CN109344765A - A kind of intelligent analysis method entering shop personnel analysis for chain shops - Google Patents
A kind of intelligent analysis method entering shop personnel analysis for chain shops Download PDFInfo
- Publication number
- CN109344765A CN109344765A CN201811139060.6A CN201811139060A CN109344765A CN 109344765 A CN109344765 A CN 109344765A CN 201811139060 A CN201811139060 A CN 201811139060A CN 109344765 A CN109344765 A CN 109344765A
- Authority
- CN
- China
- Prior art keywords
- face
- cluster
- processing module
- same day
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of intelligent analysis method entering shop personnel analysis for chain shops, using following steps, step 1: capturing engine and the face of every frame picture is detected and number is provided with to facial image, which has unique value；The face picture collection of the same number is ranked up according to clarity, the highest picture of clarity is passed into identification engine；Step 2: identification engine judges whether the corresponding number of the face picture had been analyzed, if it is, entering step 9, otherwise, extracts face characteristic from the face picture, enters step 2；Solve the problems, such as that shop personnel's guest flow statistics is not accurate enough to entering, can flow of the people, personnel's attribute to chain shops, the progress at age and gender precisely identifies.
Description
Technical field
The present invention relates to field of video monitoring, and in particular to a kind of intellectual analysis for entering shop personnel analysis for chain shops
Method.
Background technique
For the chain shops being sold under line, the collection of customer data, including the volume of the flow of passengers, sex ratio, age level in field
Secondary, contact frequency etc., plus subsequent customer's taste analysis, the level of consumption analysis etc., formation visualized data, can it is fabulous at
For the marketing decision-making foundation of manager.One of them key problem to be solved of the chain shops of traditional retail is to each shops visitor
Did the analysis of flow data, today, shops carry out how many people? does is the volume of the flow of passengers in the shop A and the shop B how many? the comparison volume of the flow of passengers and income, two
Does is the conversion ratio of shops how many? current most of solutions, which are used, disposes top set demographics video camera in entrance, passes through
Head and both shoulders to people carry out identification decision, or pass in and out personnel by WIFI probe counts.Maximum existing for these schemes
Problem is: counting the data got only person-time statistics, cannot exclude the feelings such as salesman passes in and out number, same personnel repeatedly pass in and out
Condition causes data inaccurate；It can not also learn the attribute datas such as the age into shop personnel, gender simultaneously, it can not multi dimensional analysis Gu
Objective data.Also member, frequent visitor even confirmed thief etc. can not be differentiated, causes subsequent accurate service and security that can not keep up with.Now
There is the system based on face recognition technology, but has passed video flowing back in hind computation point generally by the video camera of front end
Analysis, due to the calculating of decoding video stream, it is likely that have delay, in addition a meter is installed by unlikely each shops of chain shops
Calculation machine, higher cost, deployment are complicated.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of intellectual analysis sides for entering shop personnel analysis for chain shops
Method, specific technical solution are as follows: a kind of intelligent analysis method entering shop personnel analysis for chain shops, it is characterised in that:
Using following steps,
Step 1: it captures engine and the face of every frame picture is detected and number is provided with to facial image, the number
With unique value；
The face picture collection of the same number is ranked up according to clarity, the highest picture of clarity is passed into knowledge
Other engine；
Step 2: identification engine judges whether the corresponding number of the face picture had been analyzed, if it is, entering step
Rapid 9, otherwise, face characteristic is extracted from the face picture, enters step 3；
Step 3: face characteristic and local employee library are compared processing module, enter step 9 if matching, otherwise
Enter step 4；
Step 4: processing module judges whether that being provided with night takes precautions against, and night prevention is, in the period that night specifies,
If finding non-company personnel in monitoring area, terminal system is notified to alarm, if it is, 5 are entered step, otherwise,
Enter step 6；
Step 5: processing module notice terminal system is alarmed, and enters step 9；
Step 6: the face characteristic and blacklist library are compared processing module, are pushed to terminal system if matching
System, enters step 9, otherwise enters step 7；
Step 7: the face characteristic and member bottom library are compared processing module, are pushed to terminal system if matching
System, enters step 9, otherwise enters step 8；
Step 8: the face characteristic and local frequent visitor library are compared processing module, are pushed to terminal system if matching
System, into next step；
Step 9: the face characteristic and corresponding number are sent to face cluster module, face cluster module by processing module
Classify to the face characteristic, enters step 10；
Step 10: repeating step 1 to step, next face number is analyzed.
