DocumentCode :
2352537
Title :
Evolving image segmentations for the analysis of video sequences
Author :
Clark, A.A. ; Thomas, B.T.
Author_Institution :
Dept. of Comput. Sci., Bristol Univ., UK
Volume :
2
fYear :
2001
fDate :
2001
Abstract :
This paper concerns the segmentation of successive frames of a video sequence. Traditional methods, treating each frame in isolation, are computationally expensive, ignore potentially useful information derived from previous frames, and can lead to instabilities over the sequence. The approach developed here, based on the Region Competition algorithm (Zhu and Yuille, IEEE Trans. PAMI, 1996), employs a mesh of active contour primitives supervised by an MDL energy criterion. Temporal extensions, namely Boundary Momentum, Region Memory, and Optical Boundary Flow, are developed to ease the transition between successive frames. Further enhancements are made by incorporating mechanisms to accommodate the topological discontinuities that can arise during the sequence. The algorithm is demonstrated using a number of synthetic and real video sequences and is shown to provide an efficient method of segmentation which encourages stability across frames and preserves the quality of the original segmentation over the sequence.
Keywords :
image segmentation; image sequences; video signal processing; MDL energy criterion; active contour primitives; boundary momentum; image segmentations; optical boundary flow; region competition algorithm; region memory; successive frames segmentation; temporal extensions; video sequences analysis; Active contours; Computer science; Image analysis; Image motion analysis; Image segmentation; Image sequence analysis; Optical films; Partitioning algorithms; Stability; Video sequences;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-1272-0
Type :
conf
DOI :
10.1109/CVPR.2001.990973
Filename :
990973
Link To Document :
بازگشت