CN108875695A - Visit scene interest stream of people's statistical analysis technique based on machine vision - Google Patents
Visit scene interest stream of people's statistical analysis technique based on machine vision Download PDFInfo
- Publication number
- CN108875695A CN108875695A CN201810728713.8A CN201810728713A CN108875695A CN 108875695 A CN108875695 A CN 108875695A CN 201810728713 A CN201810728713 A CN 201810728713A CN 108875695 A CN108875695 A CN 108875695A
- Authority
- CN
- China
- Prior art keywords
- visitor
- face
- people
- stream
- head portrait
- 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
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of visit scene interest stream of people's statistical analysis technique based on machine vision, including：The video data of shooting is simultaneously uploaded to host by camera captured in real-time；The host obtains the image in camera preview frame, carries out Face datection, judges whether there is face appearance in image；If having detected face appearance, then the face that tracing detection arrives is until face disappearance, determines a visitor by display area.By guiding target Customer Acquisition direct picture, and direct picture is provided to user, benign feedback is provided, and then obtain quality relative to traditional stream of people's statistical more hi-vision, and there is higher identification accuracy.And use face tracking technology, the accuracy of guarantor's stream statistics.And have and export the stream of people in real time by situation, accurate target customer is provided for businessman.
Description
Technical field
The invention belongs to image identification technical field more particularly to a kind of visit scene interest stream of peoples based on machine vision
Statistical analysis technique.
Background technique
Stream of people's data statistics carries out feature identification to stranger, it is emerging to find sense applied to the scene of the brand promotions such as exhibition
Interesting user analyzes collected user information, show that portion about Interests User information population characteristic, is determined for company
Plan provides data and supports.In traditional approach, by access hatch, this physical structure mode counts the stream of people, but aforesaid way
It will limit stream of people's flowing velocity.Or by the modes such as admission ticket, card, preparatory statistical number of person, but aforesaid way presence can not weigh
It is multiple to use, it is at high cost.Or also have through infrared detection mode, for infrared detection when flow of the people is excessive, detection accuracy is low,
It is single to acquire information, so that business reference is low.In order to solve the above technical problems, those skilled in the art devise
A kind of elevator passenger identification of CN106379788A and stream of people's statistic device and side or CN105718873A are based on binocular vision
Stream of people's analysis method etc., but aforesaid way exists and need to be acquired in advance to user information or stranger's stream statistics effect
The defects of difference, false recognition rate is high.
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of visit scene interest stream of people's statistical based on machine vision
Analysis method.In order to which some aspects of the embodiment to disclosure have a basic understanding, simple summary is shown below.This is general
Including part is not extensive overview, nor to determine key/critical component or describe the protection scope of these embodiments.Its
Sole purpose is that some concepts are presented with simple form, in this, as the preamble of following detailed description.
The present invention adopts the following technical scheme that：
In some alternative embodiments, a kind of visit scene interest stream of people statistical analysis side based on machine vision is provided
Method, including：The video data of shooting is simultaneously uploaded to host by camera captured in real-time；The host obtains the figure in camera preview frame
Picture carries out Face datection, judges whether there is face appearance in image；If having detected face appearance, then tracing detection arrives
Face determines a visitor by display area until face disappearance.
In some alternative embodiments, the visit scene interest stream of people statistical analysis side based on machine vision
Method further includes：In face that tracing detection arrives until during face disappears, the host save simultaneously visitor's head portrait,
The time of visitor's head portrait appearance and the collected relevant information from visitor's head portrait, the relevant information include：Age
And gender；The time and acquired from visitor's head portrait that the host occurs according to visitor's head portrait, visitor's head portrait
The visitor stream of people passes through situation data at times for the relevant information output arrived, and the stream of people of visitor at times passes through situation data
For the age of the visitor for the appearance being distributed in each period, gender and collected number.
In some alternative embodiments, the visit scene interest stream of people statistical analysis side based on machine vision
Method further includes：The host retrieves visitor's head portrait of preservation, if retrieving duplicate visitor's head portrait, then will
Duplicate visitor's head portrait is labeled as same visitor；The host demarcates the duplicate visitor's head portrait retrieved,
It screens as target user interested.
