Multiple non-rigid surface detection and registration

Yi Wu, Yoshihisa Ijiri, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Detecting and registering nonrigid surfaces are two important research problems for computer vision. Much work has been done with the assumption that there exists only one instance in the image. In this work, we propose an algorithm that detects and registers multiple nonrigid instances of given objects in a cluttered image. Specifically, after we use low level feature points to obtain the initial matches between templates and the input image, a novel high-order affinity graph is constructed to model the consistency of local topology. A hierarchical clustering approach is then used to locate the nonrigid surfaces. To remove the outliers in the cluster, we propose a deterministic annealing approach based on the Thin Plate Spline (TPS) model. The proposed method achieves high accuracy even when the number of outliers is nineteen times larger than the inliers. As the matches may appear sparsely in each instance, we propose a TPS based match growing approach to propagate the matches. Finally, an approach that fuses feature and appearance information is proposed to register each nonrigid surface. Extensive experiments and evaluations demonstrate that the proposed algorithm achieves promising results in detecting and registering multiple non-rigid surfaces in a cluttered scene.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1992-1999
Number of pages8
ISBN (Print)9781479928392
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: 2013 Dec 12013 Dec 8

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other2013 14th IEEE International Conference on Computer Vision, ICCV 2013
CountryAustralia
CitySydney, NSW
Period13/12/113/12/8

Fingerprint

Splines
Electric fuses
Computer vision
Topology
Annealing
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Wu, Y., Ijiri, Y., & Yang, M. H. (2013). Multiple non-rigid surface detection and registration. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 1992-1999). [6751358] (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.249
Wu, Yi ; Ijiri, Yoshihisa ; Yang, Ming Hsuan. / Multiple non-rigid surface detection and registration. Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. pp. 1992-1999 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{5544ef69259a4321997ef3a2cd305ad2,
title = "Multiple non-rigid surface detection and registration",
abstract = "Detecting and registering nonrigid surfaces are two important research problems for computer vision. Much work has been done with the assumption that there exists only one instance in the image. In this work, we propose an algorithm that detects and registers multiple nonrigid instances of given objects in a cluttered image. Specifically, after we use low level feature points to obtain the initial matches between templates and the input image, a novel high-order affinity graph is constructed to model the consistency of local topology. A hierarchical clustering approach is then used to locate the nonrigid surfaces. To remove the outliers in the cluster, we propose a deterministic annealing approach based on the Thin Plate Spline (TPS) model. The proposed method achieves high accuracy even when the number of outliers is nineteen times larger than the inliers. As the matches may appear sparsely in each instance, we propose a TPS based match growing approach to propagate the matches. Finally, an approach that fuses feature and appearance information is proposed to register each nonrigid surface. Extensive experiments and evaluations demonstrate that the proposed algorithm achieves promising results in detecting and registering multiple non-rigid surfaces in a cluttered scene.",
author = "Yi Wu and Yoshihisa Ijiri and Yang, {Ming Hsuan}",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/ICCV.2013.249",
language = "English",
isbn = "9781479928392",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1992--1999",
booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013",
address = "United States",

}

Wu, Y, Ijiri, Y & Yang, MH 2013, Multiple non-rigid surface detection and registration. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751358, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 1992-1999, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 13/12/1. https://doi.org/10.1109/ICCV.2013.249

Multiple non-rigid surface detection and registration. / Wu, Yi; Ijiri, Yoshihisa; Yang, Ming Hsuan.

Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 1992-1999 6751358 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multiple non-rigid surface detection and registration

AU - Wu, Yi

AU - Ijiri, Yoshihisa

AU - Yang, Ming Hsuan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Detecting and registering nonrigid surfaces are two important research problems for computer vision. Much work has been done with the assumption that there exists only one instance in the image. In this work, we propose an algorithm that detects and registers multiple nonrigid instances of given objects in a cluttered image. Specifically, after we use low level feature points to obtain the initial matches between templates and the input image, a novel high-order affinity graph is constructed to model the consistency of local topology. A hierarchical clustering approach is then used to locate the nonrigid surfaces. To remove the outliers in the cluster, we propose a deterministic annealing approach based on the Thin Plate Spline (TPS) model. The proposed method achieves high accuracy even when the number of outliers is nineteen times larger than the inliers. As the matches may appear sparsely in each instance, we propose a TPS based match growing approach to propagate the matches. Finally, an approach that fuses feature and appearance information is proposed to register each nonrigid surface. Extensive experiments and evaluations demonstrate that the proposed algorithm achieves promising results in detecting and registering multiple non-rigid surfaces in a cluttered scene.

AB - Detecting and registering nonrigid surfaces are two important research problems for computer vision. Much work has been done with the assumption that there exists only one instance in the image. In this work, we propose an algorithm that detects and registers multiple nonrigid instances of given objects in a cluttered image. Specifically, after we use low level feature points to obtain the initial matches between templates and the input image, a novel high-order affinity graph is constructed to model the consistency of local topology. A hierarchical clustering approach is then used to locate the nonrigid surfaces. To remove the outliers in the cluster, we propose a deterministic annealing approach based on the Thin Plate Spline (TPS) model. The proposed method achieves high accuracy even when the number of outliers is nineteen times larger than the inliers. As the matches may appear sparsely in each instance, we propose a TPS based match growing approach to propagate the matches. Finally, an approach that fuses feature and appearance information is proposed to register each nonrigid surface. Extensive experiments and evaluations demonstrate that the proposed algorithm achieves promising results in detecting and registering multiple non-rigid surfaces in a cluttered scene.

UR - http://www.scopus.com/inward/record.url?scp=84898835497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898835497&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.249

DO - 10.1109/ICCV.2013.249

M3 - Conference contribution

AN - SCOPUS:84898835497

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1992

EP - 1999

BT - Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wu Y, Ijiri Y, Yang MH. Multiple non-rigid surface detection and registration. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc. 2013. p. 1992-1999. 6751358. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.249