CN105100735A - People intelligent monitoring management system and management method - Google Patents
People intelligent monitoring management system and management method Download PDFInfo
- Publication number
- CN105100735A CN105100735A CN201510543450.XA CN201510543450A CN105100735A CN 105100735 A CN105100735 A CN 105100735A CN 201510543450 A CN201510543450 A CN 201510543450A CN 105100735 A CN105100735 A CN 105100735A
- Authority
- CN
- China
- Prior art keywords
- data
- personnel
- monitoring management
- video
- facial image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
This invention provides a people intelligent monitoring management system and management method. The system comprises a data collection unit, a data exchange unit, a data process unit and a data receive terminal, wherein face image data captured by the data collection unit is timely uploaded to the data process unit by utilizing the data exchange unit and through communication software, the image data is analyzed and processed, and uploaded to the data receive terminal through the data process unit. Thus, the timely and precise monitoring management information is provided for a mobile client, and a monitored management target is identified, managed and warned in an intelligent, dynamic and precise manner.
Description
Technical field
The present invention relates to monitoring and technical field of security, relate more specifically to a kind of personnel's intellectual monitoring management system and management method.
Background technology
In recent years, personnel's intellectual monitoring management equipment mainly utilizes face Time Attendance Device, video monitoring equipment to realize, at present, on market, the major technique of face Time Attendance Device, watch-dog foundation utilizes multiple-core server software, carries out typing, storage, reading, comparison to facial image, video data.The major function of above system comprises: by under fixed environment, reads, comparison realizes work attendance target to the image of Static Human Face input database, video data; Observe by Security Personnel region that monitor video occurs fixing industrial computer identification disturbance information constantly to implement security or use can be transferred to the facial image of stored record, video afterwards.But there is following technological deficiency in above-mentioned prior art: the arithmetic speed of (1) data is slow, and analytic function is weak; (2) intelligence degree is low, function singleness; (3) mostly be manual analysis afterwards, cost of labor is high, and accuracy is low; (4) ex ante forecasting, early warning poor performance; (5) scope of application is little.
Summary of the invention
In view of this, an object of the present invention is to provide a kind of personnel's intellectual monitoring management system, and another object of the present invention is to provide a kind of personnel's intellectual monitoring management method.
To achieve these goals, as one aspect of the present invention, the invention provides a kind of personnel's intellectual monitoring management system, comprising:
Data acquisition unit, for catching the facial image and/or video that occur personnel in monitoring management region;
Data exchange unit, for receiving described facial image/video data that data acquisition unit catches, and is uploaded to data processing unit;
Data processing unit, for by being core with neuron algorithm, software carries out degree of depth study and analyzing and processing to the described facial image/video data from described data exchange unit, realize many people facial image, the dynamic high speed precise alignment of video and identification, and complete at matching identification send Monitoring Data and/or early warning signal to data receiving terminal afterwards;
Data receiving terminal receives the described Monitoring Data and/or early warning signal that described data processing unit sends, and is showed the holder of described data receiving terminal.
Wherein, described data processing unit comprises multinuclear and many core parallel servers.
Described data processing unit is comprised the following steps described facial image/video data step identified of comparing by the software that is core with neuron algorithm:
The first step, gathers face characteristic data building database; Selection sort device, determines the characteristic point gathering face in described database, sets up face neural network model;
Second step, utilizes linear correlation algorithm and neuron parallel algorithm, calculates the visual layers of described face neural network model and face characteristic value, the characteristic vector of each hidden layer;
3rd step, utilizes linear correlation algorithm and neuron parallel algorithm to calculate comparison, the face characteristic value of identification person, characteristic vector;
4th step, by the face feature vector of described face neural network model compared with the face feature vector of described comparison, identification person, the less then matching degree of difference is higher, otherwise, then lower.
As another aspect of the present invention, present invention also offers a kind of personnel's intellectual monitoring management method, comprise the following steps:
Facial image/the video data of the personnel occurred in the monitoring management region that data exchange unit reception data acquisition unit is caught, and uploaded to data processing unit;
Data processing unit is compared to the described facial image/video data from described data exchange unit and identifies, and complete at matching identification send early warning signal to data receiving terminal afterwards;
Data receiving terminal receives the described Monitoring Data and/or early warning signal that described data processing unit sends, and is showed the holder of described data receiving terminal;
Wherein, described data processing unit is multinuclear and many core parallel servers.
Wherein, described multinuclear and many core parallel servers carry out degree of depth study and analyzing and processing by the software being core with neuron algorithm to described facial image/video data, realize many people facial image, the intelligent dynamic high speed of video accurately identifies and comparison.
