CN108810485A - A kind of monitoring system working method - Google Patents
A kind of monitoring system working method Download PDFInfo
- Publication number
- CN108810485A CN108810485A CN201810705912.7A CN201810705912A CN108810485A CN 108810485 A CN108810485 A CN 108810485A CN 201810705912 A CN201810705912 A CN 201810705912A CN 108810485 A CN108810485 A CN 108810485A
- Authority
- CN
- China
- Prior art keywords
- face
- module
- monitoring
- record
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
A kind of monitoring system working method mainly uses following steps, step 1：Monitoring camera sends video information to candid photograph server, captures server and parses face picture from video flowing, is sent in the candid photograph theme that distributed post is subscribed in message system using picture and with the relevant parameter of picture as record is captured；Step 2：Crowd's counting module is by the video information of reading monitoring camera, the statistical number of person from video flowing, and is sent in crowd's counting theme that distributed post is subscribed in message system using the statistical number of person, camera information and current time as record is counted；Step 3：Memory module consumer groups count record, and monitoring range corresponding with video camera is recorded according to counting, and corresponding thermodynamic chart distribution is shown on display module.Using computer vision technique, data under the line of customer are subjected to structuring extraction, using face ID as bridge, merge on-line off-line data, the final reconstruct for realizing people, goods, field provides effective structural data support, lays the groundwork for the big data analysis application in later stage.
Description
Technical field
The present invention relates to field of face identification, and in particular to a kind of monitoring system working method.
Background technology
Enter shop personal information to be difficult to count
Under internet environment, one of them key problem to be solved of traditional shops is the handle to shops data itself
Control, today, shops carried out how many people？The volume of the flow of passengers in the shops A and the shops B is how many？Compare the volume of the flow of passengers and income, the conversion of Liang Ge shops
Rate is how many？Current most of solutions are used disposes top set demographics video camera in entrance, passes through the head to people
Judgement is identified with both shoulders.Greatest problem is existing for this kind of scheme：Count the data got only person-time statistics, Wu Fapai
Situations such as repeatedly being passed in and out into outdegree, same personnel except salesman causes data inaccurate；It can not also learn the year into shop personnel simultaneously
The attribute datas such as discipline, gender.
Customer behavior data blank
Market and shops can not be effectively collected in customer and enter after market (shops), the behavioral data before merchandising.Mesh
Preceding most of markets (shops) all only value transaction data, especially traditional retail enterprise, only pos machines data, historical trading
Data.It is understood that user bought, but do not know what user seen, in which shop, which product
Preceding residence time is longer, more interesting to which kind of type products.
Safety precaution is in passive, cannot achieve early warning in advance
The deployment that the video monitoring system focus of current most market shops focuses more on video camera point is covered
Lid, system group network, rear end storage etc., seldom concern finds that suspicious object and critical incident shift to an earlier date using intellectual analysis
Early warning, video monitoring become the verification tool of " subsequent ".
Precision marketing, personalized service difficulty implement place
Adhere to, with consumption demand guiding, customer-oriented, accelerating to have become entity retail to the recurrence of retailing essence
The common recognition of industry, the consumption demand of various regions, consumption habit, consumption hot spot may also be not quite similar, and necessarily also result in various regions
Entity retail shows more and more othernesses, and differentiation highlights, and personalized service is caused to be difficult to fulfill.
