Macroblock Classification Method for Video Applications Involving Motions

TL;DR

This paper introduces a low-complexity macroblock classification method for motion analysis in compressed videos, enabling efficient shot change detection, motion discontinuity detection, and outlier rejection in global motion estimation.

Contribution

It presents a novel macroblock classification technique based on motion vector analysis, improving efficiency and effectiveness in various video processing tasks.

Findings

Effective shot change detection

Accurate motion discontinuity detection

Robust outlier rejection in global motion estimation

Abstract

In this paper, a macroblock classification method is proposed for various video processing applications involving motions. Based on the analysis of the Motion Vector field in the compressed video, we propose to classify Macroblocks of each video frame into different classes and use this class information to describe the frame content. We demonstrate that this low-computation-complexity method can efficiently catch the characteristics of the frame. Based on the proposed macroblock classification, we further propose algorithms for different video processing applications, including shot change detection, motion discontinuity detection, and outlier rejection for global motion estimation. Experimental results demonstrate that the methods based on the proposed approach can work effectively on these applications.