Advertising board viewer flow analysis system
A technology for analyzing system and people flow, applied in the field of advertising monitoring, can solve the problem of not being able to know the situation after the advertisement is delivered, and achieve the effect of accurate and reliable statistics, high use value and high reference value
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0027] like figure 1 As shown, the present invention includes a billboard viewing people flow analysis system, including
[0028] Camera: Install the camera in the advertising site, so that the camera can accurately capture the audience watching the advertisement; there can be one or more advertising sites.
[0029] Data collection unit: communicate with the camera, collect the pictures taken by the camera, use the number analysis algorithm to analyze the collected pictures, and collect the number of viewers at the advertisement delivery point in real time;
[0030] Real-time analysis unit: Upload the number of viewers at each advertisement delivery point collected by the data collection unit in real time to the cloud server, present the real-time data of each advertisement delivery point in real time after analysis and calculation, and statistically analyze the real-time effect of advertisement delivery in certain designated areas;
[0031] Post-statistical analysis unit: pu...
Embodiment 2
[0034] This embodiment is preferably as follows on the basis of Embodiment 1: the number of people analysis algorithm is to extract features through deep learning, and use the trained model to predict the pictures taken by the input camera, so as to predict the number of viewers in the pictures taken by the input camera Mark and collect the number of viewers at the advertisement delivery point in real time. Using this kind of people analysis algorithm can quickly and accurately obtain the number of people data, and the later reference value is high.
[0035] The crowd analysis algorithm includes the following steps:
[0036]S1: Divide each camera picture into 13*13 rectangular blocks, and use clustering to predict the anchor point frame for each rectangular block. The size of the anchor point frame matches the size of different detected objects, so as to avoid multiple objects located in a rectangle. When only one object is detected in the block, at least 5 anchor frames are ...
PUM

Abstract
Description
Claims
Application Information

- Generate Ideas
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com