CN110428522A - A kind of intelligent safety and defence system of wisdom new city - Google Patents

A kind of intelligent safety and defence system of wisdom new city Download PDF

Info

Publication number
CN110428522A
CN110428522A CN201910669716.3A CN201910669716A CN110428522A CN 110428522 A CN110428522 A CN 110428522A CN 201910669716 A CN201910669716 A CN 201910669716A CN 110428522 A CN110428522 A CN 110428522A
Authority
CN
China
Prior art keywords
video
face
pixel
data
frame
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
Application number
CN201910669716.3A
Other languages
Chinese (zh)
Other versions
CN110428522B (en
Inventor
纪刚
周粉粉
周萌萌
周亚敏
商胜楠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Lianhe Chuangzhi Technology Co ltd
Original Assignee
Qingdao Lianhe Chuangzhi Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao Lianhe Chuangzhi Technology Co ltd filed Critical Qingdao Lianhe Chuangzhi Technology Co ltd
Priority to CN201910669716.3A priority Critical patent/CN110428522B/en
Publication of CN110428522A publication Critical patent/CN110428522A/en
Application granted granted Critical
Publication of CN110428522B publication Critical patent/CN110428522B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/71—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/215—Motion-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/269—Analysis of motion using gradient-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • 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
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • 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
    • 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
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/44—Event detection

Abstract

The invention belongs to security device manufacturing technology fields, and in particular to a kind of intelligent safety and defence system of wisdom new city.Access control system is the 4G face snap video camera disposed in the bayonet position of key area, to realize the face snap of ultra high density, in the case where not contacted directly with equipment, video camera acquires face dynamic menu, the facial image application face recognition algorithms detected to each frame with fixed frequency；4G face snap video camera embeds Intelligent human-face recognizer module, realizes recognition of face in video camera front end；The 4G face snap video camera of embedded Intelligent human-face recognizer module, the data of processing acquisition nearby on the front end picture pick-up device of edge side, it is serviced by providing proximal end in data source header side, application program is initiated in edge side, faster web services response can be generated, reduce time delay and transmission cost, reduces the transmission cost in broadband and the load of connection cloud storage.

