Title :
An iterative motion estimation-segmentation method using watershed segments
Author :
Patras, I. ; Hendriks, E.A. ; Lagendijk, R.L.
Author_Institution :
Inf. & Commun. Theory Group, Delft Univ. of Technol., Netherlands
Abstract :
This paper addresses the problem of segmentation of image sequences into moving objects. The segmentation (label) field is modeled by applying a Markov random field on regions provided by a watershed algorithm. The algorithm iterates between a motion estimation and a segmentation step. Temporal consistency is introduced by tracking the segmentation in time
Keywords :
Markov processes; image segmentation; image sequences; iterative methods; motion estimation; tracking; video signal processing; Markov random field; image sequences; iterative motion estimation-segmentation method; label field; moving objects; temporal consistency; tracking; watershed segments; Clustering algorithms; Collaboration; Image coding; Image segmentation; Image sequences; Iterative methods; MPEG 4 Standard; Markov random fields; Motion estimation; Video compression;
Conference_Titel :
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on
Conference_Location :
Chicago, IL
Print_ISBN :
0-8186-8821-1
DOI :
10.1109/ICIP.1998.723561