To better implement the present invention, further:
The face cluster module specifically includes following process:
S1: being provided with interim cluster face database, includes temporarily cluster frequent visitor's group in cluster face database, common group of cluster, gathers
Class member's group；
S2: if it is member that the facial image is corresponding, being added cluster member's group on the same day, into S5, otherwise enters S3；
S3: if it is frequent visitor, cluster frequent visitor's group on the same day is added, and the life cycle of the frequent visitor was arranged from the same day and is opened
Begin, the life cycle of frequent visitor is N days, into S5, otherwise enters S4；
S4: if it is general customer, common group of cluster of the same day is added, into S5；
S5: judging whether in statistical time section, if it is, into S7, otherwise, into S6；
S6: returning to step S1, carries out clustering to next number；
The same day: finally being clustered face database and is sent to passenger flow statistics module by S7, is set with frequent visitor number threshold value C, is retrieved N days
Interior interim cluster face database pushes information to terminal if the quantity of general customer reaches frequent visitor number threshold value C immediately
System resets the interim cluster face database more than N days.
Further:
It is provided with passenger flow statistics module, including following process:
S1: the number finally clustered in face database to the same day counts；
S2: finally clustering the corresponding attribute of face database to the same day, which includes age bracket and gender, carries out classification system
Meter；
S3: sending the result to terminal system, and resets passenger flow statistics module.
The invention has the benefit that solve the problems, such as it is not accurate enough to shop personnel's guest flow statistics is entered, can to even
It locks a door flow of the people, personnel's attribute in shop, the progress at age and gender precisely identifies.It solves and high net value customer resolution is asked
Topic, can member, frequent visitor to shops distinguish；It solves the problems, such as to improve blacklist personal identification the peace of shops
Quan Xing.Solves the problems, such as system deployment complexity.For chain shops, video monitoring and face recognition technology are combined, taken the photograph
Face is quickly detected by neural network chip on camera, calculates passenger flow and attribute, identifies member, frequent visitor, sensitive personnel etc.,
Immediately result is pushed to backstage and periodically, and supports multiple cameras networking merging data, without special setting, i.e. dress is
With simplifying complicated system deployment process.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention.
Specific embodiment
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, 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.
A kind of intelligent analysis method entering shop personnel analysis for chain shops as shown in Figure 1:,
Using following steps,
Step 1: it captures engine and the face of every frame picture is detected and number is provided with to facial image, the number
With unique value；
The face picture collection of the same number is ranked up according to clarity, the highest picture of clarity is passed into knowledge
Other engine；
Step 2: identification engine judges whether the corresponding number of the face picture had been analyzed, if it is, entering step
Rapid 9, otherwise, face characteristic is extracted from the face picture, enters step 3；
Step 3: face characteristic and local employee library are compared processing module, enter step 9 if matching, otherwise
Enter step 4；
Step 4: processing module judges whether that being provided with night takes precautions against, and night prevention is, in the period that night specifies,
If finding non-company personnel in monitoring area, terminal system is notified to alarm, if it is, 5 are entered step, otherwise,
Enter step 6；
Step 5: processing module notice terminal system is alarmed, and enters step 9；
Step 6: the face characteristic and blacklist library are compared processing module, are pushed to terminal system if matching
System, enters step 9, otherwise enters step 7；
Step 7: the face characteristic and member bottom library are compared processing module, are pushed to terminal system if matching
System, enters step 9, otherwise enters step 8；
Step 8: the face characteristic and local frequent visitor library are compared processing module, are pushed to terminal system if matching
System, into next step；
Step 9: the face characteristic and corresponding number are sent to face cluster module, face cluster module by processing module
Classify to the face characteristic, enters step 10；
Step 10: repeating step 1 to step, next face number is analyzed.
