Share Email Print

Proceedings Paper

New video object segmentation technique based on flow-thread features for MPEG-4 and multimedia systems
Author(s): Ho-Chao Huang; Yung-Chieh Lin; Yi-Ping Hung; Chiou-Shann Fuh
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we present a novel technique for video object (VO) segmentation. Compared to the existing VO segmentation methods, our method has the advantage that it does not decompose the VO segmentation problem into an initial image segmentation problem (segmenting a single image frame) followed by a temporal tracking problem. Instead, motion information contained in a finite duration of the image sequence is considered simultaneously. Given a video sequence, our method first estimates motion vectors between consecutive images, and then constructs the flow-thread for each pixel based on the estimated motion vectors. Here, a flow-thread is a series of pixels obtained by tracing the motion vectors along the image sequence. Next, we extract a set of flow- thread features (ft-features) from each flow-thread, which is then used to classify the associated pixel into the VO it belongs to. The segmentation results obtained by our unsupervised method look promising and the processing speed is fast enough for practical uses.

Paper Details

Date Published: 19 April 2000
PDF: 9 pages
Proc. SPIE 3974, Image and Video Communications and Processing 2000, (19 April 2000); doi: 10.1117/12.382953
Show Author Affiliations
Ho-Chao Huang, Institute of Information Science (Taiwan)
Yung-Chieh Lin, National Taiwan Univ. (Taiwan)
Yi-Ping Hung, Institute of Information Science and National Taiwan Univ. (Taiwan)
Chiou-Shann Fuh, National Taiwan Univ. (Taiwan)

Published in SPIE Proceedings Vol. 3974:
Image and Video Communications and Processing 2000
Bhaskaran Vasudev; T. Russell Hsing; Andrew G. Tescher; Robert L. Stevenson, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?