Description

A kind of intelligent safety and defence system of wisdom new city
Technical field:
The invention belongs to security device manufacturing technology fields, and in particular to a kind of intelligent safety and defence system of wisdom new city, In Carry out that there is high accuracy in person recognition.
Background technique:
Video monitoring is the important component of safety and protection system, it is a kind of stronger integrated system of prevention ability. Each key area of wisdom new city, all deployment 4G video monitoring camera, realization social security and city are managed for emphasis place, region Intelligent HD video construction is managed, 4G IP Camera can support mobile phone, computer remote real-time video monitoring；Video monitoring with It is intuitive, accurate, timely abundant with the information content and is widely used in many occasions.In recent years, with computer, network and The rapid development of image procossing, transmission technology, there has also been significant progresses for Video Supervision Technique.Not with Video Supervision Technique Disconnected development, application is also more and more extensive, also, requirement of the user to video monitoring is also higher and higher, more and more at present User is desirable with video monitoring system and realizes long-range monitoring, the case where to understand monitored site in real time.Due to video monitoring System is the processing for video data, is related to the operations such as a series of algorithm calling, compression, transmission and massive store, right The requirement of server performance itself is very high, can become the bottleneck that efficiency improves.However, if not using above-mentioned front monitoring front-end and prison The one-to-one configuration mode of control terminal, the communication interface of open a front monitoring front-end and multiple monitor terminals, although can be opposite The load of some servers is reduced, but there are biggish security risks.Therefore, the present invention seeks design to provide a kind of wisdom new The intelligent safety and defence system in city can effectively improve video treatment effeciency, while improve the levels of precision of monitoring.
Summary of the invention:
It is an object of the invention to overcome drawbacks described above of the existing technology, seeks design and a kind of wisdom new city is provided Intelligent safety and defence system.
To achieve the goals above, a kind of intelligent safety and defence system of wisdom new city of the present invention passes through following technical side Case is realized: data acquisition subsystem includes access control system, video monitoring system；Data processing submodule includes that face is known Processing module is invaded in other module, abnormal behaviour analysis module, anomalous event monitoring modular, region；Cloud storage subsystem includes Video data module, smart machine data memory module；Alarm system includes abnormal alarm module；Public administration platform includes There is video management platform；According to preset strategy, each system carries out linkage collaborative work, and the present invention is by hardware device, video tube Platform, mass data, intelligence AI parser, connection cloud combine, and realize intelligent safety and defence system.
Data acquisition subsystem includes a variety of smart machines of access control system, video monitoring system and installation；
Access control system is the 4G face snap video camera disposed in the bayonet position of key area, to realize ultra high density Face snap, in the case where not contacted directly with equipment, video camera with fixed frequency acquire face dynamic menu, to each The facial image application face recognition algorithms that frame detects, the portrait picture of different angle is separated from background, is saved Into face database；Face recognition algorithms realize face characteristic extraction, Face datection, Face detection, face tracking, Characteristic Contrast, The process of face early warning；When portrait moves in the range of camera is shot, face recognition algorithms can automatically be carried out portrait It tracks, whether it is the same person that the registered portrait in the portrait and face database captured does comparison and verifies, because of face database In store the face picture of different angle, face recognition algorithms support side face and pitch angle detection, and with 99.99% face Recognition accuracy, face information compare successfully, and gate mouth is open, and the linkage of alarm system is realized in comparing result failure, prompt pre- Alert information, gate mouth can not be opened；
4G face snap video camera embeds Intelligent human-face recognizer module, realizes recognition of face, 4G in video camera front end Face snap video camera acquires face picture with fixed frequency, and Intelligent human-face recognizer module can filter a large amount of unrelated images letters Breath only retains the image comprising face picture and handle and image data is transferred to connection cloud by 4G network depositing Storage；
The 4G face snap video camera of embedded Intelligent human-face recognizer module, edge side (edge calculations are conducive to Real-time data analysis and intelligent processing, edge side are equivalent to a module, close to device end, realize data filtering and Analysis, can be improved the utilization efficiency of data, and intelligent video AI Processing Algorithm keeps whole system intelligent in conjunction with edge calculations It is higher) data of processing acquisition nearby on the picture pick-up device of front end, cloud is uploaded to without mass data, by data source header side Proximal end service is provided, application program is initiated in edge side, can generate faster web services response, reduce time delay and transmission Cost greatly reduces the transmission cost in broadband and the load of connection cloud storage；
Intelligent human-face recognizer module in access control system is provided with self-study module, can be with the hair of testing staff The variations such as type, the colour of skin, age dynamic updates face database, remains that the face template of database is newest, so as to every It is secondary correctly to identify face；
The 4G candid camera installed in access control system is equally applicable to the candid photograph to suspect vehicle, by the vehicle vehicle of candid photograph Board information, candid photograph time, candid photograph place etc. information upload to connection cloud by TCP network protocol and carry out unified storage, and Establish the personal information database in emphasis place；
Video monitoring system: the collected data of 4G network monitoring video camera are mostly non-structured, abundant These data are excavated it is necessary to carry out the structuring of video data processing, using video structural technology (including space-time dividing skill Art, Feature Extraction Technology, Identifying Technique of Object, deep learning technology), management is uniformly accessed into collected video resource, it is real Existing vehicle structure, pedestrian's structuring, human face structure, anomalous event occur to video monitoring regional, (region intrusion event is stumbled Line detecting event, crowd massing event, delay event of hovering) it is analyzed, by the intellectual analysis to video data, in magnanimity Key message is extracted in video pictures, the semantic description of style of writing of going forward side by side originally uses video preferably；
The video data volume is huge, if photographic technique uploads to cloud center, needs to occupy massive band width, and cloud is handled Data are also required to the regular hour, increase user's request response time, human body behavior are analyzed from monitor video and to exception Behavior carries out alarm and needs to have high requirement to the processing response time of video, is handled and is calculated beyond the clouds and is not existing It is real.
4G monitoring device front end bayonet is embedded with intelligent AI Processing Algorithm module, to carry out preliminary video image screening Processing enables magnanimity monitoring data to provide processing service nearby in edge side, screens out a large amount of unrelated video image informations；It will Monitor video data are transferred to connection cloud through 4G network by image data after treatment, and video management platform can be direct Cloud video data is accessed, entire video management center can carry out real time inspection to entire monitoring area and historical record is looked into It askes, understands monitoring area dynamic change；Video data is stored in corresponding structuring number after intelligence structureization processing, classification According to warehouse, such as human face photo database, facial feature database, behavior picture and property data base, vehicle image and feature database, Comprehensive different data warehouse and associated video segment warehouse can establish corresponding search engine, realize to all kinds of data The depth information in warehouse excavates, and improves the efficiency that data are handled beyond the clouds.
In order to analyze the moving target in video, and different types of target is classified to be put into inhomogeneity In the database of type, facilitate the intelligent retrieval in later period, need to video carry out structuring processing, to the moving target in video into Row segmentation uses, and specific implementation is as follows:
Data structured processing is carried out to video image using the flooding mechanism of unsupervised Video segmentation, in video sequence x ={ x1,...,xFF frame xi, initial prospect conspicuousness estimation is distributed on i ∈ { 1,2 ..., F }, using super-pixel by each frame Image is divided into a group node, and uses the semantic relation in the estimation of overall situation Neighborhood Graph and coded frame with interframe, is added by one Weigh row random neighborhood matrixIndicate global Neighborhood Graph, wherein N is the node total number in video.Execute each node Initialization prospect conspicuousness estimationDiffusion be by present node estimation and Neighborhood matrix G repetition matrix phase Multiply to realize, as the t times diffusing step vt=Gvt-1.Unsupervised Video Segmentation Neighborhood matrix G based on diffusion and just Beginningization v0As unique input；
Saliency foreground moving, u are indicated using uiAnd piRespectively indicate the conspicuousness prospect and picture in the i-th frame image Element individually handles each frame x to calculate conspicuousness estimationi, wherein i ∈ { 1,2 ..., F }, gives a frame image xi, Reference image vegetarian refreshments piIntensity value,It indicates in the i-th frame and i+1 frame with pixel piObject fortune is measured for unit Dynamic light stream vector, βiIndicate the boundary pixel set at frame i.
It is based onWithThe conspicuousness sport foreground in video frame i is calculated, appointing for the i-th frame image is each measured What pixel piWith boundary set βi.First distanceCalculate the pixel p observed on boundaryiWith public flow direction it Between minimal flow direction difference；Second distanceCalculate pixel piPath cost function between boundary pixel；WithAll capture pixel piSimilitude between the movement and background motion at place；
Calculate the difference in light stream direction: pixel p of the light stream direction difference at video frame iiAnd border betaiPublic light stream side To；Gather firstly, k-means is used to cluster boundary light stream direction for K, wherein k ∈ { 1 ..., K }, by cluster centre point It covers in set, is accomplished by
WhereinIndicate distribution pixel piTo the index in cluster k, r represents the series connection of all target variables；It will KiIt is updated to only comprising being assigned with the center more than 1/6 boundary pixel, in the case where giving cluster centre, by captured frame i Pixel piOptical-flow between the key light stream direction observed in the boundary frame i, is realized by following formula:
It calculates minimum potential barrier distance: calculating pixel p in video frame iiWith the minimum potential barrier distance D of boundary pixelbd,i, pass through Following formula is calculated:
