Detection and Classification of Repetitious Human Motions Combining Shift Variant and Invariant Features

Abstract

Detection and classification of significant human motions are important tasks when analyzing a video that records human activities. Among various human motions, we consider that repetitious motions are specially important since they are usually results of activities with clear intentions. In this paper, we propose and evaluate a method that detects video segments that contain repetitious motions, which is robust to motion shift. Experimental results showed the effectiveness of the proposed method compared to conventional methods. In addition, we report a preliminary result of an experiment on the classification of the types of the detected repetitious motions.