CN117035877A - Advertisement putting system and method based on gesture recognition - Google Patents
Advertisement putting system and method based on gesture recognition Download PDFInfo
- Publication number
- CN117035877A CN117035877A CN202311002570.XA CN202311002570A CN117035877A CN 117035877 A CN117035877 A CN 117035877A CN 202311002570 A CN202311002570 A CN 202311002570A CN 117035877 A CN117035877 A CN 117035877A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- people
- screen
- gesture recognition
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 230000000694 effects Effects 0.000 claims abstract description 12
- 230000009471 action Effects 0.000 claims description 14
- 230000006399 behavior Effects 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 9
- 230000009194 climbing Effects 0.000 claims description 5
- 239000011521 glass Substances 0.000 claims description 5
- 230000003796 beauty Effects 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 230000008713 feedback mechanism Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002716 delivery method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/174—Facial expression recognition
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
Abstract
The invention provides an advertisement putting system and method based on gesture recognition, relates to the technical field of image recognition, and is beneficial to improving the interactivity of an advertisement machine and an advertisement browser, so that the propaganda effect can be improved. By adopting a target detection, tracking and gesture recognition algorithm based on YOLO, the current characteristics of the number of people, the age, the sex, the interests and the like of consumers can be obtained. By analyzing the consumer's gesture and behavior patterns, more relevant and personalized advertising content may be provided.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an advertisement delivery system and method based on gesture recognition.
Background
Advertisements include commercial advertisements and non-commercial advertisements. The commercial advertisement is commercial advertisement, and the commercial advertisement takes commercial as a final target and bears commercial information which is used for promoting commodity sales and improving brand awareness of enterprises. Non-commercial advertisements, i.e., non-commercial advertisements, refer to public and cultural advertisements other than economical advertisements. Public welfare advertisements are advertisements for promoting public welfare, environmental protection, traditional culture and other relevant pure public welfare properties. The non-profit advertisement is played by television, electronic large screen or advertisement board. Electronic screens for public welfare are usually used at buses, subways or in schools.
With this way of playing video on an electronic screen, only a promotion of a certain aspect can be made for a period of time. For example, at a bus stop board, an electronic screen at a subway is only used for playing videos or pictures in a simple cycle, the interactivity is poor, and people do not pay attention to the information after simply knowing the information. The electronic screen has low advertising efficiency and poor advertising effect. This is effectively a waste of resources.
With the rapid development of the artificial intelligence field, the computer vision technology is gradually applied to the life of people, and brings convenience to the development of various industries. Some museums and science and technology museums have some interactive games, but the human body behaviors are generally identified through wireless sensors, the application scenes are limited, advertisement delivery cannot be carried out, the cost is high, and the method is not suitable for places with more intensive people.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an advertisement putting system and method based on gesture recognition, which are beneficial to improving the interactivity of an advertisement machine and an advertisement browser, thereby improving the propaganda effect. By adopting a target detection, tracking and gesture recognition algorithm based on YOLO, the current characteristics of the number of people, the age, the sex, the interests and the like of consumers can be obtained. By analyzing the consumer's gesture and behavior patterns, more relevant and personalized advertising content may be provided.
On one hand, the advertisement delivery system based on gesture recognition comprises a camera, a computer and an electronic screen; the three are connected in a wired or wireless mode;
the camera is arranged above the screen and is used for collecting pictures of people passing through the screen;
the computer performs gesture recognition, advertisement content selection and picture output; the computer specifically comprises a target detection module, a gesture recognition module, an advertisement content pushing module, a danger early warning module, a feedback module and an advertisement database: the target detection module is used for identifying the number of people, judging the crowding degree, adjusting the interaction degree between the system and the people, detecting the moving track of the people and keeping time in front of the screen; the gesture recognition module is used for recognizing the age, sex, wearing glasses, masks, hats, action modes, face orientations, using mobile phones, carrying object features, recognizing the actions of the person and storing data into the advertisement database; the advertisement content pushing module selects corresponding interaction degree according to the crowd quantity detected by the target detection module, personalized advertisement is put on the characteristics of the people identified by the gesture identification module, video signals are output, and interaction is carried out with the people by identifying the gestures and the action modes of the people; the danger early warning module recognizes potential dangers through the detection of the number of people, including potential dangerous behaviors of trampling, falling, climbing and knife holding walking, and reminds; the feedback module judges the advertisement putting effect according to the time of the detected person staying in front of the screen, the face orientation, whether the mobile phone is in use or not, the action mode and the face orientation characteristics, and feeds the advertisement putting effect back to the target detection module as feedback information; the advertisement database comprises the characteristics of the person identified by the gesture identification module, advertisement videos and numbers corresponding to the advertisement videos;
the electronic screen is used for displaying advertisement content.