In some alternative embodiments, the visit scene interest stream of people statistical analysis side based on machine vision
Method further includes：The host obtains the video data that the camera uploads, and handles the video data and believes visitor face
Breath is issued to display and carries out real-time display.
In some alternative embodiments, visitor's facial information includes：Face location, the age, gender, face value,
Most similar star, expression, whether wearing spectacles.
Beneficial effect brought by the present invention：The present invention mentions user by guiding target Customer Acquisition direct picture
Benign feedback is provided for direct picture, and then obtains quality relative to traditional stream of people's statistical more hi-vision, and have higher
Identify accuracy.And use face tracking technology, the accuracy of guarantor's stream statistics.And has and export the stream of people in real time by feelings
Condition provides accurate target customer for businessman.
For the above and related purposes, one or more embodiments include being particularly described below and in claim
In the feature that particularly points out.Certain illustrative aspects are described in detail in the following description and the annexed drawings, and its instruction is only
Some modes in the utilizable various modes of the principle of each embodiment.Other benefits and novel features will be under
The detailed description in face is considered in conjunction with the accompanying and becomes obvious, the disclosed embodiments be all such aspects to be included and they
Be equal.
Detailed description of the invention
Fig. 1 is a kind of process signal of the live interest stream of people's statistical analysis technique of visit based on machine vision of the present invention
Figure.
Specific embodiment
The following description and drawings fully show specific embodiments of the present invention, to enable those skilled in the art to
Practice them.Other embodiments may include structure, logic, it is electrical, process and other change.Embodiment
Only represent possible variation.Unless explicitly requested, otherwise individual components and functionality is optional, and the sequence operated can be with
Variation.The part of some embodiments and feature can be included in or replace part and the feature of other embodiments.This hair
The range of bright embodiment includes equivalent obtained by the entire scope of claims and all of claims
Object.
As shown in Figure 1, in some illustrative embodiments, providing a kind of visit scene interest people based on machine vision
Stream statistics analysis method is identified using machine vision technique by face characteristic, is collected visitor's information, is passed through face retrieval
Information is arranged, the feature of user is visited in output.
Visit scene interest stream of people's statistical analysis technique based on machine vision of the invention, including：
101：The video data of shooting is simultaneously uploaded to host by camera captured in real-time.
102：Host obtains the image in camera preview frame, carries out Face datection, judges whether there is face appearance in image.
103：If having detected face appearance, then the face that tracing detection arrives is until face disappearance, determines a visit
Person passes through display area.With Face datection, face tracking scheme is used, it is ensured that face occurs to disappearance, is confirmed to be one
People passes through, it can be ensured that a face occurs primary and once recorded, and ensures that the precision counted by the stream of people.
104：In the face that tracing detection arrives until during face disappears, host saves visitor's head portrait, ginseng simultaneously
The time of onlooker's head portrait appearance and the collected relevant information from visitor's head portrait, relevant information include：Age and gender.
105：Host is collected according to visitor's head portrait, the time of visitor's head portrait appearance and from visitor's head portrait
The visitor stream of people passes through situation data at times for relevant information output, and the visitor stream of people is to be distributed in by situation data at times
Age, gender and the collected number of the visitor of appearance in each period.Collected information is analyzed, is obtained
Portion provides data for corporate decision and supports about Interests User information population characteristic.The stream of people is realized using face tracking technique
Statistics.
106：Host retrieves visitor's head portrait of preservation, if retrieving duplicate visitor's head portrait, then will weigh
Multiple visitor's head portrait is labeled as same visitor.The output that can guarantee the precision data after visiting, for visitor's head
As being retrieved, for repeating face filtering, statistical accuracy is improved.
107：Host demarcates the duplicate visitor's head portrait retrieved, screens as target use interested
Family.The present invention is applied to the scene of the brand promotions such as exhibition, carries out face characteristic identification to stranger, finds target use interested
Interests User is accurately positioned in family.
108：Host obtains the video data that institute's camera uploads, and handles video data and is issued to visitor's facial information
Display carries out real-time display.Visitor's facial information includes：Face location, age, gender, face value, most similar star, table
Feelings, whether wearing spectacles.Interest visitor realtime curve realized by display, can also the corresponding filter of AR technology addition
Mirror attracts the attention of visitor through the above way, improves the interest that visitor visits, and improves the chance for obtaining positive face, from
And improve the precision of statistics.
Display is for attracting user, the display real-time display interface UI real-time display leftmost side and its rightmost side visitor
Information, shown using UI and attract target user, can configure different templates according to different environmental demands, changeability is high.
The present invention, with for running whole system, display is a HDMI display, is used for RK3399 development board
User information is visited in display in real time, and the camera of camera for acquiring video data in real time.When visitor is demonstrated the display in area
Device or showpiece are attracted, and visitor, which turns one's attention to, visits live, the face feature of camera real-time capture to visitor, constantly
The reciprocal acquisition whole process that captures passes by and invests expression in the eyes the visitor of this side, when puting on display terminates, output point
Analyse processing result.
It should also be appreciated by one skilled in the art that various illustrative logical boxs, mould in conjunction with the embodiments herein description
Electronic hardware, computer software or combinations thereof may be implemented into block, circuit and algorithm steps.In order to clearly demonstrate hardware and
Interchangeability between software surrounds its function to various illustrative components, frame, module, circuit and step above and carries out
It is generally described.Hardware is implemented as this function and is also implemented as software, depends on specific application and to entire
The design constraint that system is applied.Those skilled in the art can be directed to each specific application, be realized in a manner of flexible
Described function, still, this realization decision should not be construed as a departure from the scope of protection of this disclosure.
Claims (5)
1. visit scene interest stream of people's statistical analysis technique based on machine vision, which is characterized in that including：
The video data of shooting is simultaneously uploaded to host by camera captured in real-time；
The host obtains the image in camera preview frame, carries out Face datection, judges whether there is face appearance in image；
If having detected face appearance, then the face that tracing detection arrives is until face disappearance, determines a visitor by exhibition
Show region.
2. visit scene interest stream of people's statistical analysis technique according to claim 1 based on machine vision, feature exist
In further including：
In the face that tracing detection arrives until during face disappears, the host saves visitor's head portrait, visitor simultaneously
The time of head portrait appearance and the collected relevant information from visitor's head portrait, the relevant information include：Age and gender；
The host is collected according to visitor's head portrait, the time of visitor's head portrait appearance and from visitor's head portrait
The visitor stream of people passes through situation data at times for relevant information output, and the stream of people of visitor at times is point by situation data
Age, gender and the collected number of the visitor of appearance of the cloth within each period.
3. visit scene interest stream of people's statistical analysis technique according to claim 2 based on machine vision, feature exist
In further including：
The host retrieves visitor's head portrait of preservation, then will be duplicate if retrieving duplicate visitor's head portrait
Visitor's head portrait is labeled as same visitor；
The host demarcates the duplicate visitor's head portrait retrieved, screens as target user interested.
4. visit scene interest stream of people's statistical analysis technique according to claim 3 based on machine vision, feature exist
In further including：
The host obtains the video data that the camera uploads, and handles the video data and issues visitor's facial information
Real-time display is carried out to display.
5. visit scene interest stream of people's statistical analysis technique according to claim 4 based on machine vision, feature exist
In visitor's facial information includes：Whether face location the age, gender, face value, most similar star, expression, is worn
Glasses.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810728713.8A CN108875695A (en) | 2018-07-05 | 2018-07-05 | Visit scene interest stream of people's statistical analysis technique based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810728713.8A CN108875695A (en) | 2018-07-05 | 2018-07-05 | Visit scene interest stream of people's statistical analysis technique based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108875695A true CN108875695A (en) | 2018-11-23 |
Family
ID=64299388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810728713.8A Pending CN108875695A (en) | 2018-07-05 | 2018-07-05 | Visit scene interest stream of people's statistical analysis technique based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875695A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359628A (en) * | 2018-11-28 | 2019-02-19 | 上海风语筑展示股份有限公司 | A kind of exhibition big data collection analysis platform |
