What went where
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
What went where. / Wills, Josh; Agarwal, Sameer; Belongie, Serge.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 2003, p. I/37-I/44.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - What went where
AU - Wills, Josh
AU - Agarwal, Sameer
AU - Belongie, Serge
PY - 2003
Y1 - 2003
N2 - We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graph-cut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods.
AB - We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graph-cut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods.
UR - http://www.scopus.com/inward/record.url?scp=0042941579&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:0042941579
VL - 1
SP - I/37-I/44
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
T2 - 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Y2 - 18 June 2003 through 20 June 2003
ER -
ID: 302056514