Bayesian method for motion segmentation and tracking in compressed videos

Treetasanatavorn S, Rauschenbach U, Heuer J, Kaup A (2005)

Publication Language: English

Publication Status: Published

Publication Type: Journal article, Report

Publication year: 2005

Journal

Computer Science Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie (AGH University of Science and Technology) / AGH University of Science and Technology Press

Book Volume: 3663

Pages Range: 277-284

Event location: Vienna

DOI: 10.1007/11550518_35

Abstract

This contribution presents a statistical method for segmentation and tracking of moving regions from the compressed videos. This technique is particularly efficient to analyse and track motion segments from the compression-oriented motion fields by using the Bayesian estimation framework. For each motion field, the algorithm initialises a partition that is subject to comparisons and associations with its tracking counterpart. Due to potential hypothesis incompatibility, the algorithm applies a conflict resolution technique to ensure that the partition inherits relevant characteristics from both hypotheses as far as possible. Each tracked region is further classified as a background or a foreground object based on an approximation of the logical mass, momentum, and impulse. The experiment has demonstrated promising results based on standard test sequences. © Springer-Verlag Berlin Heidelberg 2005.

Authors with CRIS profile

Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung

How to cite

APA:

Treetasanatavorn, S., Rauschenbach, U., Heuer, J., & Kaup, A. (2005). Bayesian method for motion segmentation and tracking in compressed videos. Computer Science, 3663, 277-284. https://dx.doi.org/10.1007/11550518_35

MLA:

Treetasanatavorn, Siripong, et al. "Bayesian method for motion segmentation and tracking in compressed videos." Computer Science 3663 (2005): 277-284.

BibTeX: Download