WhereinIndicate path, edge aggregation connects pixel piWith boundary pixel s ∈ βi, by being calculated most in frame i Small spanning tree, edge weights wi(e) it is used to minimum spanning tree and potential barrier distance in calculation formula (1), by calculating adjacent pixel Maximum light stream direction difference value obtains:E=(pi,qi) it is two pixel ps of connectioniAnd qi Side；Minimum spanning tree is calculated using the method in 4 connection fields.The potential barrier distance of point-to-point transmission is calculated as point-to-point transmission minimum to generate The difference of the maximum side right and minimum side right on path is set, the minimum value conduct of potential barrier distance should between any point on the point and boundary The minimum potential barrier distance of point；
It is significant to calculate foreground moving type: by two distance metrics after normalizationWithTo obtain in video frame i The conspicuousness foreground target u of pixelationi；
Neighborhood Graph is calculated by calculating Neighborhood matrix G=T × E × V, wherein T is inter-frame information, and E is frame information, V is long-range (long-range) components.
Interframe timing information: interframe timing information is obtained by extracting Optic flow information, to prevent the light stream at moving boundaries Estimation inaccuracy, while self-consistent property, super-pixel is connected between the light stream vectors of adjacent interframe；To calculate light stream Neighborhood matrix T, continuous two needles image xiAnd xi+1, each frame image includes pixel piAnd pi+1, calculate the forward light of each pixel Flow field fi(pi) and backward optical flow field bi+1(pi+1), optical flow field obtained by calculation defines video frame xiIn pixel piBefore place To confidence scoreRealize that formula is as follows:
Backward confidence scoreIt is accomplished by
Wherein σ2For hyper parameter；Confidence score measures pixel piWith pass through pi+fi(pi) optical flow field followed into frame xi+1 Later as a result, and passing through pi+fi(pi)+bi+1(pi+fi(pi)) return to frame xiIn result；It is calculated using confidence score Two super-pixel s in frame i and frame i+1i,kAnd si+1,mBonding strength, realized by formula:
Wherein δ () indicates target function, | si,k| and | si+1,k| it represents in si,kAnd si+1,mThe pixel quantity at place；Above formula Middle first item compares with super-pixel si,kStart, si+1,mThe bonding strength of end be derived from si,kAnd si+1,mOverall strength；Section 2 It is similar to indicate；
Spatial information prevents the diffusion of vision edge in frame in frame, if do not separated by strong edge, allows information same It is propagated between adjacent super-pixel in one frame, for the space E for finding edge perception, uses the side of trained frame and interframe first Edge response calculates confidence score A (s) by the method summed to attenuation function using skirt response for all super-pixel, real It is now as follows:
Wherein G (p) ∈ [0,1] indicates the skirt response at pixel p, σwHyper parameter is represented with ε；
Edge, which is calculated, by above-mentioned marginal information perceives Neighborhood matrix E:
If si,kSpatially close to si+1,m, that is, super picture of the centre distance less than 1.5 times between two super-pixel Plain size square root；
If having visual similarity between two super-pixel, the long connection of view-based access control model similitude allow far from the time or It is propagated between super-pixel spatially, long connection propagation information can be made more efficient by neighbour's image, to calculate view Feel similarity matrix V, these super-pixel and super-pixel si,mRelationship is the closest, k nearest neighbor search is first carried out, to each Super-pixel si,m, s is found in the time range of r framei,mK arest neighbors, feature space using Euclidean distance calculate The distance between super-pixel；
The feature f (s) of super-pixel is calculated by connecting LBP the and RGB histogram of pixel in the super-pixel being calculated, It simultaneously further include the x and y coordinates of HOG feature and super-pixel center；
By defining visual similarity matrix, make super-pixel si,mK arest neighbors pass through N (si,m) reference, visual similarity Matrix is expressed as:
Wherein σ is hyper parameter, and f (s) indicates the character representation of super-pixel s；
After carrying out structuring processing to multi-path monitoring video image, a large amount of hashes in image are not only reduced, are obtained Useful data, and reduce the load capacity of cloud storing data.In the accuracy of target identification, due to human body behavior Non-rigid characteristic so that behavior have diversity and variability, the image processing algorithm can to Different Individual generate it is same A kind of human body behavior has relatively high accuracy, enables using in practice.In order to meet actual application demand, depending on The processing speed of frequency image 30 frame images of processing per second, can achieve the effect that quasi real time.
The foreground target detected by algorithm needs to judge prospect mesh by IOU and accuracy formula evaluation index The IOU ratio of target accuracy, target and realistic objective that algorithm detects is bigger, and the foreground detection effect for representing the algorithm is got over Good, accuracy is higher.
Multi-channel video monitor picture can be by video management platform real time inspection, to the key area in different monitoring range Different grades of fence is set as security area, is calculated per the insertion intelligence AI Human bodys' response of monitoring camera front end all the way Whether the fence of method analysis monitored picture setting there are abnormal vehicle, pet, residue, the personnel that cross the border, non-working person It, will be before analysis treated result feedback to management platform after the processing of AI Human bodys' response algorithmic preliminaries Deng invasion object End, if detecting abnormal behaviour (fall down, hover) and anomalous event (assemble, fight, residue, fence cross the border), video letter Automatic spring is abnormal the picture of behavior and anomalous event by breath management platform, and carries out video recording storage, and administrative staff verify The case where whether warning message belongs to erroneous judgement, however, it is determined that be abnormal, staff is handled in time；Video monitoring system and report Alert system links, and by the way of the automatic spring warning message in monitored picture, had both improved security personnel and has handled police The correctness of feelings can also solve a case rapidly for security personnel and provide firsthand information and evidence；
Video background service provides the video monitoring service function based on cloud computing, and passes through protocol interface and external call Person communicates, while 4G monitoring camera can support mobile phone, computer remote to check real-time video monitoring picture；
4G monitors photography/videography machine for complex application context, software and algorithm that can be different according to displaying on-demand loading, By cooperateing between multi-feature extraction and identification, multiple-camera, the collaboration between cloud is held to double up intellectual analysis efficiency, it is built-in Realtime graphic quality testing and evaluation of properties, and have self perception and scene adaptability learning ability, allow algorithm and application not Disconnected iteration and evolution；
A variety of smart machines include intelligent closestool sitting alarm set, fuel gas alarm, infrared detector, interior UWB fixed A variety of smart machines such as position system；Intelligent closestool sitting alarm set has sitting reminding module, and to going to the toilet, sitting personnel are carried out Abnormity prompt, to prevent accident occurs；Fuel gas alarm measures indoor smokescope, if smokescope is beyond default Value, alarm sound an alarm；IR intrusion detector carries out infrared wiring to great security protection region, when in the region, appearance can be moved Infrared ray will be offended when object, infrared probe detects exception, issues alarm, a variety of intelligent bases of indoor locating system arrangement It stands, personnel, which carry positioning label, can determine the position of personnel；
Data processing module: data processing system carries out collected data through embedded intelligent algorithm to initial data Screening Treatment filters irrelevant information, completes to retain useful letter to various treatment processes such as the processing, arrangement, calculating of information Breath, and stored, information is uploaded to by connection cloud by 4G network.
Connection cloud: connection cloud mainly stores the information of various types of data formats, including monitor video data, Intelligent AI algorithm (Intelligent human-face recognizer module, abnormal behaviour recognizer, anomalous event recognizer), database purchase Information (various smart machine basic information managements, face information database, the storage of various warning messages)；Through each smart machine After edge data processing, connection cloud is uploaded to, connection cloud stores a plurality of types of data, carries out cloud reception by 4G network Information from different intelligent equipment, a variety of data are unified in the storage of connection cloud, facilitate the retrieval and inquiry in later period.
Alarm module:
Local area network is formed by router between smart machine in representative region scene, includes to enclose to monitoring area Region including wall, important entrance, elevator, corridor, strategic road, Underground Garage, alarm system need and IR intrusion detector, cigarette Sense alarm, access control system and monitoring system link, if detecting exception, alarm song, weight immediately occurs by loudspeaker The different fence grades of point monitoring area setting, detect region invader or fence cross the border etc. abnormal behaviours and When anomalous event, there is pop-up alarm, gate inhibition's recognition of face of important entrance setting in video management platform, once reach alarm Gate inhibition's condition, will automatic trigger alarm system.
Video management platform: management platform realizes the intelligent management to whole system, connects connection cloud, multitude of video number It is stored in connection cloud according to the data of, smart machine acquisition, video management platform and connection cloud communicate to connect, and are able to carry out It checks, video management platform includes following module:
1) basic information management: the personnel in key area are managed；
2) equipment state management includes the intellective video monitoring device of installation, infrared alarm equipment, gas alarm equipment, determines The working conditions such as position equipment are managed, and are configured to the attribute of equipment, are realized that the additions and deletions of equipment change and look into, the database of use For MySQL；
3) it region invasion management: alarms immediately once triggering in the region of setting；
4) abnormal behaviour/incident management: saving type, place and time that the abnormal behaviour/event occurred every time occurs, Convenient for statistics；
5) alarm indication and confirmation: the alarm screen of video monitoring management platform pop-up needs staff to confirm, The case where to prevent there is erroneous detection or missing inspection；
6) historical record is inquired: including monitor video inquiry, alarm logging inquiry；To the alarm logging of preservation with the time, The conditions such as event type, behavior type, scene are inquired；
7) recognition of face is shown: showing the face picture that the access control system of entrance is captured, the facial image of acquisition and people Face picture in face library is compared；
8) fence is arranged: different fence grades is arranged in different zones；
9) real-time video monitoring: the module has the function of adopting, passes, deposits, seeing, obtains per the video flowing monitored all the way Location transmits camera acquired image data by 4G network, and data are stored in connection cloud, can be appointed in front end Wherein monitoring carries out real-time display to meaning calling all the way, and to original video picture by being shown after intelligence AI algorithm process by switching Show button, the monitored picture that can show that treated, and behavior label and behavior accuracy to people in frame out, real-time video are drawn Exception is detected in face, pops up abnormal alarm dialog box, while saving abnormal picture, waits relevant staff to handle abnormal； 4G camera hardware is carried in the front end of video management platform, collected data is transmitted to background video management platform, in real time Monitor video picture, the AI intelligent algorithm of rear end can analyze the human body behavior in video.