Known based on technique scheme, personnel's intellectual monitoring management system of the present invention has the following advantages and beneficial effect: (1) is monitored by mobile client, not by place, distance limit; (2) dynamic comparison, identification can be implemented with the facial image in input database, video data information for main body, also can implement dynamic comparison, identification with the outer personnel's facial image of database, video data for main body, and comparison result or Monitoring Data are sent to client terminal immediately; (3) data operation speed is fast, analytic function is strong, intelligence degree is high, by adjustment configuration soft and hardware standard and parameter, be the different monitoring management demands of different user, formulate different technical schemes, such as: long-rangely can immediately provide image, the video of employee for manager, can immediately provide in management area, the dynamic analysis data of employee, the security protection early warning etc. that key area is instant can be provided; (4) cost of labor is low, and security protection precision is high; (5) applied widely, both be applicable to the places such as the large square of the density of population, station, harbour, hospital, school, large enterprise, business, be also applicable to the place that small business, business, family, office, unattended warehouse, hall, accounting office, machine room, garage etc. need to monitor among a small circle.
Accompanying drawing explanation
Fig. 1 is the structural representation of personnel's intellectual monitoring management system of the present invention;
Fig. 2 is the signal flow graph of personnel's intellectual monitoring management system of the present invention;
Fig. 3 is the many core calculation flow charts of recognition of face multinuclear of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in further detail.
Along with the development of computer chip integrated technology, while polycaryon processor is constantly popularized, many-core processor also starts to rise, thus is that some technical barriers solved in reality provide effective solution.Polycaryon processor is exactly can be no more than at most the processor of tens kernels by integrated two or more, and many-core processor refers to chip has tens to the processor of up to ten thousand kernels, does not have the upper limit in principle, refers generally to the processor of hundreds of kernels at present.
The development of multinuclear and many core parallel parsing technology, also makes personnel's intellectual monitoring management system and correlation technique arise at the historic moment, and has conventional face's Time Attendance Device, the irreplaceable advantage of video monitoring equipment.Personnel's intellectual monitoring management system of the present invention mainly utilizes PC, notebook computer, the multiple target personnel facial image that mobile panel computer is captured camera, video data, processed by communication software system, and upload to multinuclear and many core parallel servers, degree of depth study and analyzing and processing is carried out by the software being core with neuron algorithm, obtain monitored manager's facial image, video and statistical data analysis, and utilize mobile broadband network and communication software by image, video and statistical data analysis upload to mobile terminal immediately, for mobile client provides decision-making foundation and early warning information.
Neuron algorithm refers to the process of carrying out reasoning according to logic rules; Information is first changed into concept by it, and symbolically, then, carry out reasoning from logic according to symbolic operation by serial mode; This process can be write as the instruction of serial, allows computer perform.(1) information is stored on network by the excited mode profile on neuron; (2) information processing by between neuron simultaneously interactional dynamic process come.Degree of depth study is a new field in machine learning research, and its motivation is the neural net set up, simulation human brain carries out analytic learning, and the mechanism that its imitates human brain carrys out decryption, such as image, sound and text.
Personnel's intellectual monitoring management system of the present invention realizes its function by data acquisition unit, data exchange unit, data processing unit, the integrated of data receiving terminal, respectively in detail it is described in detail below in conjunction with accompanying drawing.
(1) data acquisition unit
Data acquisition unit of the present invention mainly comprises monitoring camera 1, this camera adopts embedded OS, adopt low-light (level) imageing sensor, support HD video, realize the low network band width transmission of HD image, support to monitor round the clock, its main feature has: support cradle head control, support trigram Flow Technique, support wireless network, support voice intercommunication, possesses low in energy consumption, low, that time delay is short, resolution is high feature of generating heat.
Wherein, The Cloud Terrace is the fastening of installation, fixed cameras, and it is divided into fixing and electric platform two kinds.Fixing The Cloud Terrace is applicable to the little situation of monitoring range, the level of adjustable video camera and the angle of pitching after fixing The Cloud Terrace installs video camera, as long as locking adjusting mechanism is just passable after reaching best operating attitude.Electric platform is applicable to carrying out scanning monitoring on a large scale, and it can expand the monitoring range of video camera.Electric platform high speed attitude is realized by two operating motors, and the signal that motor accepts self-controller accurately runs location.Under the effect of control signal, the video camera on The Cloud Terrace both can automatic scan monitor area, also can trace and monitor object under the manipulation of Surveillance center operator on duty.Namely cradle head control technology is utilize The Cloud Terrace to control shooting angle and the monitoring range of video camera, thus realizes monitoring more accurately.
