Audience measurement using a top-view camera and oriented trajectories

TL;DR

This paper introduces a method using top-view depth cameras to estimate the likelihood of advertising visibility by tracking head trajectories and orientations of passersby.

Contribution

It presents a novel approach combining depth sensing and head orientation analysis for accurate audience measurement in advertising spaces.

Findings

Effective head detection and orientation estimation using depth sensors

Trajectory tracking enables dynamic attention estimation

Method improves accuracy of audience measurement in real-time

Abstract

A crucial aspect for selecting optimal areas for commercial advertising is the probability with which that publicity will be seen. This paper presents a method based on top-view camera measurement, where the probability of viewing is estimated according to the trajectories and movements of the head of the passerby individuals in the area of interest. Using a camera with a depth sensor, the head of the people in the range of view can be detected and modeled. That method allows determining the orientation of the head which is used to estimate the direction of vision. A tracking by detection algorithm is used to compute the trajectory of each user. The attention given at each advertising spot is estimated based on the trajectories and head orientations of the individuals in the area of interest