Saliency-based video segmentation with graph cuts and sequentially updated priors
- 1 June 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper proposes a new method for achieving precise video segmentation without any supervision or interaction. The main contributions of this report include 1) the introduction of fully automatic segmentation based on the maximum a posteriori (MAP) estimation of the Markov random field (MRF) with graph cuts and saliency-driven priors and 2) the updating of priors and feature likelihoods by integrating the previous segmentation results and the currently estimated saliency-based visual attention. Test results indicate that our new method precisely extracts probable regions from videos without any supervised interactions.Keywords
This publication has 6 references indexed in Scilit:
- Real-time estimation of human visual attention with dynamic Bayesian network and MCMC-based particle filterPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A stochastic model of selective visual attention with a dynamic Bayesian networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Dynamic Graph Cuts for Efficient Inference in Markov Random FieldsIeee Transactions On Pattern Analysis and Machine Intelligence, 2007
- Graph Cuts and Efficient N-D Image SegmentationInternational Journal of Computer Vision, 2006
- A signal detection model predicts the effects of set size on visual search accuracy for feature, conjunction, triple conjunction, and disjunction displaysPerception & Psychophysics, 2000
- A model of saliency-based visual attention for rapid scene analysisIeee Transactions On Pattern Analysis and Machine Intelligence, 1998