Invention content
In view of the deficiencies of the prior art, the present invention proposes a kind of monitoring system working method, specific technical solution is as follows：One
Kind monitoring system working method, it is characterised in that：
Using following steps,
Step 1：Monitoring camera sends video information to candid photograph server, captures server and parses people from video flowing
Face picture is sent to grabbing in distributed post subscription message system using picture and with the relevant parameter of picture as record is captured
It claps in theme；
Step 2：Crowd's counting module is by the video information of reading monitoring camera, the statistical number of person from video flowing, and will
The statistical number of person, camera information and current time are sent to the crowd in distributed post subscription message system as counting record
It counts in theme；
Step 3：Memory module consumer groups count record, and monitoring range corresponding with video camera is recorded according to counting,
Corresponding thermodynamic chart distribution is shown on display module；
Step 4：Characteristic extracting module captures record by reading in real time, extracts the characteristic value of face picture, and by the spy
Value indicative is published in the candid photograph theme that distributed post is subscribed in message system；
Step 5：Identification module compares this feature value and the face in blacklist bottom library of deploying to ensure effective monitoring and control of illegal activities, and judges existing in monitoring
Whether field has the personnel in the library of blacklist bottom otherwise, to enter step 7 if so, then entering step 6；
Step 6：Identification module notifies alarm module, alarm module to be handled to salesman's early warning；
Step 7：Identification module compares this feature value and the face in frequent visitor's bottom storehouse of deploying to ensure effective monitoring and control of illegal activities, and judges the facial image
With the presence or absence of in frequent visitor library of deploying to ensure effective monitoring and control of illegal activities, if it is, into next step 8, otherwise, 9 are entered step；
Step 8：This feature is worth corresponding face registration to new person's bottom storehouse module of deploying to ensure effective monitoring and control of illegal activities by identification module；
Step 9：Identification module compares this feature value and the face in member bottom library of deploying to ensure effective monitoring and control of illegal activities, and judges the facial image
With the presence or absence of in member bottom library of deploying to ensure effective monitoring and control of illegal activities, if it is, into next step, otherwise, enter step；
Step 10：Membership information is sent to broadcast module by identification module；
Step 11：Identification module increases the facial image occurrence number in acquaintance bottom library module of deploying to ensure effective monitoring and control of illegal activities.
Further：The step 8 includes the following steps：
Step 8-1：The face picture for needing to register is uploaded, the face registration interface for calling identification module to provide, by picture
Identification service, which is issued, with bottom library number completes face registration；
Step 8-2：Inside identification module upon receiving a request, it needs to call characteristic module extraction face characteristic value first,
Then characteristic value is returned into identification module, face number, characteristic value and its attribute information etc. are registered to by finally identification service
In the library of corresponding face bottom；
Step 8-3：For the face bottom library deployed to ensure effective monitoring and control of illegal activities, the face characteristic value of new registration also will be applied to industry of deploying to ensure effective monitoring and control of illegal activities in real time
Business.
Further：The step 2 includes the following steps：
Step 2-1：Crowd's counting module obtains current crowd's quantity by parsing video flowing, analysis, and crowd is counted and is remembered
Record is sent in the counting theme of message queue；
Step 2-2：Storage service counts theme by subscription, stores structured data into database.
Further：The step 1 includes the following steps：
Step 1-1：It captures service and captures face picture by parsing video flowing, face picture is captured into record and panorama sketch
Piece record is separately sent in the face snap theme and panorama license-master topic of message queue；
Step 1-2：Memory module records theme and panorama license-master topic by subscribing to face snap, by the deposit point of picture entity
In cloth storage file system, store structured data into database.
Beneficial effects of the present invention are：Using computer vision technique, data under the line of customer are subjected to structuring extraction,
Using face ID as bridge, on-line off-line data are merged, the reconstruct of people, goods, field is finally realized, effective structural data branch is provided
Support is laid the groundwork for the big data analysis application in later stage.Region heating power distribution map, user trajectory point are provided by intelligent video analysis
Analyse function auxiliary market/comprehensive shops's operation of business and key decision.User identity is determined by face snap, identification and is divided
Analyse consumption propensity grade.It is deployed to ensure effective monitoring and control of illegal activities by face and improves the safety of market/supermarket/shops.By personalized face application and
Terminal improves the experience of market user individual.It is integrated actively to touch to reach using marketer terminal according to the customer analysis of system and label and be used
Family increases user experience and increases and improve shops into single possibility.
Description of the drawings
Fig. 1 is the work flow diagram of the present invention.
Specific implementation mode
The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
As shown in Figure 1：A kind of monitoring system working method, using following steps,
Step 1：It captures service and captures face picture by parsing video flowing, face picture is captured into record and panoramic pictures
Record is separately sent in the face snap theme and panorama license-master topic of message queue；
Step 2：Memory module records theme and panorama license-master topic by subscribing to face snap, and picture entity is stored in and is distributed
In formula storage file system, store structured data into database.
Step 3：Crowd's counting module obtains current crowd's quantity by parsing video flowing, analysis, and crowd is counted and is recorded
It is sent in the counting theme of message queue；
Step 4：Storage service counts theme by subscription, stores structured data into database.
