CN109299683A - A kind of security protection assessment system based on recognition of face and behavior big data - Google Patents
A kind of security protection assessment system based on recognition of face and behavior big data Download PDFInfo
- Publication number
- CN109299683A CN109299683A CN201811067788.2A CN201811067788A CN109299683A CN 109299683 A CN109299683 A CN 109299683A CN 201811067788 A CN201811067788 A CN 201811067788A CN 109299683 A CN109299683 A CN 109299683A
- Authority
- CN
- China
- Prior art keywords
- personnel
- image
- elevator
- resident
- subgraph
- 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.)
- Granted
Links
- 238000007781 pre-processing Methods 0.000 claims abstract description 41
- 230000005540 biological transmission Effects 0.000 claims abstract description 32
- 238000004891 communication Methods 0.000 claims abstract description 24
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 30
- 230000001815 facial effect Effects 0.000 claims description 30
- 238000011156 evaluation Methods 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 8
- 230000005484 gravity Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 3
- 230000035622 drinking Effects 0.000 claims description 2
- 101150011264 setB gene Proteins 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 claims 1
- 238000005192 partition Methods 0.000 claims 1
- 230000000717 retained effect Effects 0.000 claims 1
- 230000006399 behavior Effects 0.000 description 50
- 238000005516 engineering process Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 101100294413 Aspergillus versicolor notB' gene Proteins 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of security protection assessment system based on recognition of face and behavior big data, including capture and obtain module, preprocessing module, database, behavior judge identification module, Cloud Server, communication transmission module and remote display terminals；It captures acquisition module and judges that identification module is connect with preprocessing module and behavior respectively, Cloud Server judges that identification module, database and communication transmission module are connect with preprocessing module, behavior respectively, and communication transmission module is connect with remote display terminals.Safety estimation system provided by the invention based on recognition of face and behavior big data, improve the accuracy of the personnel's image comparison stored in personnel's image and database in elevator, and the safety of each elevator is intuitively understood convenient for cell management personnel, realization effectively judges the safety of each elevator, with timeliness, the control for improving cell security, substantially increases the accuracy and safety of community security defence, provides safety living environment for community resident.
Description
Technical field
The invention belongs to field of security technologies, are related to a kind of based on recognition of face and the security protection of behavior big data assessment system
System.
Background technique
Now, be primary requirement of the resident to residential quarters safely, at present the security system in Residential Area mainly by with
Lower two kinds of systems are constituted: closed-circuit TV monitoring system, are imaged in cell main thoroughfare, important Gongjian and circumference setting front end
Image is transmitted to monitoring center by machine, and monitoring center can be monitored in real time and be recorded to entire cell；And electronic patrol
System uses off-line type night watching technology, by patrolling stick to the Card read/write and memory technology of patrol point, to realize to night watching
The work management of member, so that the people's air defense in best performance residential security management acts on.
Although, can not be to entering elevator however, be equipped with closed-circuit TV monitoring system in many residential elevators at present
Interior personnel identity, behavior and the building generic term for a building, e. g. Apartment, store, a movie theater, etc. lived, floor number analyze and count, cause many strange personnel by into
Cell is stolen etc. after entering elevator, and with plundering, hit and the frequency of occurrences of other indecency behaviors is more next in elevator
It is higher, once accident occurs in elevator, the generation of accident can not be understood at the first time positioned at the administrative staff of monitoring center, in turn
It can not ensure the safety of resident, in order to improve the security protection characteristic of cell, now design a kind of based on recognition of face and behavior big data
Security protection assessment system.
Summary of the invention
The security protection assessment system based on recognition of face and behavior big data that the purpose of the present invention is to provide a kind of, solves
Existing community security system has that timeliness is poor and safe living environment can not be provided for resident, can not be effective
Ground judgement enters identity, movement, the floor of pressed elevator etc. of personnel in elevator, thereby reduces the safety of resident's living environment
Property.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of security protection assessment system based on recognition of face and behavior big data, including capture and obtain module, pretreatment mould
Block, database, behavior judge identification module, Cloud Server, communication transmission module and remote display terminals；
It captures acquisition module and judges that identification module is connect with preprocessing module and behavior respectively, Cloud Server is located with pre- respectively
Reason module, behavior judge that identification module, database are connected with communication transmission module, and communication transmission module and remote display terminals connect
It connects；
Capturing and obtaining module includes several image-capture units, and video capture unit is camera, for captured in real-time electricity
The elevator floor image that personnel's image information and everyone in ladder are pressed in elevator, and by personnel's image information of acquisition
The behavior of being sent to judges identification module, and the elevator floor image information that personnel's image information of acquisition and personnel are pressed is sent
To preprocessing module；
Preprocessing module, which is used to receive to capture the personnel's image information for obtaining module transmission and obtain, shoots personnel's image
The number of the video capture unit of information extracts the dressing color and hair style of personnel in received personnel's image, and to acquisition
Same personnel image information carry out clarity screening, filter out the highest image information of clarity, and the figure that will be filtered out
As carrying out image amplification, so that the size of face is hxf in amplified image, homalographic is carried out to amplified image and is drawn
Point, it is divided into L subgraph, L subgraph of division is successively compiled according to sequence from left to right and from top to bottom
Number, respectively 1,2 ..., L successively generate s to each subgraph in L subgraph of division and tie up index vector, according to dimension rope
The amount of guiding into extracts feature from spirte and labeled as DL 1, each subgraph repeats Y times, obtains Y feature of each subgraph
Subclass constitutes sample characteristics subclass DL Y, Y=1,2 ..., Y, L=1,2 ..., L,CLY is expressed as obtaining in image the Y character subset conjunction in l-th subgraph, pre- to locate
The corresponding LxY character subset conjunction of the image is sent to Cloud Server by reason module, meanwhile, preprocessing module is received to capture and be obtained
The image information for the pressed elevator floor of personnel that module is sent extracts the elevator building in the image information of the pressed elevator floor of personnel
Layer information and personnel's image information by elevator, by personnel's dressing color, hair in personnel's image information by elevator of extraction
Type is compared with personnel's dressing color, the hair style in personnel's image information of candid photograph one by one respectively, to screen matching degree highest
Image information, preprocessing module is special by the corresponding sample of the highest image of the corresponding matching degree of everyone in the elevator of screening
Sign subclass, the elevator floor number that personnel are pressed in the image and shoot the video capture element number of the image information according to
