CN106558282A - A kind of market advertisement machine with pageview statistics - Google Patents
A kind of market advertisement machine with pageview statistics Download PDFInfo
- Publication number
- CN106558282A CN106558282A CN201710071297.4A CN201710071297A CN106558282A CN 106558282 A CN106558282 A CN 106558282A CN 201710071297 A CN201710071297 A CN 201710071297A CN 106558282 A CN106558282 A CN 106558282A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- advertisement machine
- pageview
- market
- face
- 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
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F9/00—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements
- G09F9/30—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements in which the desired character or characters are formed by combining individual elements
- G09F9/33—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements in which the desired character or characters are formed by combining individual elements being semiconductor devices, e.g. diodes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention is a kind of market advertisement machine with pageview statistics.The positive face through crowd, and then the input effect of the different advertisements of statistics are detected and are recognized by using monitoring camera, realize that the fixed point to advertisement is thrown in.It is an object of the invention to overcome the situation of existing advertisement machine input advertisement single, it is impossible to count the defect of pageview.
Description
Technical field
The present invention is a kind of market advertisement machine that can count advertisement pageview.Advertisement machine equipment includes:Body fuselage,
Led display screens, control mainboard, monitoring camera.The use scene of advertisement machine is the doorway in market passage OR gate shop, aobvious in led
While display screen display advertisement, can be counted in the crowd for passing by by monitoring camera, how many people is have viewed in broadcasting
Advertisement.Statistical data can be stored in locally, and businessman can carry out tuning to ad content and display form according to statistical data.
In terms of demographics, the correlation technique of recognition of face is mainly applied.
Background technology
The popular market advertisement machine of Vehicles Collected from Market, although wide variety, but be all passive, mechanical display advertisement content,
Can not active tuning is carried out to ad content and exhibition method.In internet arena, advertiser can pass through to count click volume,
Fixed point input is carried out to advertisement, preferably throw in effect to obtain.However, there is no user's point in the advertisement machine used in market
Situation about hitting, for this purpose, the present invention devises a kind of equipment that advertisement pageview is counted based on recognition of face.
The content of the invention
Present invention aims to the situation that existing advertisement machine throws in advertisement is single, it is impossible to count lacking for pageview
Fall into, there is provided one kind can in the advertisement field of market accurate count advertisement pageview, and the equipment of adjustment ad content and
Method.
For achieving the above object, the present invention is adopted the following technical scheme that:
Whole machine hardware configuration includes:Body fuselage, led display screens, control mainboard and monitoring camera.Software aspects, in control
Mainboard is integrated with a set of guest flow statistics algorithm based on recognition of face.
Face recognition module.The module based on it is proposed that one kind combine classical cascade structure and multilayer neural network
(CNN)Method for detecting human face realize, the funnel type cascade structure adopted by which(Funnel-Structured Cascade,
FuSt)It is specifically designed for multi-pose Face detection and designs, wherein introducing by the thick design concept to essence, has taken into account speed and essence
The balance of degree.FuSt cascade structures are made up of multiple quick LAB cascade classifiers for different attitudes at top, followed by
Several multi-layer perception (MLP)s based on SURF features(MLP)Cascade structure, finally by a unified MLP cascade structure(Equally
Based on SURF features)To process the candidate window of all attitudes, funnel shaped wide at the top and narrow at the bottom is presented on the whole.From upper past
Under, it is at all levels on grader and its feature for being adopted progressively become complicated, such that it is able to retaining face window and excluding
The non-face candidate window distinguished with face is increasingly difficult to, then front face is screened through convolutional neural networks, finally
The front face of advertisement machine is being watched.
Guest flow statistics module, a front face that each is detected, it is believed that is have person-time to have viewed an advertisement.
Different time sections, for different advertisements, respectively statistics viewing person-time, one user of formation vector interested.Through one section
After the statistics of time, using k-meas algorithms, user group and advertisement are classified, obtain final result:At certain
Between section to play certain advertisement be maximally effective, and provide statistical report form, be archived in local hard drive.
Description of the drawings
Fig. 1 is the hardware connection figure of the present invention.
Schematic diagrams of the Fig. 2 for convolutional neural networks.
Specific embodiment
The hardware composition and circuit for implementing the present invention connects referring to Fig. 1.The direction of advertisement body must be with crowd's flow direction in vertical
Nogata is to advertisement machine preferably leans against wall.
Claims (3)
1. a kind of market advertisement machine with pageview statistics, its design is characterised by:It is capable of browsing for automatic data collection advertisement
Amount information, and provide the adjustment suggestion of advertisement putting.
2. the market advertisement machine with pageview statistics according to claim 1, its realization is characterised by:By building
Vertical cascade nature detects face, distinguishes positive face, side face and non-face by convolutional neural networks.