Step 5：Memory module consumer groups count record, and monitoring range corresponding with video camera is recorded according to counting,
Corresponding thermodynamic chart distribution is shown on display module；
Step 6：Characteristic extracting module is sent to by reading to capture to record in real time, extracts the characteristic value of face picture, and
This feature value is published in the candid photograph theme that distributed post is subscribed in message system；
Step 7：Identification module compares this feature value and the face in blacklist bottom library of deploying to ensure effective monitoring and control of illegal activities, and judges existing in monitoring
Whether field has the personnel in the library of blacklist bottom otherwise, to enter step 9 if so, then entering step 8；
Step 8：Identification module notifies alarm module, alarm module to be handled to salesman's early warning；
Step 9：Identification module compares this feature value and the face in frequent visitor's bottom storehouse of deploying to ensure effective monitoring and control of illegal activities, and judges the facial image
With the presence or absence of in frequent visitor library of deploying to ensure effective monitoring and control of illegal activities, if it is, into next step 10, otherwise, 13 are entered step；
Step 10：Upload and need the face picture registered, the face registration interface for calling identification module to provide, by picture and
Bottom library number issues identification service and completes face registration；
Step 11：Inside identification module upon receiving a request, characteristic module is called to extract face characteristic value first, then
Characteristic value is returned into identification module, face number, characteristic value and its attribute information are registered to corresponding by finally identification service
In the library of face bottom；
Step 12：The face characteristic value of new registration is applied to the face bottom library deployed to ensure effective monitoring and control of illegal activities in real time.
Step 13：Identification module compares this feature value and the face in member bottom library of deploying to ensure effective monitoring and control of illegal activities, and judges the face figure
As with the presence or absence of in member bottom library of deploying to ensure effective monitoring and control of illegal activities, if it is, into next step, otherwise, entering step 15；
Step 14：Membership information is sent to broadcast module by identification module；
Step 15：Identification module increases the facial image occurrence number in acquaintance bottom library module of deploying to ensure effective monitoring and control of illegal activities.
Claims (4)
1. a kind of monitoring system working method, it is characterised in that：
Using following steps,
Step 1：Monitoring camera sends video information to candid photograph server, captures server and parses face figure from video flowing
Piece, the candid photograph master being sent to using picture and with the relevant parameter of picture as candid photograph record in distributed post subscription message system
In topic；
Step 2：Crowd's counting module is by reading the video information of monitoring camera, the statistical number of person from video flowing, and by the system
Meter number, camera information and current time are counted as the crowd that record is sent in distributed post subscription message system is counted
In theme；
Step 3：Memory module consumer groups count record, record monitoring range corresponding with video camera according to counting, are showing
Corresponding thermodynamic chart distribution is shown in module；
Step 4：Characteristic extracting module captures record by reading in real time, extracts the characteristic value of face picture, and by this feature value
It is published in the candid photograph theme that distributed post is subscribed in message system；
Step 5：Identification module compares this feature value and the face in blacklist bottom library of deploying to ensure effective monitoring and control of illegal activities, judge be in monitoring site
Otherwise the no personnel having in the library of blacklist bottom, enter step 7 if so, then entering step 6；
Step 6：Identification module notifies alarm module, alarm module to be handled to salesman's early warning；
Step 7：Identification module compares this feature value and the face in frequent visitor's bottom storehouse of deploying to ensure effective monitoring and control of illegal activities, and whether judges the facial image
In the presence of in frequent visitor library of deploying to ensure effective monitoring and control of illegal activities, if it is, into next step 8, otherwise, 9 are entered step；
Step 8：This feature is worth corresponding face registration to new person's bottom storehouse module of deploying to ensure effective monitoring and control of illegal activities by identification module；
Step 9：Identification module compares this feature value and the face in member bottom library of deploying to ensure effective monitoring and control of illegal activities, and whether judges the facial image
In the presence of in member bottom library of deploying to ensure effective monitoring and control of illegal activities, if it is, into next step, otherwise, 11 are entered step；
Step 10：Membership information is sent to broadcast module by identification module；
Step 11：Identification module increases the facial image occurrence number in acquaintance bottom library module of deploying to ensure effective monitoring and control of illegal activities.