It is secondary to be sent to Cloud Server；
Database is used to store the facial image of the community resident of prior typing and each facial image is divided into several sons
The corresponding sample characteristics subclass of image, wherein each resident closes successively suitable according to the corresponding character subset of facial image of typing
Sequence is numbered respectively 1 to each resident, 2 ..., i ..., n, the subgraph of different location in the facial image of different residents
Corresponding character subset closes difference, and stores the corresponding resident's residential building number of each resident's facial image, floor number and deposit
The different behavior acts of storage personnel, behavior act are divided according to the behavior act standard of setting, and it is dynamic to be divided into abnormal behaviour
Make and normal behaviour acts；
Behavior judges identification module for receiving the personnel's image information for capturing and obtaining module and sending, to personnel's image information
Middle human behavior movement extracts, and the movement of the human behavior of extraction is sent to Cloud Server；
It is right that Cloud Server is used to receive the highest image institute of the corresponding matching degree of personnel in the elevator of preprocessing module transmission
The elevator floor number that the sample characteristics subclass and the personnel answered are pressed, the corresponding sample of received everyone's image is special
The corresponding sample characteristics subclass of each resident's facial image for storing is compared one by one in sign subclass and database, obtains spy
Sign comparison setB′LiY is expressed as in elevator in personnel's image in l-th subgraph
Y character subset is closed to close with the Y character subset in the l-th subgraph of i-th of the resident personnel stored in database and be compared
Numerical value, if i-th of resident that the Y character subset is closed and stored in database in l-th subgraph in personnel's image in elevator
The Y character subset closes consistent in the l-th subgraph of personnel, then takes B 'LiY is equal to 1, otherwise, takes B 'LiY is equal to 0, cloud clothes
Comparison of the business device according to each resident personnel image in personnel in elevator and database, statistical nature degree matching factorThe highest feature degree matching factor of feature degree matching degree coefficient is extracted, and by the spy of extraction
Sign degree matching factor and the feature degree matching factor threshold value of setting compare, if this feature degree matching factor is less than the spy of setting
Sign degree matching factor threshold value then shows that the corresponding personnel of personnel's image are non-community resident in the elevator, if this feature degree matches
Coefficient is greater than the feature degree matching factor threshold value of setting, then shows that personnel correspond to corresponding personnel as this community resident in elevator；
Cloud Server extracts the maximum feature degree matching degree of the feature degree matching factor threshold value greater than setting from database
The corresponding resident's residential building number of the personnel of coefficient, floor number, and the building of extraction number is sent with preprocessing module
The personnel that video capture element number, floor number and preprocessing module are sent are compared by elevator floor number, if extracting
Building number it is identical with the video capture element number that preprocessing module is sent, and floor number and preprocessing module transmission people
Member is pressed, and elevator floor number is identical, then the pressed elevator floor of personnel is correct, otherwise, the pressed elevator floor mistake of personnel；
Cloud Server reception behavior features judge identification module send human behavior movement, to received human behavior movement with
The human behavior movement stored in database is compared one by one, to determine whether the personnel are abnormal behavior act, and is sentenced
The type of the disconnected abnormal behaviour movement occurred；
Whether Cloud Server is whether this community resident, personnel institute are correct and should by elevator floor according to personnel in elevator
The abnormal behaviour of personnel acts corresponding type, overall construction metewand, and Cloud Server is by the safety in each building elevator
Property metewand is sent to remote display terminals through communication transmission module, meanwhile, Cloud Server by safety evaluation coefficient with set
Fixed safety evaluation coefficient threshold compares, if safety evaluation coefficient is less than the safety evaluation coefficient threshold of setting,
Cloud Server sends alarm signal to alarm module；
Communication transmission module is cordless communication network, is connect for realizing Cloud Server with remote display terminals, will be received
Cloud Server send each building elevator in safety evaluation coefficient send remote display terminals；
Remote display terminals are smart phone or computer, for receiving in each building elevator that communication transmission module is sent
Safety evaluation coefficient is simultaneously shown.
Further, several video capture units obtained in module of capturing are divided with Lou Dong, and each building is right
The number answered is followed successively by 1,2 ..., f ..., g, is numbered, is followed successively by respectively to each video capture unit in same Stall
1,2 ..., j ..., h, j are expressed as j-th of video capture unit in each building.
Further, the preprocessing module, which receives to capture, obtains personnel's image information that module is sent, clear to filter out
The method of the clear highest image information of degree, comprising the following steps:
H1, successively reception staff's image information；
H2, according to receiving time sequencing, successively the clarity of received image is identified；
H3, the clarity of the clarity of previous image and latter image is compared, rejects the low image of clarity, protects
Stay the image that clarity is high；
H4, the high image of clarity is successively compared with the clarity of next image, retains the high image of clarity,
Until when remaining amount of images is 1, using remaining image as the highest image information of clarity.
Further, the acquisition methods of the corresponding sample characteristics subclass of the facial image of each resident, comprising the following steps:
The size of S1, the face image for obtaining each resident, image are hxf, and by each image according to identical division
Model split is at the subgraph of L equal sizes, and the size of each subgraph is p=hxf/L, and the number of each resident is according to setting
Sequence be ranked up, respectively 1,2 ..., i ..., n, subgraph in the image of each resident according to from left to right and from
The sequence of top to bottm is successively numbered each subgraph in same image, and respectively 1,2 ..., k ..., L, (k < L) are each
Subgraph in the image of resident constitutes independent subgraph image set and closes Ai(ai1,ai2,...,aiL), AiIt is expressed as i-th of resident's image
Corresponding all set of sub-images, aiL is expressed as the l-th subgraph in i-th of resident's spirte set；
S2, the subgraph of same position in all resident's images is converted into column vector and according to the number order of each resident
It is combined, forms L subgraph training sample set and close, subgraph training sample set is combined into Bk (a1k,a2k,...,aik,...,
anK), aiK is expressed as k-th of sample subgraph of i-th of resident；
S3, to s dimension index vector v is randomly generated in various kinds this subgraph in each subgraph training sample set1 i=
{I1 1,I1 2,...,I1 s, according to dimension index vector v1 iFeature is extracted from Bk and is expressed as Bi1, and i=1,2 ..., i ..., n；
S4, step S3 is repeated, until executing Y times, obtains Y character subset and close BiY, Y=1,2 ..., Y；
S5, it is repeated in S3-S4 step, n sample subgraph in L subgraph training sample set conjunction is obtained respectively
Character subset closes, and the character subset for forming L nxY closes, and the character subset of L nxY, which closes, constitutes sample feature setThe corresponding sample characteristics of each resident's facial image in Screening Samples characteristic set
Subset is combined intoDLiY is expressed as the corresponding sample characteristics of i-th of resident's facial image
Subclass, BLiY is expressed as the conjunction of the Y character subset in i-th of resident's facial image in l-th subgraph.
