Spatio-temporal segmentation based on region merging
Moscheni, F.
Bhattacharjee, S.
Kunt, M.
Signal Process. Lab., Swiss Federal Inst. of Technol., Lausanne;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Sep 1998
Volume: 20,
Issue: 9
On page(s): 897-915
ISSN: 0162-8828
References Cited: 49
CODEN: ITPIDJ
INSPEC Accession Number: 6037186
Digital Object Identifier: 10.1109/34.713358
Current Version Published: 2002-08-06
Abstract
This paper proposes a technique for spatio-temporal segmentation
to identify the objects present in the scene represented in a video
sequence. This technique processes two consecutive frames at a time. A
region-merging approach is used to identify the objects in the scene.
Starting from an oversegmentation of the current frame, the objects are
formed by iteratively merging regions together. Regions are merged based
on their mutual spatio-temporal similarity. We propose a modified
Kolmogorov-Smirnov test for estimating the temporal similarity. The
region-merging process is based on a weighted, directed graph. Two
complementary graph-based clustering rules are proposed, namely, the
strong rule and the weak rule. These rules take advantage of the natural
structures present in the graph. Experimental results on different types
of scenes demonstrate the ability of the proposed technique to
automatically partition the scene into its constituent objects
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