Trigram Flow Technique refers to and generates three road video code flows simultaneously, and each road video flowing can arrange different resolution, frame per second and coded system respectively.The code stream of one road height code check is used for local high definition and stores, such as, H.264/D1 encode, and the code stream of a road low bit-rate is used for Internet Transmission, such as D1/CIF coding, and the ultralow code stream in another road is used for 3G/ Internet Transmission, and mobile phone is watched.
(2) data exchange unit
It for receiving data acquisition unit catcher face image, video data (supporting to capture many people) simultaneously, and is uploaded to data processing unit by communication software and the Internet by data exchange unit of the present invention.Data exchange unit such as comprises PC 2, notebook computer 3 and/or panel computer 4, the configuration that preferably it has high-end display card, more than 1G internal memory, more than 500G hard disk, more than 2M broadband network arrange environment.
(3) data processing unit
Data processing unit mainly comprises multinuclear and many core parallel servers 5, this parallel server carries out degree of depth study and analyses and comparison by the software being core with neuron algorithm, obtain monitored manager many people facial image, video and statistical data analysis, after result of analysing and comparing out, image, video and statistical data analysis upload on the data receiving terminal of monitoring client by data processing unit, so that user carries out remote monitoring.
Data processing unit is connected with database, and many people are retrieved in this database support simultaneously, thus when running into several monitored manager, can parallelism recognition and all monitored managers of comparison.
In the present invention, the process of facial image, video data realizes based on multinuclear and many core recognitions of face, comparison parallel computation way, as shown in Figure 3, comprises the following steps:
1st step, gathers face characteristic data Modling model; Under the state of close friend, n pitching of collection n face and left and right sides facial image, stored in database, carry out preliminary treatment to view data and automatically detect; And
Selection sort device, determines human face characteristic point, comprises age, sex, expression and colourity, saturation, brightness, lightness and gray scale etc., sets up face neural network model;
2nd step, utilizes linear correlation algorithm and the parallel computation of neuron algorithm and self-defining group of functions, calculates neural network model visual layers and every one deck hidden layer face characteristic value, characteristic vector (comprising the component of pixel);
3rd step, calculates comparison, identification person's face characteristic value, characteristic vector with same algorithm;
4th step, by face feature vector in database and comparison, identifies that compared with target face feature vector, the less then matching degree of difference is higher, otherwise, then lower.
(4) data receiving terminal
Data receiving terminal is generally detection management terminal, smart mobile phone 6 or panel computer, wherein smart mobile phone 6 and dull and stereotyped computer expert often adopt Android or IOS, downloaded the software having reception, push image, video data function, preferred described data receiving terminal supports more than 2G internal memory, more than 16G hard disk and WiMAX.By data receiving terminal, the Internet of the present invention personnel's intellectual monitoring management system can be decision-making foundation accurate when user both provides and early warning information.
By in certain small business and community discovery on probation among a small circle, personnel's intellectual monitoring management system analytic function of the present invention is strong, intelligence degree is high, fast and effeciently can complete the reception and registration of target identification and statistical data analysis, realizes accurate decision-making and early warning in time.
Above-described specific embodiment; object of the present invention, technical scheme and beneficial effect are further described; be understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. personnel's intellectual monitoring management system, comprising:
Data acquisition unit, for catching the facial image and/or video that occur personnel in monitoring management region;
Data exchange unit, for receiving described facial image/video data that data acquisition unit catches, and is uploaded to data processing unit;
Data processing unit, for by being core with neuron algorithm, software carries out degree of depth study and analyzing and processing to the described facial image/video data from described data exchange unit, realize many people facial image, the dynamic high speed precise alignment of video and identification, and complete at matching identification send Monitoring Data and/or early warning signal to data receiving terminal afterwards;
Data receiving terminal receives the described Monitoring Data and/or early warning signal that described data processing unit sends, and is showed the holder of described data receiving terminal.
2. personnel's intellectual monitoring management system according to claim 1, wherein said data acquisition unit is monitoring camera.
3. personnel's intellectual monitoring management system according to claim 2, wherein said monitoring camera adopts low-light (level) imageing sensor, supports HD video, supports to monitor round the clock.
4. personnel's intellectual monitoring management system according to claim 2, wherein said monitoring camera supports cradle head control technology and trigram Flow Technique.
5. personnel's intellectual monitoring management system according to claim 1, wherein said data exchange unit comprises PC, notebook computer and/or panel computer.
6. personnel's intellectual monitoring management system according to claim 1, wherein said data processing unit comprises multinuclear and many core parallel servers.