Further, each character subset closes corresponding specific gravity and is respectively in sample characteristics subclassUBLiY is expressed as the Y spy in the l-th subgraph of i-th of resident personnel
The specific gravity of subclass comparison is levied, and
Further, abnormal behaviour movement include hand-held cutter, fight, destroys elevator operate normally, smoking and
It drinks behavior act, abnormal behaviour is acted and is ranked up according to degree of danger, respectively hand-held cutter fights, destroys elevator
It operates normally, smoke, drink, and the corresponding danger coefficient of each abnormal behavior act is respectively t1, t2 ..., tv, tv is expressed as
The abnormal behaviour that number is v acts corresponding danger coefficient.
Further, the calculation formula of the safety evaluation coefficient in each elevator isWherein, x is expressed as whether the personnel in elevator are that this cell is signed, if this cell
Resident, x=1, otherwise, x=0.7, z be expressed as personnel by the floor of elevator whether correct, if the floor that personnel are pressed is
The floor of the resident institute residential building generic term for a building, e. g. Apartment, store, a movie theater, etc., then take z=1, otherwise, z=0.68, AvIt is expressed as abnormal behaviour of the personnel in elevator
The type of movement, and AvEqual to fixed numbers, A 'vIt is expressed as the corresponding danger of type of abnormal behaviour movement of the personnel in elevator
Dangerous coefficient, if personnel are v-th of abnormal behaviour movement, A in elevatorvEqual to 0.
It further, further include alarm module, the alarm module is processor, buzzer and LED light, processor difference
With buzzer and LED light, for receiving the alarm signal of Cloud Server transmission, alarm signal sends control respectively based on the received
Instruction carries out acoustic alarm and light alarm to buzzer and LED light.
Beneficial effects of the present invention:
Safety estimation system provided by the invention based on recognition of face and behavior big data, by resident in cell into
Row Image Acquisition divides image, feature extraction, and being merged with to obtain the corresponding sample characteristics subset of each resident will acquire
Sample feature set is stored to database, and the reference as the corresponding sample characteristics subclass of personnel's image captured in elevator is marked
Standard improves the accuracy that character subset in personnel's image closes comparison；
Identification module is judged by candid photograph acquisition module, preprocessing module, behavior and gathers Cloud Server in each elevator
The image of personnel, institute are analyzed and processed by floor and behavior act, to count the safety evaluation coefficient in each elevator, and
The safety evaluation coefficient of acquisition is sent to display terminal, the safety of each elevator is intuitively understood convenient for cell management personnel
Property, it realizes and the safety in each elevator is effectively judged, the high spy of the timeliness with safety evaluation coefficient feedback
Point improves the control of cell security, substantially increases the accuracy and safety of community security defence, provides for community resident
Safety living environment.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will be described below to embodiment required
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of schematic diagram of the security protection assessment system based on recognition of face and behavior big data of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all other
Embodiment shall fall within the protection scope of the present invention.
Refering to Figure 1, a kind of security protection assessment system based on recognition of face and behavior big data, including capture and obtain
Module, preprocessing module, database, behavior judge identification module, Cloud Server, alarm module, communication transmission module and long-range
Display terminal；It captures and obtains module and judge that identification module is connect with preprocessing module and behavior respectively, Cloud Server is respectively and in advance
Processing module, behavior judge that identification module, database, alarm module are connected with communication transmission module, communication transmission module and remote
The connection of journey display terminal；
Capturing and obtaining module includes several image-capture units, and described image snap unit is camera, is mounted on cell
In interior each elevator, for the personnel's image information and the elevator floor pressed in elevator of everyone in captured in real-time elevator
Image, and personnel's image information of acquisition is sent to behavior and judges identification module, by personnel's image information of acquisition and people
Member by elevator floor image information be sent to preprocessing module, wherein capture obtain module in several video capture lists
The building Yuan Yi is divided, and corresponding number in each building is followed successively by 1,2 ..., f ..., g, is grabbed to each image in same Stall
Unit is clapped to be numbered respectively, be followed successively by 1,2 ..., j ..., h, j be expressed as j-th of video capture unit in each building；
Preprocessing module, which is used to receive to capture the personnel's image information for obtaining module transmission and obtain, shoots personnel's image
The number of the video capture unit of information extracts the dressing color and hair style of personnel in received personnel's image, and to acquisition
Same personnel image information carry out clarity screening, filter out the highest image information of clarity, and the figure that will be filtered out
As carrying out image amplification, so that the size of face is hxf in amplified image, homalographic is carried out to amplified image and is drawn
Point, it is divided into L subgraph, L subgraph of division is successively compiled according to sequence from left to right and from top to bottom
Number, respectively 1,2 ..., L successively generate s to each subgraph in L subgraph of division and tie up index vector, according to dimension rope
The amount of guiding into extracts feature from spirte and labeled as DL 1, each subgraph repeats Y times, obtains Y feature of each subgraph
Subclass constitutes sample characteristics subclass DL Y, Y=1,2 ..., Y, L=1,2 ..., L,CLY is expressed as obtaining in image the Y character subset conjunction in l-th subgraph, pre- to locate
The corresponding LxY character subset conjunction of the image is sent to Cloud Server by reason module, meanwhile, preprocessing module is received to capture and be obtained
The image information for the pressed elevator floor of personnel that module is sent extracts the elevator building in the image information of the pressed elevator floor of personnel
Layer information and personnel's image information by elevator, by personnel's dressing color, hair in personnel's image information by elevator of extraction
Type is compared with personnel's dressing color, the hair style in personnel's image information of candid photograph one by one respectively, to screen matching degree highest
Image information, preprocessing module is special by the corresponding sample of the highest image of the corresponding matching degree of everyone in the elevator of screening
Sign subclass, the elevator floor number that personnel are pressed in the image and shoot the video capture element number of the image information according to
It is secondary to be sent to Cloud Server；
Wherein, preprocessing module, which receives to capture, obtains personnel's image information that module is sent, to filter out clarity highest
Image information method, comprising the following steps:
H1, successively reception staff's image information；
H2, according to receiving time sequencing, successively the clarity of received image is identified；
H3, the clarity of the clarity of previous image and latter image is compared, rejects the low image of clarity, protects
Stay the image that clarity is high；
H4, the high image of clarity is successively compared with the clarity of next image, retains the high image of clarity,
Until when remaining amount of images is 1, using remaining image as the highest image information of clarity.
