Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation Export

@incollection{citeulike:2642605, abstract = {This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different methods for cue integration are presented and tested. The first is a probabilistic approach which at each pixel computes the likelihood of observations over all cues before assigning pixels to foreground or background layers using Bayes Rule. The second method allows each cue to make a decision independent of the other cues before fusing their outputs with a weighted sum. A further important contribution of our work concerns demonstrating how models for some cues can be learnt and subsequently adapted online. In particular, regions of coherent motion are used to train distributions for colour and for a simple texture descriptor. An additional aspect of our framework is in providing mechanisms for suppressing cues when they are believed to be unreliable, for instance during training or when they disagree with the general consensus. Results on extended video sequences are presented.}, author = {Hayman, Eric and Eklundh, Jan-Olof}, citeulike-article-id = {2642605}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/3-540-47977-5_31}, doi = {10.1007/3-540-47977-5_31}, journal = {Computer Vision — ECCV 2002}, keywords = {bayesian, computervision, figureground, model}, pages = {469--486}, posted-at = {2008-04-08 20:23:15}, priority = {0}, title = {Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation}, url = {http://dx.doi.org/10.1007/3-540-47977-5_31}, year = {2002} }

TY - CHAP ID - citeulike:2642605 L3 - citeulike-article-id:2642605 N2 - This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different methods for cue integration are presented and tested. The first is a probabilistic approach which at each pixel computes the likelihood of observations over all cues before assigning pixels to foreground or background layers using Bayes Rule. The second method allows each cue to make a decision independent of the other cues before fusing their outputs with a weighted sum. A further important contribution of our work concerns demonstrating how models for some cues can be learnt and subsequently adapted online. In particular, regions of coherent motion are used to train distributions for colour and for a simple texture descriptor. An additional aspect of our framework is in providing mechanisms for suppressing cues when they are believed to be unreliable, for instance during training or when they disagree with the general consensus. Results on extended video sequences are presented. JF - Computer Vision — ECCV 2002 EP - 486 TI - Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation SP - 469 KW - bayesian KW - computervision KW - figureground KW - model AU - Hayman, Eric AU - Eklundh, Jan-Olof PY - 2002/// UR - http://dx.doi.org/10.1007/3-540-47977-5_31 ER -