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 }@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.