On the other hand, the advertisement putting method based on gesture recognition is realized based on the advertisement putting system based on gesture recognition, and comprises the following steps of:
step 1: the camera collects pictures of pedestrians passing through the screen and transmits picture information to the computer, and at the moment, the electronic screen randomly plays advertisement information;
step 2: the computer carries out real-time target detection on the picture, allocates a unique ID for each target object, and carries out target tracking; judging the crowding degree according to the number of people, and adjusting the interaction degree;
when no person passes, the brightness of the screen is reduced to 50%, the cyclic playing culture propaganda content comprises urban beauty and propaganda slogans, and when the time that the person passes and stays in front of the screen is longer than the preset time, the screen is opened.
When the number of people is greater than the set threshold value of the number of people, the method enters a mode A, then starts the identification of potential hazards, and when dangerous behaviors such as stepping, falling, climbing and knife holding walking are identified, the screen display content is switched to the identified dangerous behavior content, and an alarm sound effect is sent out.
When people pass by and the number of people is smaller than a set number threshold value, a mode B is entered, various gesture recognition is realized for pedestrians, such as the recognition of the age and sex of the people, whether glasses, masks and caps are worn, the action mode and the face orientation are adopted, whether a mobile phone is used, whether articles are carried or not is judged, similarity measurement is carried out on the data and corresponding data in an advertisement library, a similarity index is obtained, and advertisement content with the highest similarity index is selected and played.
Step 3: and sending the selected advertisement information to an electronic screen for display.
Step 4: and generating a heat map to display the attention degree of people to different areas of the advertisement according to the gaze point and the stay time data of the people by adopting a feedback mechanism, improving the similarity index of the advertisement in the highlight part of the heat map by a set ratio, and storing the heat map in a storage device.
The beneficial effects of adopting above-mentioned technical scheme to produce lie in:
the invention provides an advertisement putting system and method based on target detection, which can realize accurate advertisement positioning and putting by analyzing the gesture and action of a consumer. The technology is expected to realize better user personalized experience in the advertising and marketing fields and improve advertising effects. The power consumption of a large screen is saved, and the utilization rate of the screen is improved.
Drawings
FIG. 1 is a schematic diagram of an advertisement delivery system according to an embodiment of the present invention;
in the figure, a 1-camera and a 2-electronic screen comprise a computer and a 3-base;
FIG. 2 is a flowchart of an advertisement delivery method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a computer device according to the present invention;
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
On one hand, the advertisement delivery system based on gesture recognition comprises a camera, a computer and an electronic screen; the three are connected in a wired or wireless mode; as particularly shown in fig. 1;
the camera captures images of pedestrians associated with the electronic screen in real time.
Wherein, the pedestrian image associated with the electronic screen refers to acquiring the pedestrian image passing through or staying at the electronic screen.
The camera collects pictures of pedestrians passing through the screen, and transmits picture information to the computer, and at the moment, the electronic screen randomly plays advertisement information.
The computer carries out real-time target detection on the picture, allocates a unique ID for each target object, and carries out target tracking; judging the crowding degree according to the number of people, and adjusting the interaction degree; as shown in fig. 2 and 3;
when no person passes, the electronic screen is closed, the time that the person passes and stays in front of the screen is longer than the preset time, and the screen is opened.
Specifically, the preset time can be set according to the actual situation.
In the present embodiment, it is assumed that the preset time is 1 second.
The number of people is compared with a preset threshold value of the number of people.
When the number of people is greater than the set threshold number of people, the method enters a mode A, then starts the identification of potential hazards, and when dangerous behaviors such as stepping, falling, climbing and knife holding walking are identified, the screen display content is switched to the identified dangerous behavior content, and an alarm sound effect is sent out.
When people pass by and the number of people is smaller than a set number threshold value, a mode B is entered, various gesture recognition is realized for pedestrians, such as the recognition of the age and sex of the people, whether glasses, masks and caps are worn, the action mode and the face orientation are adopted, whether a mobile phone is used, whether articles are carried or not is judged, similarity measurement is carried out on the data and corresponding data in an advertisement library, a similarity index is obtained, and advertisement content with the highest similarity index is selected and played.