Face cluster module specifically includes following process:
S1: being provided with interim cluster face database, includes temporarily cluster frequent visitor's group in cluster face database, common group of cluster, gathers
Class member's group；
S2: if it is member that the facial image is corresponding, being added cluster member's group on the same day, into S5, otherwise enters S3；
S3: if it is frequent visitor, cluster frequent visitor's group on the same day is added, and the life cycle of the frequent visitor was arranged from the same day and is opened
Begin, the life cycle of frequent visitor is N days, into S5, otherwise enters S4；
S4: if it is general customer, common group of cluster of the same day is added, into S5；
S5: judging whether in statistical time section, if it is, into S7, otherwise, into S6；
S6: returning to step S1, carries out clustering to next number；
The same day: finally being clustered face database and is sent to passenger flow statistics module by S7, is set with frequent visitor number threshold value C, is retrieved N days
Interior interim cluster face database pushes information to terminal if the quantity of general customer reaches frequent visitor number threshold value C immediately
System resets the interim cluster face database more than N days.
It is provided with passenger flow statistics module, including following process:
S1: the number finally clustered in face database to the same day counts；
S2: finally clustering the corresponding attribute of face database to the same day, which includes age bracket and gender, carries out classification system
Meter；
S3: sending the result to terminal system, and resets passenger flow statistics module.
Claims (3)
1. a kind of intelligent analysis method for entering shop personnel analysis for chain shops, it is characterised in that:
Using following steps,
Step 1: capturing engine and the face of every frame picture is detected and number is provided with to facial image, which has
Unique value；
The face picture collection of the same number is ranked up according to clarity, the highest picture of clarity is passed into identification and is drawn
It holds up；
Step 2: identification engine judges whether the corresponding number of the face picture had been analyzed, if it is, 9 are entered step,
Otherwise, face characteristic is extracted from the face picture, enters step 3；
Step 3: face characteristic and local employee library are compared processing module, enter step 9 if matching, otherwise enter
Step 4；
Step 4: processing module judges whether that being provided with night takes precautions against, and night prevention is, in the period that night specifies, if
Non- company personnel is found in monitoring area, then notifies terminal system to alarm, if it is, entering step 5, otherwise, is entered
Step 6；
Step 5: processing module notice terminal system is alarmed, and enters step 9；
Step 6: the face characteristic and blacklist library are compared processing module, are pushed to terminal system if matching, into
Enter step 9, otherwise enters step 7；
Step 7: the face characteristic and member bottom library are compared processing module, are pushed to terminal system if matching, into
Enter step 9, otherwise enters step 8；
Step 8: the face characteristic and local frequent visitor library are compared processing module, are pushed to terminal system if matching,
Into next step；
Step 9: the face characteristic and corresponding number are sent to face cluster module by processing module, and face cluster module is to this
Face characteristic is classified, and enters step 10；
Step 10: repeating step 1 to step, next face number is analyzed.
2. a kind of intelligent analysis method for entering shop personnel analysis for chain shops according to claim 1, it is characterised in that:
The face cluster module specifically includes following process:
S1: it is provided with interim cluster face database, interim cluster in face database includes cluster frequent visitor's group, common group of cluster, cluster meeting
Member's group；
S2: if it is member that the facial image is corresponding, being added cluster member's group on the same day, into S5, otherwise enters S3；
S3: if it is frequent visitor, being added cluster frequent visitor's group on the same day, and the life cycle of the frequent visitor be arranged since the same day, ripe
The life cycle of visitor is N days, into S5, otherwise enters S4；
S4: if it is general customer, common group of cluster of the same day is added, into S5；
S5: judging whether in statistical time section, if it is, into S7, otherwise, into S6；
S6: returning to step S1, carries out clustering to next number；
The same day: finally being clustered face database and is sent to passenger flow statistics module by S7, frequent visitor number threshold value C is set with, in retrieval N days
Interim cluster face database pushes information to terminal system if the quantity of general customer reaches frequent visitor number threshold value C immediately
System resets the interim cluster face database more than N days.
