Stable keypoint recognition using viewpoint generative learning

Takumi Yoshida, Hideo Saito, Masayoshi Shimizu, Akinori Taguchi

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

6 Citations (Scopus)

Abstract

We propose a stable keypoint recognition method that is robust to viewpoint changes. Conventional local features such as SIFT, SURF, etc., have scale and rotation invariance but often fail in matching points when the camera pose significantly changes. In order to solve this problem, we adopt viewpoint generative learning. By generating various patterns as seen from different viewpoints and collecting local invariant features, our system can learn feature descriptors under various camera poses for each keypoint before actual matching. Experimental results comparing usual local feature matching or patch classification method show both robustness and fastness of learning.

Original languageEnglish
Title of host publicationVISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages310-315
Number of pages6
Volume2
Publication statusPublished - 2013
Event8th International Conference on Computer Vision Theory and Applications, VISAPP 2013 - Barcelona, Spain
Duration: 2013 Feb 212013 Feb 24

Other

Other8th International Conference on Computer Vision Theory and Applications, VISAPP 2013
CountrySpain
CityBarcelona
Period13/2/2113/2/24

Fingerprint

Cameras
Invariance

Keywords

  • Generative learning
  • Keypoint recognition
  • Local features
  • Pose estimation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Yoshida, T., Saito, H., Shimizu, M., & Taguchi, A. (2013). Stable keypoint recognition using viewpoint generative learning. In VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications (Vol. 2, pp. 310-315)

Stable keypoint recognition using viewpoint generative learning. / Yoshida, Takumi; Saito, Hideo; Shimizu, Masayoshi; Taguchi, Akinori.

VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 2 2013. p. 310-315.

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

Yoshida, T, Saito, H, Shimizu, M & Taguchi, A 2013, Stable keypoint recognition using viewpoint generative learning. in VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. vol. 2, pp. 310-315, 8th International Conference on Computer Vision Theory and Applications, VISAPP 2013, Barcelona, Spain, 13/2/21.
Yoshida T, Saito H, Shimizu M, Taguchi A. Stable keypoint recognition using viewpoint generative learning. In VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 2. 2013. p. 310-315
Yoshida, Takumi ; Saito, Hideo ; Shimizu, Masayoshi ; Taguchi, Akinori. / Stable keypoint recognition using viewpoint generative learning. VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 2 2013. pp. 310-315
@inproceedings{28a107bd280443afb62bc9655cfb8785,
title = "Stable keypoint recognition using viewpoint generative learning",
abstract = "We propose a stable keypoint recognition method that is robust to viewpoint changes. Conventional local features such as SIFT, SURF, etc., have scale and rotation invariance but often fail in matching points when the camera pose significantly changes. In order to solve this problem, we adopt viewpoint generative learning. By generating various patterns as seen from different viewpoints and collecting local invariant features, our system can learn feature descriptors under various camera poses for each keypoint before actual matching. Experimental results comparing usual local feature matching or patch classification method show both robustness and fastness of learning.",
keywords = "Generative learning, Keypoint recognition, Local features, Pose estimation",
author = "Takumi Yoshida and Hideo Saito and Masayoshi Shimizu and Akinori Taguchi",
year = "2013",
language = "English",
isbn = "9789898565471",
volume = "2",
pages = "310--315",
booktitle = "VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications",

}

TY - GEN

T1 - Stable keypoint recognition using viewpoint generative learning

AU - Yoshida, Takumi

AU - Saito, Hideo

AU - Shimizu, Masayoshi

AU - Taguchi, Akinori

PY - 2013

Y1 - 2013

N2 - We propose a stable keypoint recognition method that is robust to viewpoint changes. Conventional local features such as SIFT, SURF, etc., have scale and rotation invariance but often fail in matching points when the camera pose significantly changes. In order to solve this problem, we adopt viewpoint generative learning. By generating various patterns as seen from different viewpoints and collecting local invariant features, our system can learn feature descriptors under various camera poses for each keypoint before actual matching. Experimental results comparing usual local feature matching or patch classification method show both robustness and fastness of learning.

AB - We propose a stable keypoint recognition method that is robust to viewpoint changes. Conventional local features such as SIFT, SURF, etc., have scale and rotation invariance but often fail in matching points when the camera pose significantly changes. In order to solve this problem, we adopt viewpoint generative learning. By generating various patterns as seen from different viewpoints and collecting local invariant features, our system can learn feature descriptors under various camera poses for each keypoint before actual matching. Experimental results comparing usual local feature matching or patch classification method show both robustness and fastness of learning.

KW - Generative learning

KW - Keypoint recognition

KW - Local features

KW - Pose estimation

UR - http://www.scopus.com/inward/record.url?scp=84878223624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878223624&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789898565471

VL - 2

SP - 310

EP - 315

BT - VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications

ER -