2. a kind of monitoring system working method, it is characterised in that：The step includes the following steps：The step 8 includes as follows
Step：
Step 8-1：The face picture for needing to register is uploaded, the face registration interface for calling identification module to provide, by picture and bottom
Library number issues identification service and completes face registration；
Step 8-2：Inside identification module upon receiving a request, it calls characteristic module to extract face characteristic value first, then will
Characteristic value returns to identification module, and face number, characteristic value and its attribute information are registered to corresponding people by finally identification service
In the library of face bottom；
Step 8-3：The face characteristic value of new registration is applied to the face bottom library deployed to ensure effective monitoring and control of illegal activities in real time.
3. a kind of monitoring system working method, it is characterised in that：The step 2 includes the following steps：
Step 2-1：Crowd's counting module obtains current crowd's quantity by parsing video flowing, analysis, and crowd is counted record hair
It is sent in the counting theme of message queue；
Step 2-2：Storage service counts theme by subscription, stores structured data into database.
4. a kind of monitoring system working method, it is characterised in that：The step 1 includes the following steps：
Step 1-1：It captures service and captures face picture by parsing video flowing, face picture is captured into record and panoramic pictures are remembered
Record is separately sent in the face snap theme and panorama license-master topic of message queue；
Step 1-2：Memory module records theme and panorama license-master topic by subscribing to face snap, picture entity is stored in distributed
In storage file system, store structured data into database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810705912.7A CN108810485A (en) | 2018-07-02 | 2018-07-02 | A kind of monitoring system working method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810705912.7A CN108810485A (en) | 2018-07-02 | 2018-07-02 | A kind of monitoring system working method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108810485A true CN108810485A (en) | 2018-11-13 |
Family
ID=64074025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810705912.7A Pending CN108810485A (en) | 2018-07-02 | 2018-07-02 | A kind of monitoring system working method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108810485A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376689A (en) * | 2018-11-20 | 2019-02-22 | 图普科技（广州）有限公司 | Population analysis method and device |
| CN109583374A (en) * | 2018-11-30 | 2019-04-05 | 重庆市千将软件有限公司 | The method fought crime based on data iterative |
| CN110163158A (en) * | 2019-05-22 | 2019-08-23 | 广州图创计算机软件开发有限公司 | It is a kind of can Intellisense scene face identification system |
| CN110287878A (en) * | 2019-06-25 | 2019-09-27 | 秒针信息技术有限公司 | The determination method and device of marketing strategy, storage medium, electronic device |
| CN110532934A (en) * | 2019-08-26 | 2019-12-03 | 恒大智慧科技有限公司 | A kind of face bottom library update method, device, computer equipment and storage medium |
| CN110674757A (en) * | 2019-09-25 | 2020-01-10 | 北京旷视科技有限公司 | Deployment control method, system and computer readable storage medium |
| CN115862100A (en) * | 2022-11-28 | 2023-03-28 | 成都比特至简科技有限公司 | Face backtracking method and system based on video |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447458A (en) * | 2015-11-17 | 2016-03-30 | 深圳市商汤科技有限公司 | Large scale crowd video analysis system and method thereof |
| US20160203499A1 (en) * | 2013-09-06 | 2016-07-14 | Nec Corporation | Customer behavior analysis system, customer behavior analysis method, non-transitory computer readable medium, and shelf system |
| CN206472227U (en) * | 2016-10-11 | 2017-09-05 | 中控智慧科技股份有限公司 | A kind of video-unit |
| CN107679613A (en) * | 2017-09-30 | 2018-02-09 | 同观科技（深圳）有限公司 | A kind of statistical method of personal information, device, terminal device and storage medium |
| CN207352731U (en) * | 2017-10-19 | 2018-05-11 | 深圳中安安防科技有限公司 | A kind of guard against theft in market system |
-
2018
- 2018-07-02 CN CN201810705912.7A patent/CN108810485A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160203499A1 (en) * | 2013-09-06 | 2016-07-14 | Nec Corporation | Customer behavior analysis system, customer behavior analysis method, non-transitory computer readable medium, and shelf system |