The calculation process of the similarity analysis comprises the following steps: for two variables x= (x) 1 ,x 2 ,…,x n ) T ,y=(y 1 ,y 2 ,…,y n ) T Calculating covariance matrix:
inverting covariance matrix
Σ -1 =(Σ) -1
Calculating mahalanobis distance, i.e. similarity index
Wherein x is 1 ,x 2 ,...,x n And y is 1 ,y 2 ,...,y n Respectively corresponding to different characteristics of a set of data,respectively x 1 ,x 2 ,...,x n And y is 1 ,y 2 ,...,y n N is the number of data features in a set;
specifically, the preset threshold number of people may be set according to the actual situation.
In the present embodiment, it is assumed that the preset population threshold is 5 persons.
When the number of people is 0, the brightness of the screen is reduced to 50%, and the cyclic playing culture propaganda content comprises urban beauty and propaganda slogans.
When the number of people is 4, the mode B is entered.
When the number of people is 5, the mode A is entered.
In some embodiments, the average of the number of people may be calculated over a period of time, compared to a threshold number of people.
And sending the selected advertisement information to an electronic screen for display.
The electronic screen can display various advertisement contents, such as commodity advertisement, traditional festival culture, scenic spot propaganda advertisement and minority culture.
And generating a heat map to display the attention degree of people to different areas of the advertisement according to the gaze point and the stay time data of the people by adopting a feedback mechanism, improving the similarity index of the advertisement in the highlight part of the heat map by a set ratio, and storing the heat map in a storage device.
And judging whether the gazing point is an electronic screen according to the face orientation of the person, and judging whether the user is watching the content of the electronic screen according to the action mode of the person and the action of the mobile phone.
Specifically, the set ratio may be set according to the actual situation. The adjustable range of the set ratio is: more than 1% and less than 50%.
Specifically, a worker may read heat map data from the data interface.
In some embodiments, after the feedback step, a step of generating voice indication information is further included. After the display end displays the advertisement content, voice indication information is generated, so that the target object can act (such as dangerous behavior, please notice) according to the voice indication, and the advertising effect of the advertising content is improved.
In public transportation facilities such as installation and bus stations, subway stations and the like, the content displayed by the electronic screen is real-time information of buses and subways.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.
Claims (4)
1. An advertisement putting system based on gesture recognition is characterized by comprising a camera, a computer and an electronic screen; the three are connected in a wired or wireless mode;
the camera is arranged above the screen and is used for collecting pictures of people passing through the screen;
the computer performs gesture recognition, advertisement content selection and picture output;
the electronic screen is used for displaying advertisement content.
2. The advertisement delivery system based on gesture recognition as set forth in claim 1, wherein the computer specifically comprises a target detection module, a gesture recognition module, an advertisement content pushing module, a danger early warning module, a feedback module and an advertisement database;
the target detection module is used for identifying the number of people, judging the crowding degree, adjusting the interaction degree between the system and the people, detecting the moving track of the people and keeping time in front of the screen; the gesture recognition module is used for recognizing the age, sex, wearing glasses, masks, hats, action modes, face orientations, using mobile phones, carrying object features, recognizing the actions of the person and storing data into the advertisement database; the advertisement content pushing module selects corresponding interaction degree according to the crowd quantity detected by the target detection module, personalized advertisement is put on the characteristics of the people identified by the gesture identification module, video signals are output, and interaction is carried out with the people by identifying the gestures and the action modes of the people; the danger early warning module recognizes potential dangers through the detection of the number of people, including potential dangerous behaviors of trampling, falling, climbing and knife holding walking, and reminds; the feedback module judges the advertisement putting effect according to the time of the detected person staying in front of the screen, the face orientation, whether the mobile phone is in use or not, the action mode and the face orientation characteristics, and feeds the advertisement putting effect back to the target detection module as feedback information; the advertisement database comprises the characteristics of the person identified by the gesture identification module, advertisement videos and numbers corresponding to the advertisement videos.
3. An advertisement putting method based on gesture recognition, which is realized based on the advertisement putting system based on gesture recognition as set forth in claim 1, and is characterized by comprising the following steps:
step 1: the camera collects pictures of pedestrians passing through the screen and transmits picture information to the computer, and at the moment, the electronic screen randomly plays advertisement information;
step 2: the computer carries out real-time target detection on the picture, allocates a unique ID for each target object, and carries out target tracking; judging the crowding degree according to the number of people, and adjusting the interaction degree;
step 3: sending the selected advertisement information to an electronic screen for display;
step 4: and generating a heat map to display the attention degree of people to different areas of the advertisement according to the gaze point and the stay time data of the people by adopting a feedback mechanism, improving the similarity index of the advertisement in the highlight part of the heat map by a set ratio, and storing the heat map in a storage device.