3. the market advertisement machine with pageview statistics according to claim 1, its user is using being characterised by:Advertisement
The direction of machine must be vertical with crowd direction, and advertisement machine must lean against wall.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710071297.4A CN106558282A (en) | 2017-02-09 | 2017-02-09 | A kind of market advertisement machine with pageview statistics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710071297.4A CN106558282A (en) | 2017-02-09 | 2017-02-09 | A kind of market advertisement machine with pageview statistics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106558282A true CN106558282A (en) | 2017-04-05 |
Family
ID=58445559
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710071297.4A Pending CN106558282A (en) | 2017-02-09 | 2017-02-09 | A kind of market advertisement machine with pageview statistics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106558282A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679510A (en) * | 2017-10-19 | 2018-02-09 | 广州智能装备研究院有限公司 | A kind of bank client identifying system and method based on deep learning |
CN113052634A (en) * | 2021-03-30 | 2021-06-29 | 石震 | Advertisement management method, device, medium and mobile advertisement display equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3812835B2 (en) * | 2003-02-07 | 2006-08-23 | 株式会社河合楽器製作所 | Score recognition device |
CN101335864A (en) * | 2007-06-28 | 2008-12-31 | 当代天启技术(北京)有限公司 | Method and system for number of outdoor video receiving people statistic |
CN102129644A (en) * | 2011-03-08 | 2011-07-20 | 北京理工大学 | Intelligent advertising system having functions of audience characteristic perception and counting |
CN103943040A (en) * | 2014-04-30 | 2014-07-23 | 深圳市联建光电股份有限公司 | Advertisement machine and advertisement information display method |
CN105718868A (en) * | 2016-01-18 | 2016-06-29 | 中国科学院计算技术研究所 | Face detection system and method for multi-pose faces |
-
2017
- 2017-02-09 CN CN201710071297.4A patent/CN106558282A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3812835B2 (en) * | 2003-02-07 | 2006-08-23 | 株式会社河合楽器製作所 | Score recognition device |
CN101335864A (en) * | 2007-06-28 | 2008-12-31 | 当代天启技术(北京)有限公司 | Method and system for number of outdoor video receiving people statistic |
CN102129644A (en) * | 2011-03-08 | 2011-07-20 | 北京理工大学 | Intelligent advertising system having functions of audience characteristic perception and counting |
CN103943040A (en) * | 2014-04-30 | 2014-07-23 | 深圳市联建光电股份有限公司 | Advertisement machine and advertisement information display method |
CN105718868A (en) * | 2016-01-18 | 2016-06-29 | 中国科学院计算技术研究所 | Face detection system and method for multi-pose faces |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679510A (en) * | 2017-10-19 | 2018-02-09 | 广州智能装备研究院有限公司 | A kind of bank client identifying system and method based on deep learning |
CN113052634A (en) * | 2021-03-30 | 2021-06-29 | 石震 | Advertisement management method, device, medium and mobile advertisement display equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108600865B (en) | A kind of video abstraction generating method based on super-pixel segmentation | |
US11704936B2 (en) | Object tracking and best shot detection system | |
KR101741352B1 (en) | Attention estimation to control the delivery of data and audio/video content | |
AU2017268619B2 (en) | Systems and methods for analyzing event data | |
WO2017141454A1 (en) | Congestion analysis device, congestion analysis method, and congestion analysis program | |
CN110692076B (en) | Elevator advertisement putting method and device and advertisement putting equipment | |
CN109922373A (en) | Method for processing video frequency, device and storage medium | |
US20100177969A1 (en) | Method and System for Image Processing to Classify an Object in an Image | |
CN107431828B (en) | Method and system for identifying related media content | |
US20150271548A1 (en) | Video system with viewer analysis and methods for use therewith | |
CN107197384A (en) | The multi-modal exchange method of virtual robot and system applied to net cast platform | |
CN107087211A (en) | A kind of anchor shots detection method and device | |
CN101872422A (en) | People flow rate statistical method and system capable of precisely identifying targets | |
CN112837098A (en) | Mobile internet advertisement intelligent pushing system based on big data analysis | |
CN111062752A (en) | Elevator scene advertisement putting method and system based on audience group | |
CN106570449B (en) | A kind of flow of the people defined based on region and popularity detection method and detection system | |
CN110996148A (en) | Scenic spot multimedia image flow playing system and method based on face recognition | |
CN106558282A (en) | A kind of market advertisement machine with pageview statistics | |
CN111291617A (en) | Badminton event video wonderful segment extraction method based on machine learning | |
Chen et al. | A trajectory-based ball tracking framework with visual enrichment for broadcast baseball videos | |
CN113377327A (en) | Huge curtain MAX intelligent terminal in garage that possesses intelligent voice interaction function | |
Palanisamy et al. | Group behaviour profiling for detection of anomaly in crowd | |
NL2029338B1 (en) | Key person recognition in immersive video | |
Shishido et al. | Visual tracking method of a quick and anomalously moving badminton shuttlecock | |
CN108009486A (en) | Video frequency identifying method and system based on deep learning training reconstruct image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170405 |