7. personnel's intellectual monitoring management system according to claim 6, wherein said data processing unit is comprised the following steps described facial image/video data step identified of comparing by the software that is core with neuron algorithm:
The first step, gathers face characteristic data building database; Selection sort device, determines the characteristic point gathering face in described database, sets up face neural network model;
Second step, utilizes linear correlation algorithm and neuron parallel algorithm, calculates the visual layers of described face neural network model and face characteristic value, the characteristic vector of each hidden layer;
3rd step, utilizes linear correlation algorithm and neuron parallel algorithm to calculate comparison, the face characteristic value of identification person, characteristic vector;
4th step, by the face feature vector of described face neural network model compared with the face feature vector of described comparison, identification person, the less then matching degree of difference is higher, otherwise, then lower.
8. personnel's intellectual monitoring management system according to claim 1, wherein said data receiving terminal is smart mobile phone or panel computer.
9. personnel's intellectual monitoring management method, comprises the following steps:
Facial image/the video data of the personnel occurred in the monitoring management region that data exchange unit reception data acquisition unit is caught, and uploaded to data processing unit;
Data processing unit is compared to the described facial image/video data from described data exchange unit and identifies, and complete at matching identification send early warning signal to data receiving terminal afterwards;
Data receiving terminal receives the described Monitoring Data and/or early warning signal that described data processing unit sends, and is showed the holder of described data receiving terminal;
Wherein, described data processing unit is multinuclear and many core parallel servers.
10. personnel's intellectual monitoring management method according to claim 9, wherein, described multinuclear and many core parallel servers carry out degree of depth study and analyzing and processing by the software being core with neuron algorithm to described facial image/video data, realize many people facial image, the intelligent dynamic high speed of video accurately identifies and comparison.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510543450.XA CN105100735A (en) | 2015-08-31 | 2015-08-31 | People intelligent monitoring management system and management method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510543450.XA CN105100735A (en) | 2015-08-31 | 2015-08-31 | People intelligent monitoring management system and management method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105100735A true CN105100735A (en) | 2015-11-25 |
Family
ID=54580155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510543450.XA Pending CN105100735A (en) | 2015-08-31 | 2015-08-31 | People intelligent monitoring management system and management method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105100735A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105574506A (en) * | 2015-12-16 | 2016-05-11 | 深圳市商汤科技有限公司 | Intelligent face tracking system and method based on depth learning and large-scale clustering |
WO2017107957A1 (en) * | 2015-12-22 | 2017-06-29 | 中兴通讯股份有限公司 | Human face image retrieval method and apparatus |
CN107483889A (en) * | 2017-08-24 | 2017-12-15 | 北京融通智慧科技有限公司 | The tunnel monitoring system of wisdom building site control platform |
CN107493459A (en) * | 2017-09-15 | 2017-12-19 | 赵立峰 | A kind of engineer operation plateform system |
CN109508690A (en) * | 2018-11-29 | 2019-03-22 | 浙江工业大学 | A kind of non-active cooperation attendance checking system based on recognition of face |
CN109842752A (en) * | 2019-03-12 | 2019-06-04 | 安徽协创物联网技术有限公司 | It is a kind of support 4G communication can recognition of face intelligent video camera head |
CN111541867A (en) * | 2020-03-18 | 2020-08-14 | 北京中科医信科技有限公司 | Face recognition system suitable for medical institution and working method thereof |
CN111598326A (en) * | 2020-05-11 | 2020-08-28 | 南京大创师智能科技有限公司 | Artificial intelligence behavior prediction intelligent algorithm based on big data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003196793A (en) * | 2001-12-25 | 2003-07-11 | Mitsubishi Electric Corp | Mobile information communication system |
CN101526997A (en) * | 2009-04-22 | 2009-09-09 | 无锡名鹰科技发展有限公司 | Embedded infrared face image identifying method and identifying device |
CN102752574A (en) * | 2011-04-18 | 2012-10-24 | 中兴通讯股份有限公司 | Video monitoring system and method |
CN103258191A (en) * | 2013-05-15 | 2013-08-21 | 苏州福丰科技有限公司 | Community access control system based on face recognition |
CN104573679A (en) * | 2015-02-08 | 2015-04-29 | 天津艾思科尔科技有限公司 | Deep learning-based face recognition system in monitoring scene |