4. The method for putting advertisements based on gesture recognition according to claim 3, wherein the step 2 is specifically that when no person passes, the brightness of the screen is reduced to 50%, the cyclic play culture propaganda content comprises urban beauty and publicity slogans, and when the person passes and stays in front of the screen for more than a preset time, the screen is opened;
when the number of people is greater than a set threshold value of the number of people, entering a mode A, then starting the identification of potential hazards, and when dangerous behaviors such as stepping, falling, climbing and knife holding walking are identified, switching screen display contents into the identified dangerous behavior contents and sending out alarm sound effects;
when people pass by and the number of people is smaller than a set number threshold value, a mode B is entered, various gesture recognition is realized for pedestrians, such as the recognition of the age and sex of the people, whether glasses, masks and caps are worn, the action mode and the face orientation are adopted, whether a mobile phone is used, whether articles are carried or not is judged, similarity measurement is carried out on the data and corresponding data in an advertisement library, a similarity index is obtained, and advertisement content with the highest similarity index is selected and played.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311002570.XA CN117035877A (en) | 2023-08-09 | 2023-08-09 | Advertisement putting system and method based on gesture recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311002570.XA CN117035877A (en) | 2023-08-09 | 2023-08-09 | Advertisement putting system and method based on gesture recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117035877A true CN117035877A (en) | 2023-11-10 |
Family
ID=88634831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311002570.XA Pending CN117035877A (en) | 2023-08-09 | 2023-08-09 | Advertisement putting system and method based on gesture recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117035877A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117912373A (en) * | 2024-03-20 | 2024-04-19 | 内江广播电视台 | Intelligent off-line movable news media announcing device and method |
-
2023
- 2023-08-09 CN CN202311002570.XA patent/CN117035877A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117912373A (en) * | 2024-03-20 | 2024-04-19 | 内江广播电视台 | Intelligent off-line movable news media announcing device and method |
CN117912373B (en) * | 2024-03-20 | 2024-05-31 | 内江广播电视台 | Intelligent off-line movable news media declaring method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101616652B1 (en) | Digital advertising system | |
CN104486680A (en) | Video-based advertisement pushing method and system | |
US20080059994A1 (en) | Method for Measuring and Selecting Advertisements Based Preferences | |
US20120140069A1 (en) | Systems and methods for gathering viewership statistics and providing viewer-driven mass media content | |
US20130138499A1 (en) | Usage measurent techniques and systems for interactive advertising | |
JP5002441B2 (en) | Marketing data analysis method, marketing data analysis system, data analysis server device, and program | |
KR101348142B1 (en) | The method for providing the customized marketing contens for the customers classified as individuals or groups by using face recognition technology and the system thereof | |
JP2010113313A (en) | Electronic advertisement apparatus, electronic advertisement method and program | |
KR20150029514A (en) | Playing method and electronic apparatus information | |
TW201033908A (en) | System and method for counting people flow | |
JP6498900B2 (en) | Advertisement evaluation system, advertisement evaluation method | |
CN117035877A (en) | Advertisement putting system and method based on gesture recognition | |
CN102446270A (en) | Monitoring device and method based on face recognition | |
KR20190108226A (en) | Display control device and display apparatus including the same | |
Yu et al. | AI-based targeted advertising system | |
US9536158B2 (en) | Biometric based demography tool | |
CN111724199A (en) | Intelligent community advertisement accurate delivery method and device based on pedestrian active perception | |
CN110324683B (en) | Method for playing advertisement on digital signboard | |
CN113850627A (en) | Elevator advertisement display method and device and electronic equipment | |
KR20220021689A (en) | System for artificial intelligence digital signage and operating method thereof | |
KR102180258B1 (en) | Display control device | |
TWI552098B (en) | Electronic billboarding system based on inter - party relationship judgment | |
CN110287359A (en) | A kind of man-machine perception interactive system and method in city based on big data | |
CN111160945A (en) | Advertisement accurate delivery method and system based on video technology | |
WO2022023831A1 (en) | Smart display application with potential to exhibit collected outdoor information content using iot and ai platforms |
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 |