Segmentation of Moving Objects in Video Sequences (2001)
| Citations: | 41 - 0 self |
BibTeX
@TECHREPORT{Tsaig01segmentationof,
author = {Yaakov Tsaig and Amir Averbuch and Ard Mpeg- Enables},
title = {Segmentation of Moving Objects in Video Sequences},
institution = {},
year = {2001}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
various content-based functionalities for multimedia applications. To support such functionalities, as well as to improve coding efficiency, MPEG-4 relies on a decomposition of each frame of an image sequence into video object planes (VOPs). Each VOP corresponds to a single moving object in the scene. This paper presents a new method for automatic segmentation of moving objects in image sequences for VOP extraction. We formulate the problem as graph labeling over a region adjacency graph (RAG), based on motion information. The label field is modeled as a Markov random field (MRF). An initial spatial partition of each frame is obtained by a fast, floating-point based implementation of the watershed algorithm. The motion of each region is estimated by hierarchical region matching. To avoid inaccuracies in occlusion areas, a novel motion validation scheme is presented. A dynamic memory, based on object tracking, is incorporated into the segmentation process to maintain temporal coherence of the segmentation. Finally, a labeling is obtained by maximization of the a posteriori probability of the MRF using motion information, spatial information and the memory. The optimization is carried out by highest confidence first (HCF). Experimental results for several video sequences demonstrate the effectiveness of the proposed approach. Index Terms—Markov random fields, MPEG-4, video segmentation, VOP extraction, watershed segmentation. I.
Keyphrases
video sequence vop extraction motion information image sequence new method graph labeling markov random field hierarchical region initial spatial partition occlusion area index term markov random field several video sequence label field posteriori probability watershed algorithm automatic segmentation segmentation process object tracking region adjacency graph novel motion validation scheme video segmentation various content-based functionality spatial information dynamic memory video object plane temporal coherence experimental result multimedia application