Compared with prior art, the present invention what is obtained has the beneficial effect that:
(1) video data structure that monitoring camera can acquire camera in the intelligent AI algorithm that marginal end is embedded in Processing is different types of target, facilitates the inquiry of user and transfers.Since data are first handled in marginal end, screen out a large amount of The data of redundancy, then it is transferred to cloud, greatly reduce the load pressure of cloud data.
(2) using the methods of video segmentation of conspicuousness movement guidance in image, mesh is realized in the segmentation to foreground target Target subdivision, compared to other foreground object segmentation methods, video of this method in the case where handling complex background and nonrigid There is significant effect when moving target.
(3) this method is different from supervised learning method, does not need to select great amount of samples and mark interested in sample Target, this method oneself can learn the target divided the image into out and sort out.
Summary, body design is skillfully constructed, and safe and convenient to use, image processing efficiency and accuracy rate greatly improve, and answers With environmental-friendly, wide market.
Detailed description of the invention:
Fig. 1 is image processing flow schematic diagram of the present invention.
Fig. 2 is video monitoring equipment of the present invention and connection control planning schematic illustration.
Fig. 3 is video management platform feature schematic illustration of the present invention.
Fig. 4 is overall topological structure schematic illustration of the present invention.
Fig. 5 is function structure schematic illustration of the present invention.
Specific embodiment:
The invention will be further described by way of example and in conjunction with the accompanying drawings.
Embodiment 1:
A kind of intelligent safety and defence system for wisdom new city that the present embodiment is related to is accomplished in that data acquisition system System, includes access control system, video monitoring system；Data processing submodule includes face recognition module, abnormal behaviour analysis Processing module is invaded in module, anomalous event monitoring modular, region；Cloud storage subsystem includes video data module, intelligently sets Standby data memory module；Alarm system includes abnormal alarm module；Public administration platform includes video management platform；According to Preset strategy, each system carry out linkage collaborative work, and the present invention is by hardware device, video management platform, mass data, intelligence AI parser, connection cloud combine, and realize intelligent safety and defence system.
Data acquisition subsystem includes a variety of smart machines of access control system, video monitoring system and installation；
Access control system is the 4G face snap video camera disposed in the bayonet position of key area, to realize ultra high density Face snap, in the case where not contacted directly with equipment, video camera with fixed frequency acquire face dynamic menu, to each The facial image application face recognition algorithms that frame detects, the portrait picture of different angle is separated from background, is saved Into face database；Face recognition algorithms realize face characteristic extraction, Face datection, Face detection, face tracking, Characteristic Contrast, The process of face early warning；When portrait moves in the range of camera is shot, face recognition algorithms can automatically be carried out portrait It tracks, whether it is the same person that the registered portrait in the portrait and face database captured does comparison and verifies, because of face database In store the face picture of different angle, face recognition algorithms support side face and pitch angle detection, and with 99.99% face Recognition accuracy, face information compare successfully, and gate mouth is open, and the linkage of alarm system is realized in comparing result failure, prompt pre- Alert information, gate mouth can not be opened；
4G face snap video camera embeds Intelligent human-face recognizer module, realizes recognition of face, 4G in video camera front end Face snap video camera acquires face picture with fixed frequency, and Intelligent human-face recognizer module can filter a large amount of unrelated images letters Breath only retains the image comprising face picture and handle and image data is transferred to connection cloud by 4G network depositing Storage；
The 4G face snap video camera of embedded Intelligent human-face recognizer module, edge side (edge calculations are conducive to Real-time data analysis and intelligent processing, edge side are equivalent to a module, close to device end, realize data filtering and Analysis, can be improved the utilization efficiency of data, and intelligent video AI Processing Algorithm keeps whole system intelligent in conjunction with edge calculations It is higher) data of processing acquisition nearby on the picture pick-up device of front end, cloud is uploaded to without mass data, by data source header side Proximal end service is provided, application program is initiated in edge side, can generate faster web services response, reduce time delay and transmission Cost greatly reduces the transmission cost in broadband and the load of connection cloud storage；
Intelligent human-face recognizer module in access control system is provided with self-study module, can be with the hair of testing staff The variations such as type, the colour of skin, age dynamic updates face database, remains that the face template of database is newest, so as to every It is secondary correctly to identify face；
The 4G candid camera installed in access control system is equally applicable to the candid photograph to suspect vehicle, by the vehicle vehicle of candid photograph Board information, candid photograph time, candid photograph place etc. information upload to connection cloud by TCP network protocol and carry out unified storage, and Establish the personal information database in emphasis place；
Video monitoring system: the collected data of 4G network monitoring video camera are mostly non-structured, abundant These data are excavated it is necessary to carry out the structuring of video data processing, using video structural technology (including space-time dividing skill Art, Feature Extraction Technology, Identifying Technique of Object, deep learning technology), management is uniformly accessed into collected video resource, it is real Existing vehicle structure, pedestrian's structuring, human face structure, anomalous event occur to video monitoring regional, (region intrusion event is stumbled Line detecting event, crowd massing event, delay event of hovering) it is analyzed, by the intellectual analysis to video data, in magnanimity Key message is extracted in video pictures, the semantic description of style of writing of going forward side by side originally uses video preferably；
The video data volume is huge, if photographic technique uploads to cloud center, needs to occupy massive band width, and cloud is handled Data are also required to the regular hour, increase user's request response time, human body behavior are analyzed from monitor video and to exception Behavior carries out alarm and needs to have high requirement to the processing response time of video, is handled and is calculated beyond the clouds and is not existing It is real.
4G monitoring device front end bayonet is embedded with intelligent AI Processing Algorithm module, to carry out preliminary video image screening Processing enables magnanimity monitoring data to provide processing service nearby in edge side, screens out a large amount of unrelated video image informations；It will Monitor video data are transferred to connection cloud through 4G network by image data after treatment, and video management platform can be direct Cloud video data is accessed, entire video management center can carry out real time inspection to entire monitoring area and historical record is looked into It askes, understands monitoring area dynamic change；Video data is stored in corresponding structuring number after intelligence structureization processing, classification According to warehouse, such as human face photo database, facial feature database, behavior picture and property data base, vehicle image and feature database, Comprehensive different data warehouse and associated video segment warehouse can establish corresponding search engine, realize to all kinds of data The depth information in warehouse excavates, and improves the efficiency that data are handled beyond the clouds.
In order to analyze the moving target in video, and different types of target is classified to be put into inhomogeneity In the database of type, facilitate the intelligent retrieval in later period, need to video carry out structuring processing, to the moving target in video into Row segmentation uses, and specific implementation is as follows:
Data structured processing is carried out to video image using the flooding mechanism of unsupervised Video segmentation, in video sequence x ={ x1,...,xFF frame xi, initial prospect conspicuousness estimation is distributed on i ∈ { 1,2 ..., F }, using super-pixel by each frame Image is divided into a group node, and uses the semantic relation in the estimation of overall situation Neighborhood Graph and coded frame with interframe, is added by one Weigh row random neighborhood matrixIndicate global Neighborhood Graph, wherein N is the node total number in video.Execute each node Initialization prospect conspicuousness estimationDiffusion be by present node estimation and Neighborhood matrix G repetition matrix phase Multiply to realize, as the t times diffusing step vt=Gvt-1.Unsupervised Video Segmentation Neighborhood matrix G based on diffusion and just Beginningization v0As unique input；
Saliency foreground moving, u are indicated using uiAnd piRespectively indicate the conspicuousness prospect and picture in the i-th frame image Element individually handles each frame x to calculate conspicuousness estimationi, wherein i ∈ { 1,2 ..., F }, gives a frame image xi, Reference image vegetarian refreshments piIntensity value,It indicates in the i-th frame and i+1 frame with pixel piObject fortune is measured for unit Dynamic light stream vector, βiIndicate the boundary pixel set at frame i.
It is based onWithThe conspicuousness sport foreground in video frame i is calculated, appointing for the i-th frame image is each measured What pixel piWith boundary set βi.First distanceCalculate the pixel p observed on boundaryiWith public flow direction it Between minimal flow direction difference；Second distanceCalculate pixel piPath cost function between boundary pixel；WithAll capture pixel piSimilitude between the movement and background motion at place；
Calculate the difference in light stream direction: pixel p of the light stream direction difference at video frame iiAnd border betaiPublic light stream side To；Gather firstly, k-means is used to cluster boundary light stream direction for K, wherein k ∈ { 1 ..., K }, by cluster centre point It covers in set, is accomplished by
WhereinIndicate distribution pixel piTo the index in cluster k, r represents the series connection of all target variables；It will KiIt is updated to only comprising being assigned with the center more than 1/6 boundary pixel, in the case where giving cluster centre, by captured frame i Pixel piOptical-flow between the key light stream direction observed in the boundary frame i, is realized by following formula:
It calculates minimum potential barrier distance: calculating pixel p in video frame iiWith the minimum potential barrier distance D of boundary pixelbd,i, pass through Following formula is calculated:
WhereinIndicate path, edge aggregation connects pixel piWith boundary pixel s ∈ βi, by being calculated most in frame i Small spanning tree, edge weights wi(e) it is used to minimum spanning tree and potential barrier distance in calculation formula (1), by calculating adjacent pixel Maximum light stream direction difference value obtains:
E=(pi,qi) it is two pixel ps of connectioniAnd qiSide；Using 4 connections The method in field calculates minimum spanning tree.The potential barrier distance of point-to-point transmission is calculated as the maximum on point-to-point transmission minimum spanning tree path The difference of side right and minimum side right, on the point and boundary between any point potential barrier distance minimum value as the point minimum potential barrier away from From；
It is significant to calculate foreground moving type: by two distance metrics after normalizationWithTo obtain in video frame i The conspicuousness foreground target u of pixelationi；
Neighborhood Graph is calculated by calculating Neighborhood matrix G=T × E × V, wherein T is inter-frame information, and E is frame information, V is long-range (long-range) components.
Interframe timing information: interframe timing information is obtained by extracting Optic flow information, to prevent the light stream at moving boundaries Estimation inaccuracy, while self-consistent property, super-pixel is connected between the light stream vectors of adjacent interframe；To calculate light stream Neighborhood matrix T, continuous two needles image xiAnd xi+1, each frame image includes pixel piAnd pi+1, calculate the forward light of each pixel Flow field fi(pi) and backward optical flow field bi+1(pi+1), optical flow field obtained by calculation defines video frame xiIn pixel piBefore place To confidence scoreRealize that formula is as follows:
Backward confidence scoreIt is accomplished by
Wherein σ2For hyper parameter；Confidence score measures pixel piWith pass through pi+fi(pi) optical flow field followed into frame xi+1 Later as a result, and passing through pi+fi(pi)+bi+1(pi+fi(pi)) return to frame xiIn result；It is calculated using confidence score Two super-pixel s in frame i and frame i+1i,kAnd si+1,mBonding strength, realized by formula:
Wherein δ () indicates target function, | si,k| and | si+1,k| it represents in si,kAnd si+1,mThe pixel quantity at place；Above formula Middle first item compares with super-pixel si,kStart, si+1,mThe bonding strength of end be derived from si,kAnd si+1,mOverall strength；Section 2 It is similar to indicate；
Spatial information prevents the diffusion of vision edge in frame in frame, if do not separated by strong edge, allows information same It is propagated between adjacent super-pixel in one frame, for the space E for finding edge perception, uses the side of trained frame and interframe first Edge response calculates confidence score A (s) by the method summed to attenuation function using skirt response for all super-pixel, real It is now as follows:
Wherein G (p) ∈ [0,1] indicates the skirt response at pixel p, σwHyper parameter is represented with ε；
Edge, which is calculated, by above-mentioned marginal information perceives Neighborhood matrix E:
If si,kSpatially close to si+1,m, that is, super picture of the centre distance less than 1.5 times between two super-pixel Plain size square root；
If having visual similarity between two super-pixel, the long connection of view-based access control model similitude allow far from the time or It is propagated between super-pixel spatially, long connection propagation information can be made more efficient by neighbour's image, to calculate view Feel similarity matrix V, these super-pixel and super-pixel si,mRelationship is the closest, k nearest neighbor search is first carried out, to each Super-pixel si,m, s is found in the time range of r framei,mK arest neighbors, feature space using Euclidean distance calculate The distance between super-pixel；
The feature f (s) of super-pixel is calculated by connecting LBP the and RGB histogram of pixel in the super-pixel being calculated, It simultaneously further include the x and y coordinates of HOG feature and super-pixel center；
By defining visual similarity matrix, make super-pixel si,mK arest neighbors pass through N (si,m) reference, visual similarity Matrix is expressed as:
Wherein σ is hyper parameter, and f (s) indicates the character representation of super-pixel s；
After carrying out structuring processing to multi-path monitoring video image, a large amount of hashes in image are not only reduced, are obtained Useful data, and reduce the load capacity of cloud storing data.In the accuracy of target identification, due to human body behavior Non-rigid characteristic so that behavior have diversity and variability, the image processing algorithm can to Different Individual generate it is same A kind of human body behavior has relatively high accuracy, enables using in practice.In order to meet actual application demand, depending on The processing speed of frequency image 30 frame images of processing per second, can achieve the effect that quasi real time.
The foreground target detected by algorithm needs to judge prospect mesh by IOU and accuracy formula evaluation index The IOU ratio of target accuracy, target and realistic objective that algorithm detects is bigger, and the foreground detection effect for representing the algorithm is got over Good, accuracy is higher.
Multi-channel video monitor picture can be by video management platform real time inspection, to the key area in different monitoring range Different grades of fence is set as security area, is calculated per the insertion intelligence AI Human bodys' response of monitoring camera front end all the way Whether the fence of method analysis monitored picture setting there are abnormal vehicle, pet, residue, the personnel that cross the border, non-working person It, will be before analysis treated result feedback to management platform after the processing of AI Human bodys' response algorithmic preliminaries Deng invasion object End, if detecting abnormal behaviour (fall down, hover) and anomalous event (assemble, fight, residue, fence cross the border), video letter Automatic spring is abnormal the picture of behavior and anomalous event by breath management platform, and carries out video recording storage, and administrative staff verify The case where whether warning message belongs to erroneous judgement, however, it is determined that be abnormal, staff is handled in time；Video monitoring system and report Alert system links, and by the way of the automatic spring warning message in monitored picture, had both improved security personnel and has handled police The correctness of feelings can also solve a case rapidly for security personnel and provide firsthand information and evidence；
Video background service provides the video monitoring service function based on cloud computing, and passes through protocol interface and external call Person communicates, while 4G monitoring camera can support mobile phone, computer remote to check real-time video monitoring picture；
4G monitors photography/videography machine for complex application context, software and algorithm that can be different according to displaying on-demand loading, By cooperateing between multi-feature extraction and identification, multiple-camera, the collaboration between cloud is held to double up intellectual analysis efficiency, it is built-in Realtime graphic quality testing and evaluation of properties, and have self perception and scene adaptability learning ability, allow algorithm and application not Disconnected iteration and evolution；
A variety of smart machines include intelligent closestool sitting alarm set, fuel gas alarm, infrared detector, interior UWB fixed A variety of smart machines such as position system；Intelligent closestool sitting alarm set has sitting reminding module, and to going to the toilet, sitting personnel are carried out Abnormity prompt, to prevent accident occurs；Fuel gas alarm measures indoor smokescope, if smokescope is beyond default Value, alarm sound an alarm；IR intrusion detector carries out infrared wiring to great security protection region, when in the region, appearance can be moved Infrared ray will be offended when object, infrared probe detects exception, issues alarm, a variety of intelligent bases of indoor locating system arrangement It stands, personnel, which carry positioning label, can determine the position of personnel；
Data processing module: data processing system carries out collected data through embedded intelligent algorithm to initial data Screening Treatment filters irrelevant information, completes to retain useful letter to various treatment processes such as the processing, arrangement, calculating of information Breath, and stored, information is uploaded to by connection cloud by 4G network.
Connection cloud: connection cloud mainly stores the information of various types of data formats, including monitor video data, Intelligent AI algorithm (Intelligent human-face recognizer module, abnormal behaviour recognizer, anomalous event recognizer), database purchase Information (various smart machine basic information managements, face information database, the storage of various warning messages)；Through each smart machine After edge data processing, connection cloud is uploaded to, connection cloud stores a plurality of types of data, carries out cloud reception by 4G network Information from different intelligent equipment, a variety of data are unified in the storage of connection cloud, facilitate the retrieval and inquiry in later period.
Alarm module:
Local area network is formed by router between smart machine in representative region scene, includes to enclose to monitoring area Region including wall, important entrance, elevator, corridor, strategic road, Underground Garage, alarm system need and IR intrusion detector, cigarette Sense alarm, access control system and monitoring system link, if detecting exception, alarm song, weight immediately occurs by loudspeaker The different fence grades of point monitoring area setting, detect region invader or fence cross the border etc. abnormal behaviours and When anomalous event, there is pop-up alarm, gate inhibition's recognition of face of important entrance setting in video management platform, once reach alarm Gate inhibition's condition, will automatic trigger alarm system.
Video management platform: management platform realizes the intelligent management to whole system, connects connection cloud, multitude of video number It is stored in connection cloud according to the data of, smart machine acquisition, video management platform and connection cloud communicate to connect, and are able to carry out It checks, video management platform includes following module:
1) basic information management: the personnel in key area are managed；
2) equipment state management includes the intellective video monitoring device of installation, infrared alarm equipment, gas alarm equipment, determines The working conditions such as position equipment are managed, and are configured to the attribute of equipment, are realized that the additions and deletions of equipment change and look into, the database of use For MySQL；
3) it region invasion management: alarms immediately once triggering in the region of setting；
4) abnormal behaviour/incident management: saving type, place and time that the abnormal behaviour/event occurred every time occurs, Convenient for statistics；
5) alarm indication and confirmation: the alarm screen of video monitoring management platform pop-up needs staff to confirm, The case where to prevent there is erroneous detection or missing inspection；
6) historical record is inquired: including monitor video inquiry, alarm logging inquiry；To the alarm logging of preservation with the time, The conditions such as event type, behavior type, scene are inquired；
7) recognition of face is shown: showing the face picture that the access control system of entrance is captured, the facial image of acquisition and people Face picture in face library is compared；
8) fence is arranged: different fence grades is arranged in different zones；
9) real-time video monitoring: the module has the function of adopting, passes, deposits, seeing, obtains per the video flowing monitored all the way Location transmits camera acquired image data by 4G network, and data are stored in connection cloud, can be appointed in front end Wherein monitoring carries out real-time display to meaning calling all the way, and to original video picture by being shown after intelligence AI algorithm process by switching Show button, the monitored picture that can show that treated, and behavior label and behavior accuracy to people in frame out, real-time video are drawn Exception is detected in face, pops up abnormal alarm dialog box, while saving abnormal picture, waits relevant staff to handle abnormal； 4G camera hardware is carried in the front end of video management platform, collected data is transmitted to background video management platform, in real time Monitor video picture, the AI intelligent algorithm of rear end can analyze the human body behavior in video.