Database is used to store the facial image of the community resident of prior typing and each facial image is divided into several sons
The corresponding sample characteristics subclass of image, wherein each resident closes successively suitable according to the corresponding character subset of facial image of typing
Sequence is numbered respectively 1 to each resident, 2 ..., i ..., n, the subgraph of different location in the facial image of different residents
Corresponding character subset closes difference, and stores the corresponding resident's residential building number of each resident's facial image, floor number and deposit
The different behavior acts of storage personnel, behavior act are divided according to the behavior act standard of setting, and it is dynamic to be divided into abnormal behaviour
Make and normal behaviour movement, abnormal behaviour movement includes hand-held cutter, fight, destroys elevator operate normally, smoking and
It drinks and waits behavior acts, abnormal behaviour is acted and is ranked up according to degree of danger, respectively hand-held cutter fights, destroys electricity
Ladder such as operates normally, smokes, drinking at the behaviors, and the corresponding danger coefficient of each exception behavior act is respectively t1, t2 ..., tv,
Tv is expressed as the abnormal behaviour that number is v and acts corresponding danger coefficient；
Wherein, the acquisition methods of the corresponding sample characteristics subclass of the facial image of each resident, comprising the following steps:
The size of S1, the face image for obtaining each resident, image are hxf, and by each image according to identical division
Model split is at the subgraph of L equal sizes, and the size of each subgraph is p=hxf/L, and the number of each resident is according to setting
Sequence be ranked up, respectively 1,2 ..., i ..., n, subgraph in the image of each resident according to from left to right and from
The sequence of top to bottm is successively numbered each subgraph in same image, and respectively 1,2 ..., k ..., L, (k < L) are each
Subgraph in the image of resident constitutes independent subgraph image set and closes Ai(ai1,ai2,...,aiL), AiIt is expressed as i-th of resident's image
Corresponding all set of sub-images, aiL is expressed as the l-th subgraph in i-th of resident's spirte set；
S2, the subgraph of same position in all resident's images is converted into column vector and according to the number order of each resident
It is combined, forms L subgraph training sample set and close, subgraph training sample set is combined into Bk (a1k,a2k,...,aik,...,
anK), aiK is expressed as k-th of sample subgraph of i-th of resident；
S3, to s dimension index vector v is randomly generated in various kinds this subgraph in each subgraph training sample set1 i=
{I1 1,I1 2,...,I1 s, according to dimension index vector v1 iFeature is extracted from Bk and is expressed as Bi1, and i=1,2 ..., i ..., n；
S4, step S3 is repeated, until executing Y times, obtains Y character subset and close BiY, Y=1,2 ..., Y；
S5, it is repeated in S3-S4 step, n sample subgraph in L subgraph training sample set conjunction is obtained respectively
Character subset closes, and the character subset for forming L nxY closes, and the character subset of L nxY, which closes, constitutes sample feature setThe corresponding sample characteristics of each resident's facial image in Screening Samples characteristic set
Subset is combined intoDLiY is expressed as the corresponding sample characteristics of i-th of resident's facial image
Subclass, BLiY is expressed as the conjunction of the Y character subset in i-th of resident's facial image in l-th subgraph.
Behavior judges identification module for receiving the personnel's image information for capturing and obtaining module and sending, to personnel's image information
Middle human behavior movement extracts, and the movement of the human behavior of extraction is sent to Cloud Server；
It is right that Cloud Server is used to receive the highest image institute of the corresponding matching degree of personnel in the elevator of preprocessing module transmission
The elevator floor number that the sample characteristics subclass and the personnel answered are pressed, the corresponding sample of received everyone's image is special
The corresponding sample characteristics subclass of each resident's facial image for storing is compared one by one in sign subclass and database, obtains spy
Sign comparison setEach character subset closes corresponding specific gravity point in sample characteristics subclass
It is notB′LiY is expressed as in elevator in personnel's image in l-th subgraph
Y character subset is closed to close with the Y character subset in the l-th subgraph of i-th of the resident personnel stored in database and be compared
Numerical value, UBLiY is expressed as the specific gravity that the Y character subset in the l-th subgraph of i-th of resident personnel closes comparison, andIf the Y character subset is closed and is stored in database in l-th subgraph in personnel's image in elevator
The Y character subset closes consistent in the l-th subgraph of i-th of resident personnel, then takes B 'LiY is equal to 1, otherwise, takes B 'LiY
Equal to 0, comparison of the Cloud Server according to each resident personnel image in personnel in elevator and database, statistical nature degree matching factorThe highest feature degree matching factor of feature degree matching degree coefficient is extracted, and by the spy of extraction
Sign degree matching factor and the feature degree matching factor threshold value of setting compare, if this feature degree matching factor is less than the spy of setting
Sign degree matching factor threshold value then shows that the corresponding personnel of personnel's image are non-community resident in the elevator, if this feature degree matches
Coefficient is greater than the feature degree matching factor threshold value of setting, then shows that personnel correspond to corresponding personnel as this community resident in elevator；
Cloud Server extracts the maximum feature degree matching degree of the feature degree matching factor threshold value greater than setting from database
The corresponding resident's residential building number of the personnel of coefficient, floor number, and the building of extraction number is sent with preprocessing module
The personnel that video capture element number, floor number and preprocessing module are sent are compared by elevator floor number, if extracting
Building number it is identical with the video capture element number that preprocessing module is sent, and floor number and preprocessing module transmission people
Member is pressed, and elevator floor number is identical, then the pressed elevator floor of personnel is correct, otherwise, the pressed elevator floor mistake of personnel；
Cloud Server reception behavior features judge identification module send human behavior movement, to received human behavior movement with
The human behavior movement stored in database is compared one by one, to determine whether the personnel are abnormal behavior act, and is sentenced
The type of the disconnected abnormal behaviour movement occurred；
Whether Cloud Server is whether this community resident, personnel institute are correct and should by elevator floor according to personnel in elevator
The abnormal behaviour of personnel acts corresponding type, overall construction metewandWherein,
X is expressed as whether the personnel in elevator are that this cell is signed, and if this community resident, x=1, otherwise, x=0.7, z indicate to be people
Whether the floor of the pressed elevator of member if floor that personnel pressed be the floor of the resident institute residential building generic term for a building, e. g. Apartment, store, a movie theater, etc., takes z=correct
1, otherwise, z=0.68, AvIt is expressed as the type of abnormal behaviour movement of the personnel in elevator, and AvEqual to fixed numbers, A 'vTable
Be shown as personnel in elevator abnormal behaviour movement the corresponding danger coefficient of type, if personnel in elevator for do v-th it is different
Normal behavior act, then AvEqual to 0, safety evaluation coefficient is higher, shows that the security protection of cell is higher, and Cloud Server is by each building
Safety evaluation coefficient in elevator is sent to remote display terminals through communication transmission module, meanwhile, Cloud Server is by safety
Metewand and the safety evaluation coefficient threshold of setting compare, if the safety that safety evaluation coefficient is less than setting is commented
Estimate coefficient threshold, Cloud Server sends alarm signal to alarm module.
