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.
Evolving image segmentations for the analysis of video sequences
2001-01-01
987213 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Evolving Image Segmentations for the Analysis of Video Sequences
British Library Conference Proceedings | 2001
|Learning layered motion segmentations of video
IEEE | 2005
|Learning Layered Motion Segmentations of Video
British Library Online Contents | 2008
|General Theory of Fuzzy Connectedness Segmentations
British Library Online Contents | 2016
|