| CN105447458A (en) * | 2015-11-17 | 2016-03-30 | 深圳市商汤科技有限公司 | Large scale crowd video analysis system and method thereof |
| CN206472227U (en) * | 2016-10-11 | 2017-09-05 | 中控智慧科技股份有限公司 | A kind of video-unit |
| CN107679613A (en) * | 2017-09-30 | 2018-02-09 | 同观科技（深圳）有限公司 | A kind of statistical method of personal information, device, terminal device and storage medium |
| CN207352731U (en) * | 2017-10-19 | 2018-05-11 | 深圳中安安防科技有限公司 | A kind of guard against theft in market system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376689A (en) * | 2018-11-20 | 2019-02-22 | 图普科技（广州）有限公司 | Population analysis method and device |
| CN109583374A (en) * | 2018-11-30 | 2019-04-05 | 重庆市千将软件有限公司 | The method fought crime based on data iterative |
| CN110163158A (en) * | 2019-05-22 | 2019-08-23 | 广州图创计算机软件开发有限公司 | It is a kind of can Intellisense scene face identification system |
| CN110163158B (en) * | 2019-05-22 | 2019-12-20 | 广州图创计算机软件开发有限公司 | Scene face recognition system capable of intelligently sensing |
| CN110287878A (en) * | 2019-06-25 | 2019-09-27 | 秒针信息技术有限公司 | The determination method and device of marketing strategy, storage medium, electronic device |
| CN110532934A (en) * | 2019-08-26 | 2019-12-03 | 恒大智慧科技有限公司 | A kind of face bottom library update method, device, computer equipment and storage medium |
| CN110674757A (en) * | 2019-09-25 | 2020-01-10 | 北京旷视科技有限公司 | Deployment control method, system and computer readable storage medium |
| CN110674757B (en) * | 2019-09-25 | 2022-07-19 | 北京旷视科技有限公司 | Deployment control method, system and computer readable storage medium |
| CN115862100A (en) * | 2022-11-28 | 2023-03-28 | 成都比特至简科技有限公司 | Face backtracking method and system based on video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108810485A (en) | A kind of monitoring system working method | |
| US8351647B2 (en) | Automatic detection and aggregation of demographics and behavior of people | |
| WO2018180588A1 (en) | Facial image matching system and facial image search system | |
| CN111597999A (en) | 4S shop sales service management method and system based on video detection | |
| US10078693B2 (en) | People searches by multisensor event correlation | |
| Liciotti et al. | Person re-identification dataset with rgb-d camera in a top-view configuration | |
| US7267277B2 (en) | Method and system for targeted marketing by leveraging video-based demographic insights | |
| JP5224360B2 (en) | Electronic advertising device, electronic advertising method and program | |
| US20080018738A1 (en) | Video analytics for retail business process monitoring | |
| US20070253595A1 (en) | Still Image Queue Analysis System and Method | |
| KR101779096B1 (en) | The object pursuit way in the integration store management system of the intelligent type image analysis technology-based | |
| US20030040925A1 (en) | Vision-based method and apparatus for detecting fraudulent events in a retail environment | |
| CN104392370A (en) | Electronic commerce system and method for automatically acquiring customer information | |
| US20160048721A1 (en) | System and method for accurately analyzing sensed data | |
| CN109711900A (en) | Information display method and device based on face recognition, terminal equipment and storage medium | |
| CN110766454B (en) | Method for collecting customer visit information of store and store subsystem architecture | |
| JP6498900B2 (en) | Advertisement evaluation system, advertisement evaluation method | |
| WO2018132923A1 (en) | System and method for assessing customer service times | |
| Zin et al. | A Markov random walk model for loitering people detection | |
| CN106326835A (en) | Human face data collection statistical system and method for gas station convenience store | |
| CN112699328A (en) | Network point service data processing method, device, system, equipment and storage medium | |
| AU2017231602A1 (en) | Method and system for visitor tracking at a POS area | |
| JP2015090579A (en) | Behavior analysis system | |
| WO2015003287A1 (en) | Behavior recognition and tracking system and operation method therefor | |
| CN112085521A (en) | System for managing and serving store members |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 401122 5 stories, Block 106, West Jinkai Avenue, Yubei District, Chongqing Applicant after: Chongqing Zhongke Yuncong Technology Co., Ltd. Address before: 401121 5/F Internet Industrial Park, Yubei District, Chongqing Applicant before: CHONGQING ZHONGKE YUNCONG TECHNOLOGY CO., LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |