Video region segmentation by spatio-temporal watersheds

M. A. El Saban, amd B. S. Manjunath
Dept. of Electrical and Computer Engineering
University of California at Santa Barbara,
Santa Barbara, CA 93106
E-mail: {msaban, manj } [at] ece.ucsb.edu

Abstract

We propose a video region segmentation scheme combin-ing spatio-temporal edges and watershed techniques. We consider the video sequence as a 3-D volume and compute color edges within this volume. These color edges form a vector field that is in turn used to obtain an edge function. This edge function is used as a topological surface for a watershed grouping stage. Considering the video as a 3-D volume results in a batch segmentation instead of the tradi-tional frame-by-frame segmentation. The main advantages of this approach are: 1) exploiting the time continuity in the frame sequence , 2) avoiding problems in tracking re-gions from frame to frame, 3) using a fast watershed-based method in forming the final video regions. Preliminary ex-perimental results are very promising.
[PDF] [BibTex]
M. A. El Saban and B. S. Manjunath,
IEEE International Conference on Image Processing (ICIP), vol. 1, pp. 349-352, Barcelona, Spain, Sep. 2003.
Node ID: 354 , DB ID: 152 , VRLID: 117 , Lab: VRL , Target: Conference
Subject: [Detection on Images and Videos] « Look up more