| Large Disparity Motion Layer Extraction via Topological Clustering. | |
| | |
MedLine Citation:
|
PMID: 20876022 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
In this paper, we present a robust and efficient approach to extract motion layers from a pair of images with large disparity motion. First, motion models are established as: 1) initial SIFT matches are obtained and grouped into a set of clusters using our developed topological clustering algorithm; 2) for each cluster with no less than three matches, an affine transformation is estimated with least-square solution as tentative motion model; and 3) the tentative motion models are refined and the invalid models are pruned. Then, with the obtained motion models, a graph cuts based layer assignment algorithm is employed to segment the scene into several motion layers. Experimental results demonstrate that our method can successfully segment scenes containing objects with large interframe motion or even with significant interframe scale and pose changes. Furthermore, compared with the previous method invented by Wills and its modified version, our method is much faster and more robust. |
| | |
Authors:
|
Yongtao Wang; Junbin Gong; Dazhi Zhang; Chenqiang Gao; Jinwen Tian; Huanqiang Zeng |
Publication Detail:
|
Type: Journal Article Date: 2010-09-27 |
Journal Detail:
|
Title: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Volume: 20 ISSN: 1941-0042 ISO Abbreviation: IEEE Trans Image Process Publication Date: 2011 Jan |
Date Detail:
|
Created Date: 2010-12-21 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 9886191 Medline TA: IEEE Trans Image Process Country: United States |
Other Details:
|
Languages: eng Pagination: 43-52 Citation Subset: IM |
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: Variational bayesian super resolution.
Next Document: Adaptive Multiwavelet-Based Watermarking Through JPW Masking.