This paper addresses the problem of segmentation of moving objects in image sequences, which is of key importance in content-based applications. We transform the problem into a graph labeling problem over a region adjacency graph (RAG), by introducing a Markov random field (MRF) model based on spatio-temporal information. The initial partition is obtained by fast, color-based watershed segmentation. The motion of each region is estimated and validated in a hierarchical framework. A dynamic memory, based on object tracking, is incorporated into the segmentation process to maintain temporal coherence. The performance of the algorithm is evaluated on several real-world image sequences.
A region-based MRF model for unsupervised segmentation of moving objects in image sequences
2001-01-01
865073 byte
Conference paper
Electronic Resource
English
A Region-Based MRF Model for Unsupervised Segmentation of Moving Objects in Image Sequences
British Library Conference Proceedings | 2001
|New method for unsupervised segmentation of moving objects in infrared videos
British Library Online Contents | 2013
|Unsupervised image segmentation combining region and boundary estimation
British Library Online Contents | 2001
|Region-growing detection of moving objects in video sequences based on optical flow
British Library Online Contents | 2012
|