| CN110765919A (en) * | 2019-10-18 | 2020-02-07 | 山东浪潮人工智能研究院有限公司 | Interview image display system and method based on face detection |
| CN110784453A (en) * | 2019-09-27 | 2020-02-11 | 广州市水一方信息科技有限公司 | Intelligent identification system for exhibition hall and exhibition hall |
| CN113128403A (en) * | 2021-04-19 | 2021-07-16 | 深圳市上源艺术设计有限公司 | Intelligent exhibit display method and system based on data analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105718873A (en) * | 2016-01-18 | 2016-06-29 | 北京联合大学 | People stream analysis method based on binocular vision |
| CN105809178A (en) * | 2014-12-31 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Population analyzing method based on human face attribute and device |
| CN108197971A (en) * | 2017-12-08 | 2018-06-22 | 北京天正聚合科技有限公司 | Information collecting method, information processing method, apparatus and system |
| CN108230032A (en) * | 2017-12-28 | 2018-06-29 | 珠海市君天电子科技有限公司 | Determine method, apparatus, electronic equipment and the storage medium of the going value of business entity |
-
2018
- 2018-07-05 CN CN201810728713.8A patent/CN108875695A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809178A (en) * | 2014-12-31 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Population analyzing method based on human face attribute and device |
| CN105718873A (en) * | 2016-01-18 | 2016-06-29 | 北京联合大学 | People stream analysis method based on binocular vision |
| CN108197971A (en) * | 2017-12-08 | 2018-06-22 | 北京天正聚合科技有限公司 | Information collecting method, information processing method, apparatus and system |
| CN108230032A (en) * | 2017-12-28 | 2018-06-29 | 珠海市君天电子科技有限公司 | Determine method, apparatus, electronic equipment and the storage medium of the going value of business entity |
Non-Patent Citations (1)
| Title |
|---|
| 姚博韬 等: "一种基于人脸检测的客流统计分析方法", 《中国通信学会信息通信网络技术委员会2015年年会论文集》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359628A (en) * | 2018-11-28 | 2019-02-19 | 上海风语筑展示股份有限公司 | A kind of exhibition big data collection analysis platform |
| CN110784453A (en) * | 2019-09-27 | 2020-02-11 | 广州市水一方信息科技有限公司 | Intelligent identification system for exhibition hall and exhibition hall |
| CN110765919A (en) * | 2019-10-18 | 2020-02-07 | 山东浪潮人工智能研究院有限公司 | Interview image display system and method based on face detection |
| CN113128403A (en) * | 2021-04-19 | 2021-07-16 | 深圳市上源艺术设计有限公司 | Intelligent exhibit display method and system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104361327B (en) | A kind of pedestrian detection method and system | |
| CN108875695A (en) | Visit scene interest stream of people's statistical analysis technique based on machine vision | |
| CN108229376B (en) | Method and device for detecting blinking | |
| CN104951773B (en) | A kind of real-time face recognition monitoring system | |
| US9639747B2 (en) | Online learning method for people detection and counting for retail stores | |
| CN109272347A (en) | A kind of statistical analysis technique and system of shops's volume of the flow of passengers | |
| CN108549886A (en) | A kind of human face in-vivo detection method and device | |
| CN108600865B (en) | A kind of video abstraction generating method based on super-pixel segmentation | |
| CN109359625A (en) | The method and system of customer identification is judged based on head and shoulder detection and face recognition technology | |
| CN107408205A (en) | Foreground and background is distinguished with infrared imaging | |
| CN104112209A (en) | Audience statistical method of display terminal, and audience statistical system of display terminal | |
| US8879789B1 (en) | Object analysis using motion history | |
| WO2021043090A1 (en) | Method and apparatus for compiling statistics on number of customers, and electronic device and readable storage medium | |
| CA3014365C (en) | System and method for gathering data related to quality of service in a customer service environment | |
| CN109902550A (en) | The recognition methods of pedestrian's attribute and device | |
| Shahrian et al. | Temporally coherent and spatially accurate video matting | |
| CA3158925A1 (en) | Customer path tracking method and system | |
| CN106558061A (en) | A kind of cash register loss prevention method and system based on cloud computing | |
| CN109074498A (en) | Visitor's tracking and system for the region POS | |
| JP2020140630A (en) | Fixation point estimation system, fixation point estimation method, fixation point estimation program, and information recording medium for recording the same | |
| Ardeshir et al. | Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignment | |
| Szankin et al. | Long distance vital signs monitoring with person identification for smart home solutions | |
| Lucio et al. | Simultaneous iris and periocular region detection using coarse annotations | |
| Tran et al. | Adaptive pulsatile plane for robust noncontact heart rate monitoring | |
| CN103927518A (en) | Facial feature extraction method for facial analysis 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |