Match-time covariance for descriptors

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Standard

Match-time covariance for descriptors. / Christiansen, Eric; Rabaud, Vincent; Ziegler, Andrew; Kriegman, David; Belongie, Serge.

2013. Paper præsenteret ved 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, Storbritannien.

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Harvard

Christiansen, E, Rabaud, V, Ziegler, A, Kriegman, D & Belongie, S 2013, 'Match-time covariance for descriptors', Paper fremlagt ved 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, Storbritannien, 09/09/2013 - 13/09/2013. https://doi.org/10.5244/C.27.12

APA

Christiansen, E., Rabaud, V., Ziegler, A., Kriegman, D., & Belongie, S. (2013). Match-time covariance for descriptors. Paper præsenteret ved 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, Storbritannien. https://doi.org/10.5244/C.27.12

Vancouver

Christiansen E, Rabaud V, Ziegler A, Kriegman D, Belongie S. Match-time covariance for descriptors. 2013. Paper præsenteret ved 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, Storbritannien. https://doi.org/10.5244/C.27.12

Author

Christiansen, Eric ; Rabaud, Vincent ; Ziegler, Andrew ; Kriegman, David ; Belongie, Serge. / Match-time covariance for descriptors. Paper præsenteret ved 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, Storbritannien.

Bibtex

@conference{a7d7e06118a242d1b714feb4868d7b3f,
title = "Match-time covariance for descriptors",
abstract = "Local descriptor methods are widely used in computer vision to compare local regions of images. These descriptors are often extracted relative to an estimated scale and rotation to provide invariance up to similarity transformations. The estimation of rotation and scale in local neighborhoods (also known as steering) is an imperfect process, however, and can produce errors downstream. In this paper, we propose an alternative to steering that we refer to as match-time covariance (MTC). MTC is a general strategy for descriptor design that simultaneously provides invariance in local neighborhood matches together with the associated aligning transformations. We also provide a general framework for endowing existing descriptors with similarity invariance through MTC. The framework, Similarity-MTC, is simple and dramatically improves accuracy. Finally, we propose NCC-S, a highly effective descriptor based on classic normalized cross-correlation, designed for fast execution in the Similarity-MTC framework. The surprising effectiveness of this very simple descriptor suggests that MTC offers fruitful research directions for image matching previously not accessible in the steering based paradigm.",
author = "Eric Christiansen and Vincent Rabaud and Andrew Ziegler and David Kriegman and Serge Belongie",
year = "2013",
doi = "10.5244/C.27.12",
language = "English",
note = "2013 24th British Machine Vision Conference, BMVC 2013 ; Conference date: 09-09-2013 Through 13-09-2013",

}

RIS

TY - CONF

T1 - Match-time covariance for descriptors

AU - Christiansen, Eric

AU - Rabaud, Vincent

AU - Ziegler, Andrew

AU - Kriegman, David

AU - Belongie, Serge

PY - 2013

Y1 - 2013

N2 - Local descriptor methods are widely used in computer vision to compare local regions of images. These descriptors are often extracted relative to an estimated scale and rotation to provide invariance up to similarity transformations. The estimation of rotation and scale in local neighborhoods (also known as steering) is an imperfect process, however, and can produce errors downstream. In this paper, we propose an alternative to steering that we refer to as match-time covariance (MTC). MTC is a general strategy for descriptor design that simultaneously provides invariance in local neighborhood matches together with the associated aligning transformations. We also provide a general framework for endowing existing descriptors with similarity invariance through MTC. The framework, Similarity-MTC, is simple and dramatically improves accuracy. Finally, we propose NCC-S, a highly effective descriptor based on classic normalized cross-correlation, designed for fast execution in the Similarity-MTC framework. The surprising effectiveness of this very simple descriptor suggests that MTC offers fruitful research directions for image matching previously not accessible in the steering based paradigm.

AB - Local descriptor methods are widely used in computer vision to compare local regions of images. These descriptors are often extracted relative to an estimated scale and rotation to provide invariance up to similarity transformations. The estimation of rotation and scale in local neighborhoods (also known as steering) is an imperfect process, however, and can produce errors downstream. In this paper, we propose an alternative to steering that we refer to as match-time covariance (MTC). MTC is a general strategy for descriptor design that simultaneously provides invariance in local neighborhood matches together with the associated aligning transformations. We also provide a general framework for endowing existing descriptors with similarity invariance through MTC. The framework, Similarity-MTC, is simple and dramatically improves accuracy. Finally, we propose NCC-S, a highly effective descriptor based on classic normalized cross-correlation, designed for fast execution in the Similarity-MTC framework. The surprising effectiveness of this very simple descriptor suggests that MTC offers fruitful research directions for image matching previously not accessible in the steering based paradigm.

UR - http://www.scopus.com/inward/record.url?scp=84898491145&partnerID=8YFLogxK

U2 - 10.5244/C.27.12

DO - 10.5244/C.27.12

M3 - Paper

AN - SCOPUS:84898491145

T2 - 2013 24th British Machine Vision Conference, BMVC 2013

Y2 - 9 September 2013 through 13 September 2013

ER -

ID: 302046402