Claims (2)

1. a kind of intelligent safety and defence system of wisdom new city, it is characterised in that be achieved through the following technical solutions: data acquisition system System, includes access control system, video monitoring system；Data processing submodule includes face recognition module, abnormal behaviour analysis Processing module is invaded in module, anomalous event monitoring modular, region；Cloud storage subsystem includes video data module, intelligently sets Standby data memory module；Alarm system includes abnormal alarm module；Public administration platform includes video management platform；According to Preset strategy, each system carry out linkage collaborative work, and the present invention is by hardware device, video management platform, mass data, intelligence AI parser, connection cloud combine, and realize intelligent safety and defence system；
Data acquisition subsystem includes a variety of smart machines of access control system, video monitoring system and installation；
Access control system is the 4G face snap video camera disposed in the bayonet position of key area, to realize the people of ultra high density Face is captured, and in the case where not contacting directly with equipment, video camera acquires face dynamic menu with fixed frequency, is examined to each frame The facial image application face recognition algorithms measured, the portrait picture of different angle is separated from background, is saved in people In face library；Face recognition algorithms realize face characteristic extraction, Face datection, Face detection, face tracking, Characteristic Contrast, face The process of early warning；When portrait moves in the range of camera is shot, face recognition algorithms can automatically be tracked portrait, Whether it is the same person that the registered portrait in the portrait and face database captured does comparison and verifies, because storing in face database The face picture of different angle, face recognition algorithms support side face and pitch angle detection, and quasi- with 99.99% recognition of face True rate, face information compare successfully, and gate mouth is open, and the linkage of alarm system is realized in comparing result failure, prompt early warning letter Breath, gate mouth can not be opened；
4G face snap video camera embeds Intelligent human-face recognizer module, realizes recognition of face, 4G face in video camera front end Candid camera acquires face picture with fixed frequency, and Intelligent human-face recognizer module can filter a large amount of unrelated images information, Only retain the image comprising face picture handle and image data is transferred to connection cloud by 4G network storing；
The 4G face snap video camera of embedded Intelligent human-face recognizer module, on the front end picture pick-up device of edge side just nearby Reason acquisition data, upload to cloud without mass data, are serviced by providing proximal end in data source header side, application program is on side Edge side is initiated, and can be generated faster web services response, be reduced time delay and transmission cost, greatly reduce the transmission in broadband The load of cost and the storage of connection cloud；Edge calculations are conducive to real-time data analysis and intelligent processing, edge side phase When realizing the filtering and analysis of data close to device end in a module, the utilization efficiency of data can be improved, intelligence regards Frequency AI Processing Algorithm keeps whole system intelligence higher in conjunction with edge calculations；
Intelligent human-face recognizer module in access control system is provided with self-study module, being capable of hair style with testing staff, skin The variations such as color, age dynamic updates face database, remains that the face template of database is newest, so as to every time can Correct identification face；
Video monitoring system: video structural technology is used, mainly includes space-time dividing technology, Feature Extraction Technology, object Identification technology, deep learning technology are uniformly accessed into management to collected video resource, realize vehicle structure, pedestrian's structure Change, human face structure, anomalous event occurs to video monitoring regional and analyze, pass through the intellectual analysis to video data, In Key message is extracted in video pictures, the semantic description of style of writing of going forward side by side originally；
4G monitoring device front end bayonet is embedded with intelligent AI Processing Algorithm module, to carry out at preliminary video image screening Reason enables monitoring data to provide processing service nearby in edge side, screens out a large amount of unrelated video image informations；It will be by place Monitor video data are transferred to connection cloud through 4G network by the image data after reason, and video management platform can directly access cloud Video data is held, entire video management center real time inspection can be carried out to entire monitoring area and historical record is inquired, and understands Monitoring area dynamic change；Video data is stored in corresponding structural data warehouse after intelligence structureization processing, classification, It include human face photo database, facial feature database, behavior picture and property data base, vehicle image and feature database, it is comprehensive Corresponding search engine can be established by closing different data warehouse and associated video segment warehouse, be realized to all kinds of data bins The depth information in library excavates, and improves the efficiency that data are handled beyond the clouds；
Multi-channel video monitor picture can set the key area in different monitoring range by video management platform real time inspection Different grades of fence is set as security area, is embedded in intelligence AI Human bodys' response algorithm per monitoring camera front end all the way Whether the fence of analysis monitored picture setting there is abnormal vehicle, pet, residue, the personnel that cross the border, non-working person enter Invade, after the processing of AI Human bodys' response algorithmic preliminaries, will analysis treated result feedback to management platform front end, if detection To abnormal behaviour and anomalous event, automatic spring is abnormal the picture of behavior and anomalous event by video information management platform, And carry out video recording storage, administrative staff verify the case where whether warning message belongs to erroneous judgement, however, it is determined that be abnormal, staff and Shi Jinhang processing；Video monitoring system links with alarm system, using the automatic spring warning message in monitored picture Mode had both improved the correctness that security personnel handles alert, can also solve a case rapidly for security personnel and provide firsthand information and card According to；
Video background service provides the video monitoring service function based on cloud computing, and by protocol interface and external callers into Row communication, while 4G monitoring camera can support mobile phone, computer remote to check real-time video monitoring picture；
4G monitors photography/videography machine for complex application context, and software and algorithm that can be different according to displaying on-demand loading pass through Cooperateing with, the collaboration between cloud held to double up intellectual analysis efficiency between multi-feature extraction and identification, multiple-camera, it is built-in real-time Picture quality detection and evaluation of properties, and have self perception and scene adaptability learning ability, make algorithm and application continuous repeatedly Generation and evolution；
A variety of smart machines include intelligent closestool sitting alarm set, fuel gas alarm, infrared detector, interior UWB positioning system A variety of smart machines such as system；Intelligent closestool sitting alarm set has sitting reminding module, carries out to the sitting personnel that go to the toilet abnormal It reminds, to prevent accident occurs；Fuel gas alarm measures indoor smokescope, if smokescope exceeds preset value, Alarm sounds an alarm；IR intrusion detector carries out infrared wiring to great security protection region, when the object that can be moved in region appearance Infrared ray will be offended when body, infrared probe detects exception, issues alarm, a variety of intelligent bases of indoor locating system arrangement It stands, personnel, which carry positioning label, can determine the position of personnel；
Data processing module: data processing system screens collected data through embedded intelligent algorithm to initial data Processing filters irrelevant information, completes to retain useful information to various treatment processes such as the processing, arrangement, calculating of information, and It is stored, information is uploaded to by connection cloud by 4G network；
Connection cloud: connection cloud mainly stores the information of various types of data formats, including monitor video data, intelligence AI algorithm (Intelligent human-face recognizer module, abnormal behaviour recognizer, anomalous event recognizer), database stores information (various smart machine basic information managements, face information database, the storage of various warning messages)；Edge through each smart machine After data processing, connection cloud is uploaded to, connection cloud stores a plurality of types of data, carries out cloud reception by 4G network and comes from The information of different intelligent equipment, a variety of data are unified in the storage of connection cloud, facilitate the retrieval and inquiry in later period；
Alarm module:
Local area network is formed by router between smart machine in representative region scene, includes enclosure wall, again to monitoring area The region including entrance, elevator, corridor, strategic road, Underground Garage is wanted, alarm system needs and IR intrusion detector, cigarette sense report Alert device, access control system and monitoring system link, if detecting exception, alarm song, emphasis prison immediately occurs by loudspeaker The different fence grades for controlling region setting detect that region invader or fence such as cross the border at abnormal behaviours and the exception When event, there is pop-up alarm, gate inhibition's recognition of face of important entrance setting in video management platform, once reach alarm gate inhibition Condition, will automatic trigger alarm system；
Video management platform: intelligent management of the management platform realization to whole system, connection connection cloud, multitude of video data, The data of smart machine acquisition are stored in connection cloud, and video management platform and connection cloud communicate to connect, and are able to carry out and look into It sees, video management platform includes following module:
1) basic information management: the personnel in key area are managed；
2) equipment state management include installation intellective video monitoring device, infrared alarm equipment, gas alarm equipment, positioning set The working conditions such as standby are managed, and are configured to the attribute of equipment, are realized that the additions and deletions of equipment change and look into, the database used for MySQL；
3) it region invasion management: alarms immediately once triggering in the region of setting；
4) abnormal behaviour/incident management: type, place and time that the abnormal behaviour/event occurred every time occurs are saved, is convenient for Statistics；
5) alarm indication and confirmation: the alarm screen of video monitoring management platform pop-up needs staff to confirm, to prevent There is the case where erroneous detection or missing inspection；
6) historical record is inquired: including monitor video inquiry, alarm logging inquiry；To the alarm logging of preservation with time, event The conditions such as type, behavior type, scene are inquired；
7) recognition of face is shown: showing the face picture that the access control system of entrance is captured, the facial image and face database of acquisition In face picture be compared；
8) fence is arranged: different fence grades is arranged in different zones；
9) real-time video monitoring: the module has the function of adopting, passes, deposits, seeing, obtains per the video flowing address monitored all the way, will Camera acquired image data are transmitted by 4G network, and data are stored in connection cloud, can arbitrarily be adjusted in front end With wherein monitoring carries out real-time display all the way, and to original video picture by being pressed by switching display after intelligence AI algorithm process Button, the monitored picture that can show that treated, and behavior label and behavior accuracy to people in frame out, in real-time video picture It detects exception, pops up abnormal alarm dialog box, while saving abnormal picture, wait relevant staff to handle abnormal；Video 4G camera hardware is carried in the front end for managing platform, and collected data are transmitted to background video management platform, real time monitoring Video pictures, the AI intelligent algorithm of rear end can analyze the human body behavior in video.
2. a kind of intelligent safety and defence system of wisdom new city according to claim 1, it is characterised in that in order to analyze view Moving target in frequency, and different types of target is classified to be put into different types of database, facilitate the later period Intelligent retrieval, need to video carry out structuring processing, use, specific implementation side are split to the moving target in video Formula is as follows:
Data structured processing is carried out to video image using the flooding mechanism of unsupervised Video segmentation, in video sequence x= {x1,...,xFF frame xi, initial prospect conspicuousness estimation is distributed on i ∈ { 1,2 ..., F }, using super-pixel by each frame figure As being divided into a group node, and the semantic relation in global Neighborhood Graph estimation and coded frame with interframe is used, passes through one and weight Row random neighborhood matrixIndicate global Neighborhood Graph, wherein N is the node total number in video；Execute each node The estimation of initialization prospect conspicuousnessDiffusion be by present node estimation and the repetition matrix multiple of Neighborhood matrix G It realizes, as the t times diffusing step vt=Gvt-1, unsupervised Video Segmentation Neighborhood matrix G based on diffusion and initial Change v0As unique input；
Saliency foreground moving, u are indicated using uiAnd piThe conspicuousness prospect and pixel in the i-th frame image are respectively indicated, is Calculating conspicuousness estimation, individually handles each frame xi, wherein i ∈ { 1,2 ..., F }, gives a frame image xi, reference image Vegetarian refreshments piIntensity value,It indicates in the i-th frame and i+1 frame with pixel piThe light of object of which movement is measured for unit Flow vector, βiIndicate the boundary pixel set at frame i；
It is based onWithThe conspicuousness sport foreground in video frame i is calculated, any picture of the i-th frame image is each measured Plain piWith boundary set βi；First distanceCalculate the pixel p observed on boundaryiBetween public flow direction Minimal flow direction difference；Second distanceCalculate pixel piPath cost function between boundary pixel；WithAll Capture pixel piSimilitude between the movement and background motion at place；
Calculate the difference in light stream direction: pixel p of the light stream direction difference at video frame iiAnd border betaiPublic light stream direction；It is first First, it uses k-means to cluster boundary light stream direction to gather for K, wherein k ∈ { 1 ..., K }, cluster centre point is covered In set, it is accomplished by
WhereinIndicate distribution pixel piTo the index in cluster k, r represents the series connection of all target variables；By KiIt updates Only comprising being assigned with the center more than 1/6 boundary pixel, in the case where giving cluster centre, to pass through pixel p in captured frame ii Optical-flow between the key light stream direction observed in the boundary frame i, is realized by following formula:
It calculates minimum potential barrier distance: calculating pixel p in video frame iiWith the minimum potential barrier distance D of boundary pixelbd,i, by as follows Formula is calculated:
WhereinIndicate path, edge aggregation connects pixel piWith boundary pixel s ∈ βi, minimum raw by being calculated in frame i Cheng Shu, edge weights wi(e) it is used to minimum spanning tree and potential barrier distance in calculation formula (1), it is maximum by calculating adjacent pixel Light stream direction difference value obtains:E=(pi,qi) it is two pixel ps of connectioniAnd qiSide； Minimum spanning tree is calculated using the method in 4 connection fields, the potential barrier distance of point-to-point transmission is calculated as point-to-point transmission minimum spanning tree road The difference of maximum side right on diameter and minimum side right, on the point and boundary between any point the minimum value of potential barrier distance as the point Minimum potential barrier distance；
It is significant to calculate foreground moving type: by two distance metrics after normalizationWithTo obtain pixelation in video frame i Conspicuousness foreground target ui；
Neighborhood Graph is calculated by calculating Neighborhood matrix G=T × E × V, wherein T is inter-frame information, and E is frame information, and V is Long-range (long-range) components；
Interframe timing information: interframe timing information is obtained by extracting Optic flow information, to prevent the light stream at moving boundaries from estimating Super-pixel is connected between the light stream vectors of adjacent interframe by inaccuracy while self-consistent property；To calculate light stream neighborhood Matrix T, continuous two needles image xiAnd xi+1, each frame image includes pixel piAnd pi+1, calculate the forward direction optical flow field of each pixel fi(pi) and backward optical flow field bi+1(pi+1), optical flow field obtained by calculation defines video frame xiIn pixel piThe forward direction at place is set Confidence scoreRealize that formula is as follows:
Backward confidence scoreIt is accomplished by
Wherein σ2For hyper parameter；Confidence score measures pixel piWith pass through pi+fi(pi) optical flow field followed into frame xi+1Later As a result, and passing through pi+fi(pi)+bi+1(pi+fi(pi)) return to frame xiIn result；Using confidence score calculate frame i and Two super-pixel s in frame i+1i,kAnd si+1,mBonding strength, realized by formula:
Wherein δ () indicates target function, | si,k| and | si+1,k| it represents in si,kAnd si+1,mThe pixel quantity at place；First in above formula Item compares with super-pixel si,kStart, si+1,mThe bonding strength of end be derived from si,kAnd si+1,mOverall strength；Section 2 is similar to table Show；
Spatial information prevents the diffusion of vision edge in frame in frame, if do not separated by strong edge, allows information in same frame In propagate between adjacent super-pixel, for the space E for finding edge perception, rung first using trained frame and the edge of interframe It answers, confidence score A (s) is calculated for all super-pixel by the method summed to attenuation function using skirt response, is realized such as Under:
Wherein G (p) ∈ [0,1] indicates the skirt response at pixel p, σwHyper parameter is represented with ε；
Edge, which is calculated, by above-mentioned marginal information perceives Neighborhood matrix E:
If si,kSpatially close to si+1,m, that is, super-pixel ruler of the centre distance less than 1.5 times between two super-pixel Very little square root；
If having visual similarity between two super-pixel, the long connection of view-based access control model similitude allows far from time or space On super-pixel between propagated, long connection can be made to propagate information by neighbour's image more efficient, be computation vision phase Like property matrix V, these super-pixel and super-pixel si,mRelationship is the closest, and k nearest neighbor search is first carried out, and surpasses picture to each Plain si,m, s is found in the time range of r framei,mK arest neighbors, super picture is calculated using Euclidean distance in feature space The distance between element；
The feature f (s) of super-pixel is calculated by connecting LBP the and RGB histogram of pixel in the super-pixel being calculated, simultaneously It further include the x and y coordinates of HOG feature and super-pixel center；
By defining visual similarity matrix, make super-pixel si,mK arest neighbors pass through N (si,m) reference, visual similarity matrix It indicates are as follows:
Wherein σ is hyper parameter, and f (s) indicates the character representation of super-pixel s；
After carrying out structuring processing to multi-path monitoring video image, a large amount of hashes in image are not only reduced, are obtained useful Data, and reduce the load capacity of cloud storing data, it is non-due to human body behavior in the accuracy of target identification Rigidity characteristics, so that behavior has diversity and variability, which can generate Different Individual same Human body behavior has relatively high accuracy, enables to apply in practice, in order to meet actual application demand, video figure The processing speed of picture 30 frame images of processing per second, can achieve the effect that quasi real time.
CN201910669716.3A 2019-07-24 2019-07-24 Intelligent security system of wisdom new town Active CN110428522B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910669716.3A CN110428522B (en) 2019-07-24 2019-07-24 Intelligent security system of wisdom new town