CN104574555A (en) * | 2015-01-14 | 2015-04-29 | 四川大学 | Remote checking-in method adopting face classification algorithm based on sparse representation |
-
2015
- 2015-08-31 CN CN201510543450.XA patent/CN105100735A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003196793A (en) * | 2001-12-25 | 2003-07-11 | Mitsubishi Electric Corp | Mobile information communication system |
CN101526997A (en) * | 2009-04-22 | 2009-09-09 | 无锡名鹰科技发展有限公司 | Embedded infrared face image identifying method and identifying device |
CN102752574A (en) * | 2011-04-18 | 2012-10-24 | 中兴通讯股份有限公司 | Video monitoring system and method |
CN103258191A (en) * | 2013-05-15 | 2013-08-21 | 苏州福丰科技有限公司 | Community access control system based on face recognition |
CN104574555A (en) * | 2015-01-14 | 2015-04-29 | 四川大学 | Remote checking-in method adopting face classification algorithm based on sparse representation |
CN104573679A (en) * | 2015-02-08 | 2015-04-29 | 天津艾思科尔科技有限公司 | Deep learning-based face recognition system in monitoring scene |
Non-Patent Citations (3)
Title |
---|
张宁等: "《基于深度自动编码器的机场安检人脸识别***设计》", 《计算机测量与控制》 * |
王欣: "《DirectX游戏程序设计》", 31 May 2014 * |
黄恺等: "《云计算与分布式***:从并行处理到物联网》", 31 January 2013 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105574506A (en) * | 2015-12-16 | 2016-05-11 | 深圳市商汤科技有限公司 | Intelligent face tracking system and method based on depth learning and large-scale clustering |
CN105574506B (en) * | 2015-12-16 | 2020-03-17 | 深圳市商汤科技有限公司 | Intelligent face pursuit system and method based on deep learning and large-scale clustering |
WO2017107957A1 (en) * | 2015-12-22 | 2017-06-29 | 中兴通讯股份有限公司 | Human face image retrieval method and apparatus |
CN107483889A (en) * | 2017-08-24 | 2017-12-15 | 北京融通智慧科技有限公司 | The tunnel monitoring system of wisdom building site control platform |
CN107493459A (en) * | 2017-09-15 | 2017-12-19 | 赵立峰 | A kind of engineer operation plateform system |
CN109508690A (en) * | 2018-11-29 | 2019-03-22 | 浙江工业大学 | A kind of non-active cooperation attendance checking system based on recognition of face |
CN109508690B (en) * | 2018-11-29 | 2021-08-17 | 浙江工业大学 | Non-active cooperation attendance system based on face recognition |
CN109842752A (en) * | 2019-03-12 | 2019-06-04 | 安徽协创物联网技术有限公司 | It is a kind of support 4G communication can recognition of face intelligent video camera head |
CN111541867A (en) * | 2020-03-18 | 2020-08-14 | 北京中科医信科技有限公司 | Face recognition system suitable for medical institution and working method thereof |
CN111598326A (en) * | 2020-05-11 | 2020-08-28 | 南京大创师智能科技有限公司 | Artificial intelligence behavior prediction intelligent algorithm based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105100735A (en) | People intelligent monitoring management system and management method | |
US11735018B2 (en) | Security system with face recognition | |
CN109271554B (en) | Intelligent video identification system and application thereof | |
CN105354548B (en) | A kind of monitor video pedestrian recognition methods again based on ImageNet retrievals | |
US20190130188A1 (en) | Object classification in a video analytics system | |
CN103986910A (en) | Method and system for passenger flow statistics based on cameras with intelligent analysis function | |
CN115272037B (en) | Smart city based on Internet of things regional public security management early warning method and system | |
CN105913037A (en) | Face identification and radio frequency identification based monitoring and tracking system | |
Othman et al. | A new IoT combined body detection of people by using computer vision for security application | |
US8855369B2 (en) | Self learning face recognition using depth based tracking for database generation and update | |
CN112396658B (en) | Indoor personnel positioning method and system based on video | |
CN112562161A (en) | Based on 5G thing networking and AI intelligent entrance guard integrated management system | |
CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
Kumar et al. | Application of internet of things in image processing | |
KR102333143B1 (en) | System for providing people counting service | |
CN105243386A (en) | Face living judgment method and system | |
CN110728252B (en) | Face detection method applied to regional personnel motion trail monitoring | |
CN109697499A (en) | Pedestrian's flow funnel generation method and device, storage medium, electronic equipment | |
CN206322194U (en) | A kind of anti-fraud face identification system based on 3-D scanning | |
CN110659391A (en) | Video detection method and device | |
CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
CN104134067A (en) | Road vehicle monitoring system based on intelligent visual Internet of Things | |
CN104159088A (en) | System and method of remote monitoring of intelligent vehicle | |
Venkatesvara Rao et al. | Real-time video object detection and classification using hybrid texture feature extraction | |
CN112700568B (en) | Identity authentication method, equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151125 |