Detecting Removed Object from Video with Stationary Background

摘要

This paper presents a method for detecting the removed object in video captured by stationary camera. The method is based on an observation that the removed object, while not distinguishable by human eyes, leaves artifacts that can be detected by computers. In this paper, the block based motion estimation method is employed to extract motion information from adjacent video frames. Then the magnitude and orientation of the motion vectors are used to differentiate the authentic region and the forged region. By exploring the discrepancies in motion vectors, the position of the removed object can be revealed. The efficiency of the proposed method is demonstrated by experiments.