Pervasive Retail Strategy Using a Low-Cost Free Gaze Estimation System

This paper proposes a pervasive retail architecture based on a free human gaze estimation system. The main aim of the paper is to investigate the possibility to automatically understand the behavior of the persons looking at a shop window: this is done by a gaze estimation technique that uses a RGB-D device in order to extract head pose information from which a fast geometric technique then evaluates the focus of attention of the persons in the scene (even more persons at the same time). The main contribution concerns with the application into this challenging research field of a gaze estimation working without any initial calibration and, in spite of this, able to properly deal with completely unaware persons moving in unconstrained environments. Preliminary experiments were conducted in our lab in order to quantitative validate the accuracy of the gaze estimation on different benchmarks of persons. Then the qualitative evaluation of the effectiveness of the proposed architecture was conducted in a real shop window demonstrating the ability to deal with real challenging environmental conditions.