3. a kind of intelligent analysis method for entering shop personnel analysis for chain shops according to claim 1, it is characterised in that:
It is provided with passenger flow statistics module, including following process:
S1: the number finally clustered in face database to the same day counts；
S2: finally clustering the corresponding attribute of face database to the same day, which includes age bracket and gender, carries out statistic of classification；
S3: sending the result to terminal system, and resets passenger flow statistics module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811139060.6A CN109344765A (en) | 2018-09-28 | 2018-09-28 | A kind of intelligent analysis method entering shop personnel analysis for chain shops |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811139060.6A CN109344765A (en) | 2018-09-28 | 2018-09-28 | A kind of intelligent analysis method entering shop personnel analysis for chain shops |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109344765A true CN109344765A (en) | 2019-02-15 |
Family
ID=65307164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811139060.6A Pending CN109344765A (en) | 2018-09-28 | 2018-09-28 | A kind of intelligent analysis method entering shop personnel analysis for chain shops |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109344765A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147784A (en) * | 2019-06-26 | 2019-08-20 | 苏州金螳螂怡和科技有限公司 | A kind of passenger flow recognition of face flow system |
| CN111260400A (en) * | 2020-01-16 | 2020-06-09 | 广东超悦科技有限公司 | Member identification method and passenger flow analysis method |
| CN111340569A (en) * | 2020-03-27 | 2020-06-26 | 上海钧正网络科技有限公司 | Store people stream analysis method, device, system, terminal and medium based on cross-border tracking |
| WO2020207038A1 (en) * | 2019-04-12 | 2020-10-15 | 深圳壹账通智能科技有限公司 | People counting method, apparatus, and device based on facial recognition, and storage medium |
| CN111784387A (en) * | 2020-06-23 | 2020-10-16 | 大连中维世纪科技有限公司 | Multi-dimensional big data-based consumer brand loyalty analysis method |
| CN111784405A (en) * | 2020-07-10 | 2020-10-16 | 大连中维世纪科技有限公司 | Off-line store intelligent shopping guide method based on face intelligent recognition KNN algorithm |
| CN111783588A (en) * | 2020-06-23 | 2020-10-16 | 大连中维世纪科技有限公司 | Distributed intelligent passenger flow statistics effective de-duplication method |
| CN112365301A (en) * | 2020-12-09 | 2021-02-12 | 重庆满惠网络科技有限公司 | Marketing service big data application system and method thereof |
| CN112862192A (en) * | 2021-02-08 | 2021-05-28 | 青岛理工大学 | Crowd evacuation auxiliary decision-making system based on ant colony algorithm and improved social model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
| CN106326835A (en) * | 2016-08-05 | 2017-01-11 | 中国石油天然气股份有限公司安徽销售分公司 | Human face data collection statistical system and method for gas station convenience store |
| CN106998444A (en) * | 2017-02-14 | 2017-08-01 | 北京中科天云科技有限公司 | A kind of big data face monitoring system and device |
| CN107563343A (en) * | 2017-09-18 | 2018-01-09 | 南京甄视智能科技有限公司 | The self-perfection method and system of FaceID databases based on face recognition technology |
| 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 |
-
2018
- 2018-09-28 CN CN201811139060.6A patent/CN109344765A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
| CN106326835A (en) * | 2016-08-05 | 2017-01-11 | 中国石油天然气股份有限公司安徽销售分公司 | Human face data collection statistical system and method for gas station convenience store |
| CN106998444A (en) * | 2017-02-14 | 2017-08-01 | 北京中科天云科技有限公司 | A kind of big data face monitoring system and device |
| CN107563343A (en) * | 2017-09-18 | 2018-01-09 | 南京甄视智能科技有限公司 | The self-perfection method and system of FaceID databases based on face recognition technology |