Communication transmission module is cordless communication network, is connect for realizing Cloud Server with remote display terminals, will be received
Cloud Server send each building elevator in safety evaluation coefficient send remote display terminals；
Remote display terminals are smart phone or computer, for receiving in each building elevator that communication transmission module is sent
Safety evaluation coefficient is simultaneously shown, clearly grasps the safety evaluation coefficient in each elevator convenient for cell management personnel,
Improve the safety of cell.
Alarm module is processor, buzzer and LED light, and processor with buzzer and LED light, takes respectively for receiving cloud
The alarm signal that business device is sent, alarm signal sends control instruction to buzzer and LED light, realization sound report respectively based on the received
The alarm of alert and light.
Safety estimation system provided by the invention based on recognition of face and behavior big data, by resident in cell into
Row Image Acquisition divides image, feature extraction, and being merged with to obtain the corresponding sample characteristics subset of each resident will acquire
Sample feature set is stored to database, and the reference as the corresponding sample characteristics subclass of personnel's image captured in elevator is marked
Standard improves the accuracy that character subset in personnel's image closes comparison；
Identification module is judged by candid photograph acquisition module, preprocessing module, behavior and gathers Cloud Server, in each elevator
The image of personnel, institute are analyzed and processed by floor and behavior act, to count the safety evaluation coefficient in each elevator, and
The safety evaluation coefficient of acquisition is sent to display terminal, the safety of each elevator is intuitively understood convenient for cell management personnel
Property, it realizes and the safety in each elevator is effectively judged, the high spy of the timeliness with safety evaluation coefficient feedback
Point improves the control of cell security, substantially increases the accuracy and safety of community security defence, provides for community resident
Safety living environment.
The above content is just an example and description of the concept of the present invention, affiliated those skilled in the art
It makes various modifications or additions to the described embodiments or is substituted in a similar manner, without departing from invention
Design or beyond the scope defined by this claim, be within the scope of protection of the invention.
Claims (8)
1. a kind of security protection assessment system based on recognition of face and behavior big data, it is characterised in that: including capture obtain module,
Preprocessing module, database, behavior judge identification module, Cloud Server, communication transmission module and remote display terminals；
Capture obtain module judge that identification module is connect with preprocessing module and behavior respectively, Cloud Server respectively with pre-process mould
Block, behavior judge that identification module, database are connected with communication transmission module, and communication transmission module is connect with remote display terminals；
Capturing and obtaining module includes several image-capture units, and video capture unit is camera, in captured in real-time elevator
Personnel's image information and the elevator floor image pressed in elevator of everyone, and personnel's image information of acquisition is sent
Judge identification module to behavior, by personnel's image information of acquisition and personnel by elevator floor image information be sent to it is pre-
Processing module；
Preprocessing module, which is used to receive to capture the personnel's image information for obtaining module transmission and obtain, shoots personnel's image information
Video capture unit number, extract the dressing color and hair style of personnel in received personnel's image, and to the same of acquisition
The image information of one personnel carries out clarity screening, filters out the highest image information of clarity, and by the image filtered out into
The amplification of row image carries out equal area partition to amplified image, draws so that the size of face is hxf in amplified image
It is divided into L subgraph, L subgraph of division is successively numbered according to sequence from left to right and from top to bottom, point
Not Wei 1,2 ..., L, successively in L subgraph of division each subgraph generate s tie up index vector, according to dimension index vector
Feature is extracted from spirte and is labeled as DL 1, each subgraph repeats Y times, and Y character subset for obtaining each subgraph closes,
Constitute sample characteristics subclass DL Y, Y=1,2 ..., Y, L=1,2 ..., L,CLY table
It is shown as obtaining in image the Y character subset conjunction in l-th subgraph, preprocessing module is by the corresponding LxY feature of the image
Subclass is sent to Cloud Server, meanwhile, preprocessing module, which receives, captures the pressed elevator floor of personnel for obtaining that module is sent
Image information is extracted the elevator floor information in the image information of the pressed elevator floor of personnel and is believed by personnel's image of elevator
Breath, by personnel's dressing color, hair style in personnel's image information by elevator of extraction respectively and in personnel's image information of candid photograph
Personnel's dressing color, hair style compared one by one, to screen the highest image information of matching degree, preprocessing module is by screening
The electricity that personnel are pressed in the corresponding sample characteristics subclass of the highest image of the corresponding matching degree of everyone, the image in elevator
Terraced floor number and the video capture element number for shooting the image information are successively sent to Cloud Server；
Database is used to store the facial image of the community resident of prior typing and each facial image is divided into several subgraphs
Corresponding sample characteristics subclass, wherein each resident closes sequencing according to the corresponding character subset of facial image of typing, right
Each resident is numbered respectively 1,2 ..., i ..., n, and the subgraph of different location is corresponding in the facial image of different residents
Character subset close different, and store the corresponding resident's residential building number of each resident's facial image, floor number and storage people
The different behavior acts of member, behavior act divided according to the behavior act standard of setting, be divided into abnormal behaviour movement and
Normal behaviour movement；
Behavior judges identification module for receiving the personnel's image information for capturing and obtaining module and sending, to people in personnel's image information
Member's behavior act extracts, and the movement of the human behavior of extraction is sent to Cloud Server；
Cloud Server is used to receive in the elevator of preprocessing module transmission corresponding to the highest image of the corresponding matching degree of personnel
The elevator floor number that sample characteristics subclass and the personnel are pressed, by corresponding sample characteristics of received everyone's image
Gather sample characteristics subclass corresponding with each resident's facial image stored in database to be compared one by one, obtains feature pair
Than setB′LiY is expressed as in elevator in personnel's image in l-th subgraph Y
Character subset, which is closed, closes comparison number with the Y character subset in the l-th subgraph of i-th of the resident personnel stored in database
Value, if i-th of resident people that the Y character subset is closed and stored in database in l-th subgraph in personnel's image in elevator
The Y character subset closes consistent in the l-th subgraph of member, then takes B 'LiY is equal to 1, otherwise, takes B 'LiY is equal to 0, cloud service
Comparison of the device according to each resident personnel image in personnel in elevator and database, statistical nature degree matching factorThe highest feature degree matching factor of feature degree matching degree coefficient is extracted, and by the feature of extraction
Degree matching factor and the feature degree matching factor threshold value of setting compare, if this feature degree matching factor is less than the feature of setting
Matching factor threshold value is spent, then shows that the corresponding personnel of personnel's image are non-community resident in the elevator, if this feature degree matching system
Number is greater than the feature degree matching factor threshold value of setting, then shows that personnel correspond to corresponding personnel as this community resident in elevator；
Cloud Server extracts the maximum feature degree matching degree coefficient of the feature degree matching factor threshold value greater than setting from database
Personnel's corresponding resident's residential building number, floor number, and the image that the building of extraction number is sent with preprocessing module
The personnel that snap unit number, floor number and preprocessing module are sent are compared by elevator floor number, if the building extracted
Number is identical as the video capture element number that preprocessing module is sent, and the personnel institute that floor number and preprocessing module are sent
Identical by elevator floor number, then the pressed elevator floor of personnel is correct, otherwise, the pressed elevator floor mistake of personnel；
Cloud Server reception behavior features judge the human behavior movement that identification module is sent, to the movement of received human behavior and data
The human behavior movement stored in library is compared one by one, to determine whether the personnel are abnormal behavior act, and judges to send out
The type of raw abnormal behaviour movement；
Whether Cloud Server is this community resident, personnel institute by whether elevator floor correct and the personnel according to personnel in elevator
Abnormal behaviour act corresponding type, overall construction metewand, Cloud Server comments the safety in each building elevator
Estimate coefficient and be sent to remote display terminals through communication transmission module, meanwhile, Cloud Server by safety evaluation coefficient and setting
Safety evaluation coefficient threshold compares, if safety evaluation coefficient is less than the safety evaluation coefficient threshold of setting, cloud clothes
Business device sends alarm signal to alarm module；
Communication transmission module is cordless communication network, is connect for realizing Cloud Server with remote display terminals, by received cloud
The safety evaluation coefficient in each building elevator that server is sent sends remote display terminals；
Remote display terminals are smart phone or computer, the safety in each building elevator for receiving communication transmission module transmission
Property metewand is simultaneously shown.
2. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
In: the candid photograph is obtained several video capture units in module and is divided with Lou Dong, and corresponding number in each building is followed successively by
Each video capture unit in same Stall is numbered in 1,2 ..., f ..., g respectively, be followed successively by 1,2 ..., j ...,
H, j are expressed as j-th of video capture unit in each building.
3. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
In: the preprocessing module receives the personnel's image information for capturing and obtaining module and sending, to filter out the highest image of clarity
The method of information, comprising the following steps:
H1, successively reception staff's image information；
H2, according to receiving time sequencing, successively the clarity of received image is identified；
H3, the clarity of the clarity of previous image and latter image is compared, rejects the low image of clarity, retained clear
The high image of clear degree；
H4, the high image of clarity is successively compared with the clarity of next image, retains the high image of clarity, until
When remaining amount of images is 1, using remaining image as the highest image information of clarity.
4. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
In: the acquisition methods of the corresponding sample characteristics subclass of the facial image of each resident, comprising the following steps:
The size of S1, the face image for obtaining each resident, image are hxf, and by each image according to identical division mode
It is divided into the subgraph of L equal sizes, the size of each subgraph is p=hxf/L, and the number of each resident is according to the suitable of setting
Sequence is ranked up, respectively 1,2 ..., i ..., n, subgraph in the image of each resident according to from left to right and on to
Under sequence successively each subgraph in same image is numbered, respectively 1,2 ..., k ..., L, (k < L) each resident
Image in subgraph constitute independent subgraph image set close Ai(ai1,ai2,...,aiL), AiIt is corresponding to be expressed as i-th of resident's image
All set of sub-images, aiL is expressed as the l-th subgraph in i-th of resident's spirte set；
S2, the subgraph of same position in all resident's images is converted into column vector and is carried out according to the number order of each resident
Combination forms L subgraph training sample set and closes, and subgraph training sample set is combined into Bk (a1k,a2k,...,aik,...,
anK), aiK is expressed as k-th of sample subgraph of i-th of resident；
S3, to s dimension index vector v is randomly generated in various kinds this subgraph in each subgraph training sample set1 i={ I1 1,
I1 2,...,I1 s, according to dimension index vector v1 iFeature is extracted from Bk and is expressed as Bi1, and i=1,2 ..., i ..., n；
S4, step S3 is repeated, until executing Y times, obtains Y character subset and close BiY, Y=1,2 ..., Y；
S5, it is repeated in S3-S4 step, feature is obtained respectively to n sample subgraph in L subgraph training sample set conjunction
Subclass, the character subset for forming L nxY close, and the character subset of L nxY, which closes, constitutes sample feature setThe corresponding sample characteristics of each resident's facial image in Screening Samples characteristic set
Subset is combined intoDLiY is expressed as the corresponding sample characteristics of i-th of resident's facial image
Subclass, BLiY is expressed as the conjunction of the Y character subset in i-th of resident's facial image in l-th subgraph.
5. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
In: each character subset closes corresponding specific gravity and is respectively in sample characteristics subclassUBLiY is expressed as the Y spy in the l-th subgraph of i-th of resident personnel
The specific gravity of subclass comparison is levied, and
6. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
Include hand-held cutter, fight, destroy elevator normal operation, smoke and behavior act of drinking in: abnormal behaviour movement, it is right
Abnormal behaviour movement is ranked up according to degree of danger, and respectively hand-held cutter fights, destroys elevator and operate normally, smoke, drink
Wine, and the corresponding danger coefficient of each abnormal behavior act is respectively t1, t2 ..., tv, tv is expressed as the abnormal row that number is v
To act corresponding danger coefficient.
7. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
In: the calculation formula of the safety evaluation coefficient in each elevator isWherein, x table
Whether the personnel being shown as in elevator are that this cell is signed, and if this community resident, x=1, otherwise, x=0.7, z are expressed as personnel
Whether the floor of pressed elevator if floor that personnel pressed be the floor of the resident institute residential building generic term for a building, e. g. Apartment, store, a movie theater, etc., takes z=1 correct,
Otherwise, z=0.68, AvIt is expressed as the type of abnormal behaviour movement of the personnel in elevator, and AvEqual to fixed numbers, A 'vIt indicates
The corresponding danger coefficient of type of the abnormal behaviour for being personnel in elevator movement, if personnel done in elevator v-th it is abnormal
Behavior act, then AvEqual to 0.
8. a kind of security protection assessment system based on recognition of face and behavior big data according to claim 1, feature exist
In: further include alarm module, the alarm module be processor, buzzer and LED light, processor respectively with buzzer and LED
Lamp, for receiving the alarm signal of Cloud Server transmission, alarm signal sends control instruction to buzzer respectively based on the received
And LED light, carry out acoustic alarm and light alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811067788.2A CN109299683B (en) | 2018-09-13 | 2018-09-13 | Security protection evaluation system based on face recognition and behavior big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811067788.2A CN109299683B (en) | 2018-09-13 | 2018-09-13 | Security protection evaluation system based on face recognition and behavior big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109299683A true CN109299683A (en) | 2019-02-01 |
| CN109299683B CN109299683B (en) | 2019-12-10 |
Family
ID=65166814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811067788.2A Active CN109299683B (en) | 2018-09-13 | 2018-09-13 | Security protection evaluation system based on face recognition and behavior big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109299683B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978390A (en) * | 2019-03-29 | 2019-07-05 | 嘉应学院 | Office efficiency assessment system and its method based on image recognition |
| CN110309768A (en) * | 2019-06-28 | 2019-10-08 | 上海眼控科技股份有限公司 | The staff's detection method and equipment of car test station |
| CN110430395A (en) * | 2019-07-19 | 2019-11-08 | 苏州维众数据技术有限公司 | Video data AI processing system and processing method |
| CN110490098A (en) * | 2019-07-31 | 2019-11-22 | 恒大智慧科技有限公司 | Smoking behavior automatic testing method, equipment and the readable storage medium storing program for executing of community user |
| CN110674717A (en) * | 2019-09-16 | 2020-01-10 | 合肥中科奔巴科技有限公司 | Smoking monitoring system based on gesture recognition |
| CN111028109A (en) * | 2019-12-23 | 2020-04-17 | 重庆紫光华山智安科技有限公司 | Data processing method, device, server and storage medium |
| CN111435435A (en) * | 2019-12-10 | 2020-07-21 | 杭州海康威视数字技术股份有限公司 | Method, device, server and system for identifying pedestrians |
| CN111488853A (en) * | 2020-04-23 | 2020-08-04 | 杨九妹 | Big data face recognition method and system for financial institution security system and robot |
| CN111967410A (en) * | 2020-08-20 | 2020-11-20 | 倪慧珍 | Property intelligent management and allocation system based on big data |
| CN112330514A (en) * | 2020-09-29 | 2021-02-05 | 佳都新太科技股份有限公司 | Community public security information evaluation method, device, equipment and storage medium |
| CN113688841A (en) * | 2020-05-19 | 2021-11-23 | 深圳市中兴***集成技术有限公司 | Intelligent security method based on image feature extraction |
| CN114548831A (en) * | 2022-04-21 | 2022-05-27 | 深圳市龙光云众智慧科技有限公司 | Evaluation report generation method and device, electronic equipment and storage medium |
| CN117437157A (en) * | 2023-10-16 | 2024-01-23 | 无锡远传融创科技有限公司 | Image processing method based on monitoring video data |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050080520A1 (en) * | 2003-09-22 | 2005-04-14 | Robert Kline | Waste recovery and material handling process to replace the traditional trash transfer station and landfil by extracting reusable material and energy from joined refuse streams to include; office waste, dry waste, wet garbage and the special hazardous material handling of biological, chemical, and nuclear waste |
| US20080013807A1 (en) * | 2004-07-01 | 2008-01-17 | American Express Travel Related Services Company, Inc. | Method and system for keystroke scan recognition biometrics on a smartcard |
| US20090310828A1 (en) * | 2007-10-12 | 2009-12-17 | The University Of Houston System | An automated method for human face modeling and relighting with application to face recognition |
| CN101923669A (en) * | 2008-07-18 | 2010-12-22 | 史迪芬·凯斯 | Intelligent adaptive design |
| CN102009879A (en) * | 2010-11-18 | 2011-04-13 | 无锡中星微电子有限公司 | Elevator automatic keying control system and method, face model training system and method |
| CN102194106A (en) * | 2011-05-11 | 2011-09-21 | 西安理工大学 | Human face recognition method used in door access system |
| CN104394359A (en) * | 2014-11-05 | 2015-03-04 | 浪潮(北京)电子信息产业有限公司 | Security monitoring method and system based on infrared and face recognition technologies |
| CN105678873A (en) * | 2015-12-31 | 2016-06-15 | 恩泊泰（天津）科技有限公司 | Intelligent building elevator access control and security guard system |
| CN105929696A (en) * | 2015-12-18 | 2016-09-07 | 许昌学院 | Intelligent home security method |
| CN106379777A (en) * | 2016-10-29 | 2017-02-08 | 安徽省艾佳信息技术有限公司 | Housing estate elevator security and protection system |
| CN106429660A (en) * | 2016-11-24 | 2017-02-22 | 江苏旭云物联信息科技有限公司 | Intelligent elevator safety management system and method |
| CN106652293A (en) * | 2016-12-30 | 2017-05-10 | 安徽杰瑞信息科技有限公司 | Intelligent district online safety and protection monitoring system |
-
2018
- 2018-09-13 CN CN201811067788.2A patent/CN109299683B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050080520A1 (en) * | 2003-09-22 | 2005-04-14 | Robert Kline | Waste recovery and material handling process to replace the traditional trash transfer station and landfil by extracting reusable material and energy from joined refuse streams to include; office waste, dry waste, wet garbage and the special hazardous material handling of biological, chemical, and nuclear waste |
| US20080013807A1 (en) * | 2004-07-01 | 2008-01-17 | American Express Travel Related Services Company, Inc. | Method and system for keystroke scan recognition biometrics on a smartcard |
