Robust Region-of-Interest Determination Based on User Attention Model Through Visual Rhythm Analysis

This paper investigates a user attention model based on the visual rhythm analysis for automatically determining the region-of-interest (ROI) in a video. The visual rhythm, an abstraction of a video, is a thumbnail version of a fully video by a 2D image that captures the temporal information of a video sequence. Four sampling lines, including diagonal, anti-diagonal, vertical and horizontal lines, are employed to obtain four visual rhythm maps in order to analyze the location of the ROI from video data. Via the variation on visual rhythms, object and camera motions can be efficiently distinguished. The proposed scheme can extract the ROI accurately with very low computational complexity. The promising results from the experiments demonstrate that the moving object is effectively and efficiently extracted.