Robust affine point matching via quadratic assignment on Grassmannians

Alexander Kolpakov; Michael Werman

doi:10.1016/j.patrec.2024.09.016

Robust affine point matching via quadratic assignment on Grassmannians

Alexander Kolpakov^*, Michael Werman

^*Corresponding author for this work

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance between two elements of the Grassmannian. For this purpose, an indefinite relaxation of the Quadratic Assignment Problem (QAP) is used, and several approaches to affine feature matching are studied and compared. Experiments demonstrate that RoAM is more robust to noise and point discrepancy than previous methods.

Original language	English
Pages (from-to)	265-271
Number of pages	7
Journal	Pattern Recognition Letters
Volume	186
DOIs	https://doi.org/10.1016/j.patrec.2024.09.016
State	Published - Oct 2024

Bibliographical note

Publisher Copyright:
© 2024 Elsevier B.V.

Keywords

Affine correspondence
Affine feature matching
Grassmann manifold
Point cloud registration
Quadratic assignment problem (QAP)
Shape matching
Singular value decomposition (SVD)

Access to Document

10.1016/j.patrec.2024.09.016

Cite this

@article{c944cf9a12664987aedba1526d8cb8c7,

title = "Robust affine point matching via quadratic assignment on Grassmannians",

abstract = "Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance between two elements of the Grassmannian. For this purpose, an indefinite relaxation of the Quadratic Assignment Problem (QAP) is used, and several approaches to affine feature matching are studied and compared. Experiments demonstrate that RoAM is more robust to noise and point discrepancy than previous methods.",

keywords = "Affine correspondence, Affine feature matching, Grassmann manifold, Point cloud registration, Quadratic assignment problem (QAP), Shape matching, Singular value decomposition (SVD)",

author = "Alexander Kolpakov and Michael Werman",

note = "Publisher Copyright: {\textcopyright} 2024 Elsevier B.V.",

year = "2024",

month = oct,

doi = "10.1016/j.patrec.2024.09.016",

language = "אנגלית",

volume = "186",

pages = "265--271",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier",

}

TY - JOUR

T1 - Robust affine point matching via quadratic assignment on Grassmannians

AU - Kolpakov, Alexander

AU - Werman, Michael

PY - 2024/10

Y1 - 2024/10

N2 - Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance between two elements of the Grassmannian. For this purpose, an indefinite relaxation of the Quadratic Assignment Problem (QAP) is used, and several approaches to affine feature matching are studied and compared. Experiments demonstrate that RoAM is more robust to noise and point discrepancy than previous methods.

AB - Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance between two elements of the Grassmannian. For this purpose, an indefinite relaxation of the Quadratic Assignment Problem (QAP) is used, and several approaches to affine feature matching are studied and compared. Experiments demonstrate that RoAM is more robust to noise and point discrepancy than previous methods.

KW - Affine correspondence

KW - Affine feature matching

KW - Grassmann manifold

KW - Point cloud registration

KW - Quadratic assignment problem (QAP)

KW - Shape matching

KW - Singular value decomposition (SVD)

UR - http://www.scopus.com/inward/record.url?scp=85207753613&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2024.09.016

DO - 10.1016/j.patrec.2024.09.016

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85207753613

SN - 0167-8655

VL - 186

SP - 265

EP - 271

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

ER -

Robust affine point matching via quadratic assignment on Grassmannians

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this