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910669716.3A CN110428522B (en) 2019-07-24 2019-07-24 Intelligent security system of wisdom new town

Publications (2)

Publication Number Publication Date
CN110428522A true CN110428522A (en) 2019-11-08
CN110428522B CN110428522B (en) 2021-04-30

Family

ID=68410541

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910669716.3A Active CN110428522B (en) 2019-07-24 2019-07-24 Intelligent security system of wisdom new town

Country Status (1)

Country Link
CN (1) CN110428522B (en)

Cited By (55)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110853276A (en) * 2019-12-05 2020-02-28 电子科技大学中山学院 Intelligent security intrusion detection system
CN110996067A (en) * 2019-12-19 2020-04-10 哈尔滨融智爱科智能科技有限公司 Personnel safety real-time intelligent video monitoring system under high-risk operation environment based on deep learning
CN111104916A (en) * 2019-12-23 2020-05-05 中科讯安(深圳)科技有限公司 Data analysis system for crowd image perception based on Internet of things
CN111191631A (en) * 2020-01-08 2020-05-22 哈尔滨融智爱科智能科技有限公司 Video monitoring supervision area multi-device linkage method based on image domain template matching
CN111263114A (en) * 2020-02-14 2020-06-09 北京百度网讯科技有限公司 Abnormal event alarm method and device
CN111459965A (en) * 2019-12-24 2020-07-28 中国科学院沈阳自动化研究所 Information monitoring system facing edge calculation
CN111491133A (en) * 2020-04-09 2020-08-04 河南城建学院 Market safety monitoring system applying electronic portrait locking technology
CN111510689A (en) * 2020-07-01 2020-08-07 成都宜泊信息科技有限公司 Video monitoring system and monitoring method
CN111540152A (en) * 2020-04-20 2020-08-14 张杜平 Intelligent security early warning system
CN111583485A (en) * 2020-04-16 2020-08-25 北京澎思科技有限公司 Community access control system, access control method and device, access control unit and medium
CN111582165A (en) * 2020-05-07 2020-08-25 广东中立建设有限公司 Electric power distribution station room monitored control system
CN111698470A (en) * 2020-06-03 2020-09-22 河南省民盛安防服务有限公司 Security video monitoring system based on cloud edge cooperative computing and implementation method thereof
CN111726579A (en) * 2020-06-12 2020-09-29 平湖市凯翔电子科技有限公司 Campus security monitoring system
CN111738163A (en) * 2020-06-23 2020-10-02 广东辰启科技有限责任公司 Processing method for edge calculation box front end identification
CN111787189A (en) * 2020-07-17 2020-10-16 塔盾信息技术(上海)有限公司 Gridding automatic monitoring system for integration of augmented reality and geographic information
CN111832457A (en) * 2020-07-01 2020-10-27 济南浪潮高新科技投资发展有限公司 Stranger intrusion detection method based on cloud edge cooperation
CN111862434A (en) * 2020-07-30 2020-10-30 上海茂声智能科技有限公司 Pedestrian passing control system and method
CN111866450A (en) * 2020-06-18 2020-10-30 昇辉控股有限公司 Intelligent video monitoring device based on cloud edge cooperation
CN111898524A (en) * 2020-07-29 2020-11-06 江苏艾什顿科技有限公司 5G edge computing gateway and application thereof
CN111932704A (en) * 2020-07-17 2020-11-13 苏州企智信息科技有限公司 Intelligent operation standard inspection method based on video behavior recognition
CN111950478A (en) * 2020-08-17 2020-11-17 浙江东鼎电子股份有限公司 Method for detecting S-shaped driving behavior of automobile in weighing area of dynamic flat-plate scale
CN112016474A (en) * 2020-08-31 2020-12-01 重庆紫光华山智安科技有限公司 Face recognition method, device and equipment and computer readable storage medium
CN112040196A (en) * 2020-09-15 2020-12-04 南京智能仿真技术研究院有限公司 Indoor intelligent security system based on machine vision
CN112050944A (en) * 2020-08-31 2020-12-08 深圳数联天下智能科技有限公司 Doorway position determining method and related device
CN112153345A (en) * 2020-09-25 2020-12-29 内蒙古蒙达发电有限责任公司 On-site intelligent anti-violation management and control platform based on 5G application operation
CN112200955A (en) * 2020-10-09 2021-01-08 北京首钢自动化信息技术有限公司 Method and device for controlling passing of target object
CN112383615A (en) * 2020-11-12 2021-02-19 山东建筑大学 Residential building entrance guard security system and method based on edge calculation
CN112417987A (en) * 2020-10-30 2021-02-26 四川天翼网络服务有限公司 Multi-angle face acquisition-based non-inductive identification passing method and system
CN112614161A (en) * 2020-12-28 2021-04-06 之江实验室 Three-dimensional object tracking method based on edge confidence
CN112634580A (en) * 2021-03-05 2021-04-09 深圳佳兆业科技集团有限公司 Community warning situation processing method, server, execution terminal and system
CN112733819A (en) * 2021-03-30 2021-04-30 成都大学 Multi-mode security monitoring method based on deep learning image processing
CN112770090A (en) * 2020-12-28 2021-05-07 杭州电子科技大学 Monitoring method based on transaction detection and target tracking
CN112818854A (en) * 2021-02-01 2021-05-18 南通大学 All-weather video person searching method applied to campus security
CN112861642A (en) * 2021-01-15 2021-05-28 北京睿芯高通量科技有限公司 Real-time face license plate recognition 5G police security system and method for mobile carrier
CN112907808A (en) * 2021-01-29 2021-06-04 西藏宁算科技集团有限公司 Specific area face recognition early warning system based on cloud computing
CN113297415A (en) * 2021-04-27 2021-08-24 安徽继远软件有限公司 Intelligent service method and system for edge video analysis facing power edge side
CN113392714A (en) * 2021-05-20 2021-09-14 上海可深信息科技有限公司 Crowd event detection method and system
CN113468948A (en) * 2021-04-26 2021-10-01 深圳市安软科技股份有限公司 View data based security and protection control method, module, equipment and storage medium
CN113762163A (en) * 2021-09-09 2021-12-07 杭州澳亚生物技术股份有限公司 GMP workshop intelligent monitoring management method and system
CN113823054A (en) * 2021-11-24 2021-12-21 中国南方电网有限责任公司超高压输电公司广州局 Comprehensive security management system, method and device for converter station and computer equipment
CN113903115A (en) * 2021-10-04 2022-01-07 哈尔滨徙木科技有限公司 Smart city security system
CN114281553A (en) * 2022-03-08 2022-04-05 开泰远景信息科技有限公司 Business processing method and system and cloud platform
CN114363344A (en) * 2022-01-04 2022-04-15 保利和悦生活科技服务有限公司 Intelligent community service management method and system based on cloud computing
CN114666554A (en) * 2022-05-23 2022-06-24 创意信息技术股份有限公司 Edge gateway cloud service management system
CN114827540A (en) * 2022-04-14 2022-07-29 山西长河科技股份有限公司 Monitoring station safe operation method and terminal based on video intelligent analysis technology
CN114937303A (en) * 2022-06-07 2022-08-23 慧之安信息技术股份有限公司 Scenic spot registration monitoring method based on face recognition
CN115103155A (en) * 2022-05-30 2022-09-23 广州工商学院 Public video monitoring system based on big data
CN115223002A (en) * 2022-05-09 2022-10-21 广州汽车集团股份有限公司 Model training method, door opening action detection method and device and computer equipment
WO2023280273A1 (en) * 2021-07-08 2023-01-12 云丁网络技术(北京)有限公司 Control method and system
TWI803760B (en) * 2019-06-27 2023-06-01 核桃運算股份有限公司 Bionic computing system and cloud system thereof
CN116955092A (en) * 2023-09-20 2023-10-27 山东小萌信息科技有限公司 Multimedia system monitoring method and system based on data analysis
CN117011963A (en) * 2023-10-07 2023-11-07 四川金投科技股份有限公司 Intelligent lock and intelligent door control system based on electronic key
CN117135324A (en) * 2023-09-08 2023-11-28 南京启征信息技术有限公司 Video integration intelligent identification system
CN117197876A (en) * 2023-11-07 2023-12-08 深圳凯升联合科技有限公司 Face recognition security system and method based on deep learning
CN117424988A (en) * 2023-12-15 2024-01-19 浙江大学台州研究院 Image processing system and processing method for intelligently managing welding machine

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002304651A (en) * 2001-04-06 2002-10-18 Nippon Telegr & Teleph Corp <Ntt> Device and method for managing entering/leaving room, program for executing the same method and recording medium with the same execution program recorded thereon
CN101778260A (en) * 2009-12-29 2010-07-14 公安部第三研究所 Method and system for monitoring and managing videos on basis of structured description
CN204229196U (en) * 2014-09-01 2015-03-25 无锡市七芯物联科技有限公司 A kind of Internet of Things practice teaching platform that can be applicable to Smart Home, intelligent grid
CN104537336A (en) * 2014-12-17 2015-04-22 厦门立林科技有限公司 Face identification method and system with self-learning function
CN205959347U (en) * 2016-08-17 2017-02-15 成都环球物讯科技有限责任公司 Community's intellectuality and electronic monitoring alarm system
CN107742092A (en) * 2016-08-31 2018-02-27 彭青 Smart city common monitoring system
CN109218660A (en) * 2017-07-07 2019-01-15 中兴通讯股份有限公司 A kind of method for processing video frequency and device
CN109302586A (en) * 2018-10-22 2019-02-01 成都臻识科技发展有限公司 A kind of structuring face snap camera and corresponding video monitoring system
CN109618286A (en) * 2018-10-24 2019-04-12 广州烽火众智数字技术有限公司 A kind of real-time monitoring system and method
KR20190072323A (en) * 2017-12-15 2019-06-25 동의대학교 산학협력단 Image Monitoring System and Method for Monitoring Image

