What went where [motion segmentation]

Datalogisk Institut

What went where [motion segmentation]

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Standard

What went where [motion segmentation]. / Wills, J.; Agarwal, S.; Belongie, S.

2003.

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Harvard

Wills, J, Agarwal, S & Belongie, S 2003, 'What went where [motion segmentation]'. https://doi.org/10.1109/cvpr.2003.1211335

APA

Wills, J., Agarwal, S., & Belongie, S. (2003). What went where [motion segmentation]. https://doi.org/10.1109/cvpr.2003.1211335

Vancouver

Wills J, Agarwal S, Belongie S. What went where [motion segmentation]. 2003. https://doi.org/10.1109/cvpr.2003.1211335

Author

Wills, J. ; Agarwal, S. ; Belongie, S. / What went where [motion segmentation].

Bibtex

@conference{a7e46cd7311846c48f3454707f539766,

title = "What went where [motion segmentation]",

abstract = "We present a 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.",

author = "J. Wills and S. Agarwal and S. Belongie",

year = "2003",

month = nov,

day = "4",

doi = "10.1109/cvpr.2003.1211335",

language = "English",

}

RIS

TY - CONF

T1 - What went where [motion segmentation]

AU - Wills, J.

AU - Agarwal, S.

AU - Belongie, S.

PY - 2003/11/4

Y1 - 2003/11/4

N2 - We present a 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 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 - https://www.mendeley.com/catalogue/067a1294-6997-3e65-a710-12e426e0435f/

U2 - 10.1109/cvpr.2003.1211335

DO - 10.1109/cvpr.2003.1211335

M3 - Paper

ER -

ID: 303681593