Real-time estimation of point-of-interest in video surveillance based on visual fixation

Analyzing and interpreting the behavior of humans in a sequence of images from a video stream is an active and growing topic in computer vision and its applications. This paper focuses on real-time visual fixation analysis in which the study of human's gaze allows investigation and reasoning of a point-of-interest (POI) in the scene. The system's architecture comprises of 3 major components; (i) head detection, (ii) head direction detection and (iii) POI analysis. We employ the 3D color space (RGB) model as proposed in the installation of “15 Seconds of Fame” to detect skin color pixels for head detection. The head direction specified is based on estimating the orientation in tilt angle and pan angle using neural network. Finally, the POI is determined via the correlation between multiple head directions. Experimental results are given to demonstrate the reliability of our system in estimating POI in a sequence of low-resolution images.