| Bilayer segmentation of webcam videos using tree-based classifiers. | |
| | |
MedLine Citation:
|
PMID: 21088317 Owner: NLM Status: In-Process |
Abstract/OtherAbstract:
|
This paper presents an automatic segmentation algorithm for video frames captured by a (monocular) webcam that closely approximates depth segmentation from a stereo camera. The frames are segmented into foreground and background layers that comprise a subject (participant) and other objects and individuals. The algorithm produces correct segmentations even in the presence of large background motion with a nearly stationary foreground. This research makes three key contributions: First, we introduce a novel motion representation, referred to as "motons," inspired by research in object recognition. Second, we propose estimating the segmentation likelihood from the spatial context of motion. The estimation is efficiently learned by random forests. Third, we introduce a general taxonomy of tree-based classifiers that facilitates both theoretical and experimental comparisons of several known classification algorithms and generates new ones. In our bilayer segmentation algorithm, diverse visual cues such as motion, motion context, color, contrast, and spatial priors are fused by means of a conditional random field (CRF) model. Segmentation is then achieved by binary min-cut. Experiments on many sequences of our videochat application demonstrate that our algorithm, which requires no initialization, is effective in a variety of scenes, and the segmentation results are comparable to those obtained by stereo systems. |
| | |
Authors:
|
Pei Yin; Antonio Criminisi; John Winn; Irfan Essa |
Related Documents
:
|
2281087 - Normal mode analysis of human lysozyme: study of the relative motion of the two domains... 10426507 - Computer evaluation of left ventricular wall motion by means of shape-based tracking an... 19826197 - Validation of a computational method for assessing the impact of intra-fraction motion ... 12780207 - The transient behaviour of models of bowed-string motion. 19327817 - Predictors of noise annoyance in noisy and quiet urban streets. 22628477 - Rhabdom evolution in butterflies: insights from the uniquely tiered and heterogeneous o... |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: IEEE transactions on pattern analysis and machine intelligence Volume: 33 ISSN: 1939-3539 ISO Abbreviation: IEEE Trans Pattern Anal Mach Intell Publication Date: 2011 Jan |
Date Detail:
|
Created Date: 2010-11-22 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 9885960 Medline TA: IEEE Trans Pattern Anal Mach Intell Country: United States |
Other Details:
|
Languages: eng Pagination: 30-42 Citation Subset: IM |
Affiliation:
|
Microsoft Corp., One Microsoft Way, Redmond, WA 98052, USA. peiyin@microsoft.com |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Turbo segmentation of textured images.
Next Document: Discriminative learning of local image descriptors.