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002304651A (en) * 2001-04-06 2002-10-18 Nippon Telegr & Teleph Corp <Ntt> Device and method for managing entering/leaving room, program for executing the same method and recording medium with the same execution program recorded thereon
CN101778260A (en) * 2009-12-29 2010-07-14 公安部第三研究所 Method and system for monitoring and managing videos on basis of structured description
CN204229196U (en) * 2014-09-01 2015-03-25 无锡市七芯物联科技有限公司 A kind of Internet of Things practice teaching platform that can be applicable to Smart Home, intelligent grid
CN104537336A (en) * 2014-12-17 2015-04-22 厦门立林科技有限公司 Face identification method and system with self-learning function
CN205959347U (en) * 2016-08-17 2017-02-15 成都环球物讯科技有限责任公司 Community's intellectuality and electronic monitoring alarm system
CN107742092A (en) * 2016-08-31 2018-02-27 彭青 Smart city common monitoring system
CN109218660A (en) * 2017-07-07 2019-01-15 中兴通讯股份有限公司 A kind of method for processing video frequency and device
KR20190072323A (en) * 2017-12-15 2019-06-25 동의대학교 산학협력단 Image Monitoring System and Method for Monitoring Image
CN109302586A (en) * 2018-10-22 2019-02-01 成都臻识科技发展有限公司 A kind of structuring face snap camera and corresponding video monitoring system
CN109618286A (en) * 2018-10-24 2019-04-12 广州烽火众智数字技术有限公司 A kind of real-time monitoring system and method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周宾: "人脸识别技术在"智慧南京"城市建设中的应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
王文新: "海量视频摘要及检索关键技术研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (73)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI803760B (en) * 2019-06-27 2023-06-01 核桃運算股份有限公司 Bionic computing system and cloud system thereof
CN110853276A (en) * 2019-12-05 2020-02-28 电子科技大学中山学院 Intelligent security intrusion detection system
CN110996067A (en) * 2019-12-19 2020-04-10 哈尔滨融智爱科智能科技有限公司 Personnel safety real-time intelligent video monitoring system under high-risk operation environment based on deep learning
CN111104916A (en) * 2019-12-23 2020-05-05 中科讯安(深圳)科技有限公司 Data analysis system for crowd image perception based on Internet of things
CN111459965A (en) * 2019-12-24 2020-07-28 中国科学院沈阳自动化研究所 Information monitoring system facing edge calculation
CN111459965B (en) * 2019-12-24 2023-05-05 中国科学院沈阳自动化研究所 Information monitoring system for edge calculation
CN111191631A (en) * 2020-01-08 2020-05-22 哈尔滨融智爱科智能科技有限公司 Video monitoring supervision area multi-device linkage method based on image domain template matching
CN111263114A (en) * 2020-02-14 2020-06-09 北京百度网讯科技有限公司 Abnormal event alarm method and device
CN111491133A (en) * 2020-04-09 2020-08-04 河南城建学院 Market safety monitoring system applying electronic portrait locking technology
CN111583485A (en) * 2020-04-16 2020-08-25 北京澎思科技有限公司 Community access control system, access control method and device, access control unit and medium
CN111540152A (en) * 2020-04-20 2020-08-14 张杜平 Intelligent security early warning system
CN111582165A (en) * 2020-05-07 2020-08-25 广东中立建设有限公司 Electric power distribution station room monitored control system
CN111582165B (en) * 2020-05-07 2024-02-09 广东中立建设有限公司 Monitoring system for power distribution station room
CN111698470A (en) * 2020-06-03 2020-09-22 河南省民盛安防服务有限公司 Security video monitoring system based on cloud edge cooperative computing and implementation method thereof
CN111698470B (en) * 2020-06-03 2021-09-03 中科民盛安防(河南)有限公司 Security video monitoring system based on cloud edge cooperative computing and implementation method thereof
CN111726579A (en) * 2020-06-12 2020-09-29 平湖市凯翔电子科技有限公司 Campus security monitoring system
CN111726579B (en) * 2020-06-12 2022-02-11 禾研(嘉兴)建筑智能化工程有限公司 Campus security monitoring system
CN111866450A (en) * 2020-06-18 2020-10-30 昇辉控股有限公司 Intelligent video monitoring device based on cloud edge cooperation
CN111738163A (en) * 2020-06-23 2020-10-02 广东辰启科技有限责任公司 Processing method for edge calculation box front end identification
CN111832457A (en) * 2020-07-01 2020-10-27 济南浪潮高新科技投资发展有限公司 Stranger intrusion detection method based on cloud edge cooperation
CN111832457B (en) * 2020-07-01 2022-07-22 山东浪潮科学研究院有限公司 Stranger intrusion detection method based on cloud edge cooperation
CN111510689A (en) * 2020-07-01 2020-08-07 成都宜泊信息科技有限公司 Video monitoring system and monitoring method
CN111932704A (en) * 2020-07-17 2020-11-13 苏州企智信息科技有限公司 Intelligent operation standard inspection method based on video behavior recognition
CN111787189A (en) * 2020-07-17 2020-10-16 塔盾信息技术(上海)有限公司 Gridding automatic monitoring system for integration of augmented reality and geographic information
CN111898524A (en) * 2020-07-29 2020-11-06 江苏艾什顿科技有限公司 5G edge computing gateway and application thereof
CN111862434A (en) * 2020-07-30 2020-10-30 上海茂声智能科技有限公司 Pedestrian passing control system and method
CN111950478B (en) * 2020-08-17 2021-07-23 浙江东鼎电子股份有限公司 Method for detecting S-shaped driving behavior of automobile in weighing area of dynamic flat-plate scale
CN111950478A (en) * 2020-08-17 2020-11-17 浙江东鼎电子股份有限公司 Method for detecting S-shaped driving behavior of automobile in weighing area of dynamic flat-plate scale
CN112016474A (en) * 2020-08-31 2020-12-01 重庆紫光华山智安科技有限公司 Face recognition method, device and equipment and computer readable storage medium
CN112050944A (en) * 2020-08-31 2020-12-08 深圳数联天下智能科技有限公司 Doorway position determining method and related device
CN112016474B (en) * 2020-08-31 2021-11-09 重庆紫光华山智安科技有限公司 Face recognition method, device and equipment and computer readable storage medium
CN112050944B (en) * 2020-08-31 2023-12-08 深圳数联天下智能科技有限公司 Gate position determining method and related device
CN112040196A (en) * 2020-09-15 2020-12-04 南京智能仿真技术研究院有限公司 Indoor intelligent security system based on machine vision
CN112153345A (en) * 2020-09-25 2020-12-29 内蒙古蒙达发电有限责任公司 On-site intelligent anti-violation management and control platform based on 5G application operation
CN112200955A (en) * 2020-10-09 2021-01-08 北京首钢自动化信息技术有限公司 Method and device for controlling passing of target object
CN112417987A (en) * 2020-10-30 2021-02-26 四川天翼网络服务有限公司 Multi-angle face acquisition-based non-inductive identification passing method and system
CN112383615A (en) * 2020-11-12 2021-02-19 山东建筑大学 Residential building entrance guard security system and method based on edge calculation
CN112770090A (en) * 2020-12-28 2021-05-07 杭州电子科技大学 Monitoring method based on transaction detection and target tracking
CN112614161A (en) * 2020-12-28 2021-04-06 之江实验室 Three-dimensional object tracking method based on edge confidence
CN112861642A (en) * 2021-01-15 2021-05-28 北京睿芯高通量科技有限公司 Real-time face license plate recognition 5G police security system and method for mobile carrier
CN112907808A (en) * 2021-01-29 2021-06-04 西藏宁算科技集团有限公司 Specific area face recognition early warning system based on cloud computing
CN112818854B (en) * 2021-02-01 2023-12-05 南通大学 All-weather video person searching method applied to campus security
CN112818854A (en) * 2021-02-01 2021-05-18 南通大学 All-weather video person searching method applied to campus security
CN112634580A (en) * 2021-03-05 2021-04-09 深圳佳兆业科技集团有限公司 Community warning situation processing method, server, execution terminal and system
CN112733819A (en) * 2021-03-30 2021-04-30 成都大学 Multi-mode security monitoring method based on deep learning image processing
CN113468948B (en) * 2021-04-26 2023-11-10 深圳市安软科技股份有限公司 View data-based security control method, module, equipment and storage medium
CN113468948A (en) * 2021-04-26 2021-10-01 深圳市安软科技股份有限公司 View data based security and protection control method, module, equipment and storage medium
CN113297415B (en) * 2021-04-27 2023-09-15 安徽继远软件有限公司 Intelligent service method and system for edge video analysis facing to electric power edge side
CN113297415A (en) * 2021-04-27 2021-08-24 安徽继远软件有限公司 Intelligent service method and system for edge video analysis facing power edge side
CN113392714A (en) * 2021-05-20 2021-09-14 上海可深信息科技有限公司 Crowd event detection method and system
WO2023280273A1 (en) * 2021-07-08 2023-01-12 云丁网络技术(北京)有限公司 Control method and system
CN113762163A (en) * 2021-09-09 2021-12-07 杭州澳亚生物技术股份有限公司 GMP workshop intelligent monitoring management method and system
CN113903115A (en) * 2021-10-04 2022-01-07 哈尔滨徙木科技有限公司 Smart city security system
CN113823054A (en) * 2021-11-24 2021-12-21 中国南方电网有限责任公司超高压输电公司广州局 Comprehensive security management system, method and device for converter station and computer equipment
CN114363344A (en) * 2022-01-04 2022-04-15 保利和悦生活科技服务有限公司 Intelligent community service management method and system based on cloud computing
CN114281553A (en) * 2022-03-08 2022-04-05 开泰远景信息科技有限公司 Business processing method and system and cloud platform
CN114281553B (en) * 2022-03-08 2022-05-13 开泰远景信息科技有限公司 Business processing method and system and cloud platform
CN114827540A (en) * 2022-04-14 2022-07-29 山西长河科技股份有限公司 Monitoring station safe operation method and terminal based on video intelligent analysis technology
CN115223002A (en) * 2022-05-09 2022-10-21 广州汽车集团股份有限公司 Model training method, door opening action detection method and device and computer equipment
CN115223002B (en) * 2022-05-09 2024-01-09 广州汽车集团股份有限公司 Model training method, door opening motion detection device and computer equipment
CN114666554A (en) * 2022-05-23 2022-06-24 创意信息技术股份有限公司 Edge gateway cloud service management system
CN115103155A (en) * 2022-05-30 2022-09-23 广州工商学院 Public video monitoring system based on big data
WO2023231082A1 (en) * 2022-05-30 2023-12-07 广州工商学院 Public video surveillance system based on big data
CN114937303A (en) * 2022-06-07 2022-08-23 慧之安信息技术股份有限公司 Scenic spot registration monitoring method based on face recognition
CN117135324A (en) * 2023-09-08 2023-11-28 南京启征信息技术有限公司 Video integration intelligent identification system
CN116955092A (en) * 2023-09-20 2023-10-27 山东小萌信息科技有限公司 Multimedia system monitoring method and system based on data analysis
CN116955092B (en) * 2023-09-20 2024-01-30 山东小萌信息科技有限公司 Multimedia system monitoring method and system based on data analysis
CN117011963A (en) * 2023-10-07 2023-11-07 四川金投科技股份有限公司 Intelligent lock and intelligent door control system based on electronic key
CN117011963B (en) * 2023-10-07 2023-12-08 四川金投科技股份有限公司 Intelligent lock and intelligent door control system based on electronic key
CN117197876A (en) * 2023-11-07 2023-12-08 深圳凯升联合科技有限公司 Face recognition security system and method based on deep learning
CN117197876B (en) * 2023-11-07 2024-04-09 深圳凯升联合科技有限公司 Face recognition security system and method based on deep learning
CN117424988A (en) * 2023-12-15 2024-01-19 浙江大学台州研究院 Image processing system and processing method for intelligently managing welding machine
CN117424988B (en) * 2023-12-15 2024-03-15 浙江大学台州研究院 Image processing system and processing method for intelligently managing welding machine

Also Published As

Publication number Publication date
CN110428522B (en) 2021-04-30

Similar Documents

Publication Publication Date Title
CN110428522A (en) A kind of intelligent safety and defence system of wisdom new city
US10346688B2 (en) Congestion-state-monitoring system
US7617167B2 (en) Machine vision system for enterprise management
CN104303193B (en) Target classification based on cluster
CN108174165A (en) Electric power safety operation and O＆M intelligent monitoring system and method
CN105426820B (en) More people&#39;s anomaly detection methods based on safety monitoring video data
CN108062349A (en) Video frequency monitoring method and system based on video structural data and deep learning
KR102149832B1 (en) Automated Violence Detecting System based on Deep Learning
US11288954B2 (en) Tracking and alerting traffic management system using IoT for smart city
CN110414360A (en) A kind of detection method and detection device of abnormal behaviour
CN115346163A (en) Warehouse safety monitoring method, device, system, equipment and computer storage medium
CN109255360A (en) A kind of objective classification method, apparatus and system
CN109284740A (en) Method, apparatus, equipment and the storage medium that mouse feelings are counted
CN105095891A (en) Human face capturing method, device and system
KR101513180B1 (en) System for a real-time cashing event summarization in surveillance images and the method thereof
CN116419059A (en) Automatic monitoring method, device, equipment and medium based on behavior label
CN111160150A (en) Video monitoring crowd behavior identification method based on depth residual error neural network convolution
CN114222163A (en) Intelligent video analysis system for business hall
CN113191182A (en) Violent abnormal behavior detection method based on deep learning
Costache et al. Target audience response analysis in out-of-home advertising using computer vision
CN110738692A (en) spark cluster-based intelligent video identification method
CN115953650B (en) Training method and device for feature fusion model
CN109726691B (en) Monitoring method
CN116246424A (en) Old people&#39;s behavioral safety monitored control system
CN115909144A (en) Method and system for detecting abnormity of surveillance video based on counterstudy

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
CP02 Change in the address of a patent holder
CP02 Change in the address of a patent holder

Address after: 266200 Household No. 8, Qingda Third Road, Laoshan District, Qingdao City, Shandong Province

Patentee after: QINGDAO LIANHE CHUANGZHI TECHNOLOGY Co.,Ltd.

Address before: Room 1204, No. 40, Hong Kong Middle Road, Shinan District, Qingdao, Shandong 266200

Patentee before: QINGDAO LIANHE CHUANGZHI TECHNOLOGY Co.,Ltd.