| US20090310828A1 (en) * | 2007-10-12 | 2009-12-17 | The University Of Houston System | An automated method for human face modeling and relighting with application to face recognition |
| CN101923669A (en) * | 2008-07-18 | 2010-12-22 | 史迪芬·凯斯 | Intelligent adaptive design |
| CN102009879A (en) * | 2010-11-18 | 2011-04-13 | 无锡中星微电子有限公司 | Elevator automatic keying control system and method, face model training system and method |
| CN102194106A (en) * | 2011-05-11 | 2011-09-21 | 西安理工大学 | Human face recognition method used in door access system |
| CN104394359A (en) * | 2014-11-05 | 2015-03-04 | 浪潮(北京)电子信息产业有限公司 | Security monitoring method and system based on infrared and face recognition technologies |
| CN105929696A (en) * | 2015-12-18 | 2016-09-07 | 许昌学院 | Intelligent home security method |
| CN105678873A (en) * | 2015-12-31 | 2016-06-15 | 恩泊泰（天津）科技有限公司 | Intelligent building elevator access control and security guard system |
| CN106379777A (en) * | 2016-10-29 | 2017-02-08 | 安徽省艾佳信息技术有限公司 | Housing estate elevator security and protection system |
| CN106429660A (en) * | 2016-11-24 | 2017-02-22 | 江苏旭云物联信息科技有限公司 | Intelligent elevator safety management system and method |
| CN106652293A (en) * | 2016-12-30 | 2017-05-10 | 安徽杰瑞信息科技有限公司 | Intelligent district online safety and protection monitoring system |
Non-Patent Citations (2)
| Title |
|---|
| DANIEL TRONIAK等: "Charlie Rides the Elevator–Integrating Vision, Navigation and Manipulation Towards Multi-Floor Robot Locomotion", 《2013 INTERNATIONAL CONFERENCE ON COMPUTER AND ROBOT VISION》 * |
| 马明: "面向住宅小区的电梯内人员检测和识别方法研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978390A (en) * | 2019-03-29 | 2019-07-05 | 嘉应学院 | Office efficiency assessment system and its method based on image recognition |
| CN110309768A (en) * | 2019-06-28 | 2019-10-08 | 上海眼控科技股份有限公司 | The staff's detection method and equipment of car test station |
| CN110430395A (en) * | 2019-07-19 | 2019-11-08 | 苏州维众数据技术有限公司 | Video data AI processing system and processing method |
| CN110490098A (en) * | 2019-07-31 | 2019-11-22 | 恒大智慧科技有限公司 | Smoking behavior automatic testing method, equipment and the readable storage medium storing program for executing of community user |
| CN110674717A (en) * | 2019-09-16 | 2020-01-10 | 合肥中科奔巴科技有限公司 | Smoking monitoring system based on gesture recognition |
| CN110674717B (en) * | 2019-09-16 | 2022-08-26 | 杭州奔巴慧视科技有限公司 | Smoking monitoring system based on gesture recognition |
| CN111435435A (en) * | 2019-12-10 | 2020-07-21 | 杭州海康威视数字技术股份有限公司 | Method, device, server and system for identifying pedestrians |
| CN111435435B (en) * | 2019-12-10 | 2024-06-07 | 杭州海康威视数字技术股份有限公司 | Companion identification method, device, server and system |
| CN111028109A (en) * | 2019-12-23 | 2020-04-17 | 重庆紫光华山智安科技有限公司 | Data processing method, device, server and storage medium |
| CN111488853A (en) * | 2020-04-23 | 2020-08-04 | 杨九妹 | Big data face recognition method and system for financial institution security system and robot |
| CN113688841A (en) * | 2020-05-19 | 2021-11-23 | 深圳市中兴***集成技术有限公司 | Intelligent security method based on image feature extraction |
| CN111967410A (en) * | 2020-08-20 | 2020-11-20 | 倪慧珍 | Property intelligent management and allocation system based on big data |
| CN111967410B (en) * | 2020-08-20 | 2021-03-23 | 王锐 | Property intelligent management and allocation system based on big data |
| CN112330514A (en) * | 2020-09-29 | 2021-02-05 | 佳都新太科技股份有限公司 | Community public security information evaluation method, device, equipment and storage medium |
| CN114548831A (en) * | 2022-04-21 | 2022-05-27 | 深圳市龙光云众智慧科技有限公司 | Evaluation report generation method and device, electronic equipment and storage medium |
| CN117437157A (en) * | 2023-10-16 | 2024-01-23 | 无锡远传融创科技有限公司 | Image processing method based on monitoring video data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109299683B (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299683A (en) | A kind of security protection assessment system based on recognition of face and behavior big data | |
| CN109271554B (en) | Intelligent video identification system and application thereof | |
| CN101404107A (en) | Internet bar monitoring and warning system based on human face recognition technology | |
| CN108961522A (en) | A kind of intelligent visitor system based on recognition of face | |
| CN107688775A (en) | Binocular camera recognition of face right discriminating system and method based on elevator scene | |
| CN205354056U (en) | Law enforcement record appearance with face identification | |
| CN110442742A (en) | Retrieve method and device, processor, electronic equipment and the storage medium of image | |
| CN101976356A (en) | Face identification method for surfing identification policy, and identification system thereof | |
| CN111429639A (en) | Artificial intelligence access control system | |
| CN108205896A (en) | A kind of Campus transport safety intelligence monitoring and controlling manages system | |
| CN103324911A (en) | Anti-cheating system based on face recognition | |
| CN102930243A (en) | Method and system for identifying facial information of special personnel | |
| CN210515326U (en) | Scenic spot ticket inspection system based on face AI recognition | |
| CN109993044A (en) | Telecommunication fraud identifying system, method, apparatus, electronic equipment and storage medium | |
| CN107516076A (en) | Portrait identification method and device | |
| CN108765935A (en) | A kind of pedestrian running red light is broken rules and regulations processing system and its method | |
| CN111047824A (en) | Indoor child nursing linkage control early warning method and system | |
| CN114898443A (en) | Face data acquisition method and device | |
| CN201134110Y (en) | Human face recognition system | |
| CN111091047B (en) | Living body detection method and device, server and face recognition equipment | |
| CN110324589A (en) | A kind of monitoring system and method for tourist attraction | |
| CN102096811A (en) | Intelligent face recognition module based on embedded platform, and recognition method thereof | |
| CN213338863U (en) | Offline authorization system of dynamic face access control | |
| CN204272303U (en) | A kind of secret protection supervisory control system | |
| CN202121706U (en) | Intelligent personnel monitoring 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Deng Jiaming Inventor after: Hou Yueen Inventor after: Chen Shouyi Inventor after: Cai Penghui Inventor after: Zeng Xiangyu Inventor after: Zhang Haixin Inventor before: Deng Jiaming Inventor before: Hou Yueen |