Out-of-home Ad Viewer Counting via Image Orientation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for measuring the effectiveness of out-of-home advertising, such as DEC and EOI, rely on statistical extrapolations and do not accurately account for the number of individuals who actually view advertisements, leading to potential inaccuracies in billing and targeting.
Innovation Solution
A system utilizing digital cameras and computer processing to analyze images of individuals in proximity to advertisements, determining whether their eyes or faces are directed at the ad, thereby providing a more accurate count of actual viewers, which can be used for billing and targeting improvements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If DEC or EOI measurement methods are used, then billing and advertising effectiveness can be estimated, but the measurement precision is insufficient because these methods rely on statistical extrapolations rather than actual viewer data
Solution Approach 1:
The patent replaces statistical estimation methods (DEC/EOI) with automated image recognition technology. Digital cameras capture images of pedestrians, and computer processing automatically identifies and counts individuals whose eyes or faces are directed at advertisements. This substitution of mechanical/automated systems for statistical methods achieves precise actual viewer counting without manual intervention.
2Measurement precision
If manual counting of actual viewers is implemented, then measurement precision improves, but the productivity and efficiency deteriorate due to the time-consuming nature of manual processes
Solution Approach 1:
The system enables self-service automated counting through digital cameras that continuously capture images and computer processing algorithms that automatically identify and count viewers. The system processes images, determines whether eyes or faces are directed at ads, and generates billing data without human intervention, achieving both high precision and high efficiency simultaneously.
Solution Approach 2:
Manual counting operations are replaced by automated image recognition systems. The computer processing automatically analyzes captured images, identifies individuals viewing advertisements, and generates accurate counts, eliminating the need for manual observation and counting while maintaining high measurement precision.
3Reliability
If digital image processing is implemented to accurately count actual viewers, then billing accuracy improves, but the device complexity and implementation cost increase
Solution Approach 1:
The patent introduces digital cameras as intermediary devices between the advertisement and the counting process. These cameras capture images of pedestrians, which are then processed by computer algorithms to identify viewers. This intermediary system provides reliable automated counting data for accurate billing while managing implementation complexity through standardized camera and processing components.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Method of monitoring real time demographic information to cause an advertisement to be played on a display, the method comprising: determining a total number of persons who faced the advertisement during a period of time by (702): obtaining via a digital camera an image of a the person (704), processing the image to determine whether the person is facing the advertisement (706), storing in a database data indicating whether and for how long the person faced the advertisement (708); retrieving from the database data representing the total number of persons who faced the advertisement during the period of time (712); processing each of the images obtained to determine a demographic of each person who faced the advertisement; monitoring a campaign budget in respect of the advertisement for the period of time; and, in response to the monitoring indicating that the campaign budget has been reached, ceasing to play the advertisement on the display.