Evolving Image Segmentations for the Analysis of Video Sequences

AA Clark, BT Thomas

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

1 Citation (Scopus)

Abstract

A methodology for the segmentation of successive frames of a video sequence is presented. Traditional methods, treating each frame in isolation, are computationally expensive, ignore potentially useful information derived from previous frames, and can lead to instabilities in the segmentation 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, to partition the image into homogeneous regions. The inherently dynamic nature of the algorithm allows an initial segmentation to evolve in response to changes observed in the video sequence. 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 (e.g. objects entering or leaving the scene). 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.
Translated title of the contributionEvolving Image Segmentations for the Analysis of Video Sequences
Original languageEnglish
Title of host publicationUnknown
EditorsAnne Jacobs, Thomas Baldwin
PublisherIEEE Computer Society
Pages290 - 295
Number of pages5
ISBN (Print)0769512720
Publication statusPublished - Dec 2001

Bibliographical note

Conference Proceedings/Title of Journal: Computer Vision and Pattern Recognition 2001, Vol. 2

Fingerprint

Dive into the research topics of 'Evolving Image Segmentations for the Analysis of Video Sequences'. Together they form a unique fingerprint.

Cite this