A NOVEL OBJECT DETECTION TECHNIQUE IN COMPRESSED DOMAIN

Abstract

In this paper we propose a novel approach for robust motion vector based object detection in MPEG-1 video streams. By processing the extracted motion vector fields that are directly extracted from MPEG-1 video streams in the compressed domain, through our proposed system, in order to reduce the noise within the motion vector content, obtain more robust object information, and refine this information. As a result, the object detection algorithm is more capable of accurately detecting objects with more efficient performance.