| 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020207038A1 (en) * | 2019-04-12 | 2020-10-15 | 深圳壹账通智能科技有限公司 | People counting method, apparatus, and device based on facial recognition, and storage medium |
| CN110147784A (en) * | 2019-06-26 | 2019-08-20 | 苏州金螳螂怡和科技有限公司 | A kind of passenger flow recognition of face flow system |
| CN110147784B (en) * | 2019-06-26 | 2024-03-26 | 苏州朗捷通智能科技有限公司 | Passenger flow face identification flow system |
| CN111260400A (en) * | 2020-01-16 | 2020-06-09 | 广东超悦科技有限公司 | Member identification method and passenger flow analysis method |
| CN111340569A (en) * | 2020-03-27 | 2020-06-26 | 上海钧正网络科技有限公司 | Store people stream analysis method, device, system, terminal and medium based on cross-border tracking |
| CN111784387A (en) * | 2020-06-23 | 2020-10-16 | 大连中维世纪科技有限公司 | Multi-dimensional big data-based consumer brand loyalty analysis method |
| CN111783588A (en) * | 2020-06-23 | 2020-10-16 | 大连中维世纪科技有限公司 | Distributed intelligent passenger flow statistics effective de-duplication method |
| CN111784405A (en) * | 2020-07-10 | 2020-10-16 | 大连中维世纪科技有限公司 | Off-line store intelligent shopping guide method based on face intelligent recognition KNN algorithm |
| CN112365301A (en) * | 2020-12-09 | 2021-02-12 | 重庆满惠网络科技有限公司 | Marketing service big data application system and method thereof |
| CN112862192A (en) * | 2021-02-08 | 2021-05-28 | 青岛理工大学 | Crowd evacuation auxiliary decision-making system based on ant colony algorithm and improved social model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109344765A (en) | A kind of intelligent analysis method entering shop personnel analysis for chain shops | |
| CN105488478B (en) | Face recognition system and method | |
| CN110942545B (en) | Dense person entrance guard control system and method based on face recognition and video fence | |
| CN205451095U (en) | A face -identifying device | |
| US10445567B2 (en) | Pedestrian head identification method and system | |
| WO2017113822A1 (en) | Method, system and device for security check | |
| WO2017122258A1 (en) | Congestion-state-monitoring system | |
| US8744124B2 (en) | Systems and methods for detecting anomalies from data | |
| JP6854881B2 (en) | Face image matching system and face image search system | |
| CN102163290B (en) | Method for modeling abnormal events in multi-visual angle video monitoring based on temporal-spatial correlation information | |
| US7310442B2 (en) | Scene analysis surveillance system | |
| US8570376B1 (en) | Method and system for efficient sampling of videos using spatiotemporal constraints for statistical behavior analysis | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| CN108009690B (en) | Ground bus stealing group automatic detection method based on modularity optimization | |
| CN103049459A (en) | Feature recognition based quick video retrieval method | |
| Zhou et al. | Unusual event detection via multi-camera video mining | |
| CN104463232A (en) | Density crowd counting method based on HOG characteristic and color histogram characteristic | |
| CN101950448B (en) | Detection method and system for masquerade and peep behaviors before ATM (Automatic Teller Machine) | |
| Ryan | Crowd monitoring using computer vision | |
| Altowairqi et al. | A Review of the Recent Progress on Crowd Anomaly Detection | |
| CN112258707A (en) | Intelligent access control system based on face recognition | |
| Ahmed et al. | Efficient and effective automated surveillance agents using kernel tricks | |
| CN111369394B (en) | Scenic spot passenger flow volume statistical evaluation system and method based on big data | |
| Shuoyan et al. | Abnormal behavior detection based on the motion-changed rules | |
| CN210983509U (en) | Entry key group distribution and control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |