ2For preset threshold constant, and meet λ1> λ2, T (A) is the contribution degree of pixel A, which is used to
The degree that the pixel belongs to noise spot is measured, η is the exponential factor of setting, meets 2≤η≤4 and shows as T (A)=0
Pixel A is noise pixel point certainly, and as T (A)=1, showing pixel A not is noise pixel point；
(4) according to the contribution degree of pixel A, the denoising estimated value of pixel A is calculated using following formula,
In formula,For the denoising estimated value of pixel A,For centered on pixel A, size is (2M+1,2M+1)
Rectangular window in all pixels point average gray value, g (A) be pixel A gray value；
All pixels point in facial image after traversing gray processing, and replaced with the denoising estimated value for each pixel being calculated
The gray value of pixel is answered in commutation, and the set that replaced all pixels point is constituted is the facial image after denoising.
6. tripper according to claim 5, which is characterized in that described to extract obtained face feature vector and institute
The face feature vector prestored in black list database is stated to be compared, judge the face whether in the black list database
The face that prestores is corresponding, if it does correspond, then determining that the face is to identify target, and its corresponding identity information is transferred to aobvious
Show terminal, specifically: the face feature vector for obtaining extractionWith the face feature vector prestored in the black list databaseIt is compared, if metThen judge that the face is to identify target, and by its corresponding identity information
It is transferred to display terminal, whereinFor the face feature vector of the facial image of camera transmissions,For the blacklist data
The face feature vector prestored in library, δ are the customized similarity factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811031988.2A CN109145862A (en) | 2018-09-05 | 2018-09-05 | A kind of super anti-theft monitoring system of quotient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811031988.2A CN109145862A (en) | 2018-09-05 | 2018-09-05 | A kind of super anti-theft monitoring system of quotient |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109145862A true CN109145862A (en) | 2019-01-04 |
Family
ID=64827020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811031988.2A Withdrawn CN109145862A (en) | 2018-09-05 | 2018-09-05 | A kind of super anti-theft monitoring system of quotient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145862A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389793A (en) * | 2018-10-16 | 2019-02-26 | 深圳众宝城贸易有限公司 | A kind of super anti-theft monitoring system of quotient |
| CN110207318A (en) * | 2019-06-10 | 2019-09-06 | 吴赵东 | The air purifying robot of voice control |
| CN112422499A (en) * | 2020-09-14 | 2021-02-26 | 深圳英飞拓科技股份有限公司 | Method and system for identifying black and white lists of human face based on 5G transmission |
| CN113378622A (en) * | 2021-04-06 | 2021-09-10 | 青岛以萨数据技术有限公司 | Specific person identification method, device, system and medium |
| CN113435274A (en) * | 2021-06-15 | 2021-09-24 | 深圳市综合交通设计研究院有限公司 | Identification and analysis algorithm and device for illegal pull personnel of comprehensive transportation hub |
-
2018
- 2018-09-05 CN CN201811031988.2A patent/CN109145862A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389793A (en) * | 2018-10-16 | 2019-02-26 | 深圳众宝城贸易有限公司 | A kind of super anti-theft monitoring system of quotient |
| CN109389793B (en) * | 2018-10-16 | 2021-05-28 | 南京溧水高新产业股权投资有限公司 | Superbusiness anti-theft monitoring system |
| CN110207318A (en) * | 2019-06-10 | 2019-09-06 | 吴赵东 | The air purifying robot of voice control |
| CN112422499A (en) * | 2020-09-14 | 2021-02-26 | 深圳英飞拓科技股份有限公司 | Method and system for identifying black and white lists of human face based on 5G transmission |
| CN113378622A (en) * | 2021-04-06 | 2021-09-10 | 青岛以萨数据技术有限公司 | Specific person identification method, device, system and medium |
| CN113435274A (en) * | 2021-06-15 | 2021-09-24 | 深圳市综合交通设计研究院有限公司 | Identification and analysis algorithm and device for illegal pull personnel of comprehensive transportation hub |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145862A (en) | A kind of super anti-theft monitoring system of quotient | |
| CN109389793B (en) | Superbusiness anti-theft monitoring system | |
| CN110087099B (en) | Monitoring method and system for protecting privacy | |
| CN110070010B (en) | Face attribute association method based on pedestrian re-recognition | |
| Tian et al. | Robust detection of abandoned and removed objects in complex surveillance videos | |
| Piccinini et al. | Reliable smoke detection in the domains of image energy and color | |
| CN105574855B (en) | Infrared small target detection method under cloud background based on template convolution and false alarm rejection | |
| US20060215904A1 (en) | Video based fire detection system | |
| CN108877009A (en) | A kind of intelligent access control system based on recognition of face | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN109460705A (en) | Oil pipeline monitoring method based on machine vision | |
| Karpagavalli et al. | Estimating the density of the people and counting the number of people in a crowd environment for human safety | |
| Patil et al. | Motion saliency based generative adversarial network for underwater moving object segmentation | |
| CN109446913A (en) | A kind of detection method for judging vehicle bottom and whether reequiping | |
| CN104881643A (en) | Method and system for rapidly detecting remains | |
| Zhang et al. | Fusion of infrared and visible light images based on nonsubsampled shearlet transform | |
| CN107818547A (en) | The minimizing technology of the spiced salt and Gaussian mixed noise in a kind of sequence towards twilight image | |
| Hou et al. | Automated people counting at a mass site | |
| CN109754411A (en) | Building pivot frame larceny detection method and system are climbed based on optical flow method target following | |
| CN111950518A (en) | Video image enhancement method for violent behavior recognition | |
| CN116798100A (en) | Face video detection method and device | |
| CN110189273A (en) | A kind of hidden image restorative procedure based on double sampling | |
| Frejlichowski et al. | Extraction of the foreground regions by means of the adaptive background modelling based on various colour components for a visual surveillance system | |
| Harlapur et al. | Fire Detection using Optical Flow Method in Videos | |
| Ali et al. | Automated secure room system |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190104 |
|
| WW01 | Invention patent application withdrawn after publication |