Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching

João Paulo Lima; Francisco Simões; Hideaki Uchiyama; Veronica Teichrieb; Eric Marchand

Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching

João Paulo Lima, Francisco Simões, Hideaki Uchiyama, Veronica Teichrieb, Eric Marchand

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a method named Depth-Assisted Rectification of Patches (DARP), which exploits depth information available in RGB-D consumer devices to improve keypoint matching of perspectively distorted images. This is achieved by generating a projective rectification of a patch around the keypoint, which is normalized with respect to perspective distortions and scale. The DARP method runs in real-time and can be used with any local feature detector and descriptor. Evaluations with planar and non-planar scenes show that DARP can obtain better results than existing keypoint matching approaches in oblique poses.

Original language	English
Title of host publication	VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages	651-656
Number of pages	6
Publication status	Published - May 31 2013
Externally published	Yes
Event	8th International Conference on Computer Vision Theory and Applications, VISAPP 2013 - Barcelona, Spain Duration: Feb 21 2013 → Feb 24 2013

Publication series

Name	VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications
Volume	1

Other

Other	8th International Conference on Computer Vision Theory and Applications, VISAPP 2013
Country/Territory	Spain
City	Barcelona
Period	2/21/13 → 2/24/13

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition

Cite this

Lima, J. P., Simões, F., Uchiyama, H., Teichrieb, V., & Marchand, E. (2013). Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching. In VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications (pp. 651-656). (VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications; Vol. 1).

Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching. / Lima, João Paulo; Simões, Francisco; Uchiyama, Hideaki et al.
VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. 2013. p. 651-656 (VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lima, JP, Simões, F, Uchiyama, H, Teichrieb, V & Marchand, E 2013, Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching. in VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications, vol. 1, pp. 651-656, 8th International Conference on Computer Vision Theory and Applications, VISAPP 2013, Barcelona, Spain, 2/21/13.

Lima JP, Simões F, Uchiyama H, Teichrieb V, Marchand E. Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching. In VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. 2013. p. 651-656. (VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications).

Lima, João Paulo ; Simões, Francisco ; Uchiyama, Hideaki et al. / Depth-Assisted Rectification of Patches : Using RGB-D consumer devices to improve real-time keypoint matching. VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications. 2013. pp. 651-656 (VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications).

@inproceedings{bb2ba2a8e8384778b62ce648fd6d8ead,

title = "Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching",

abstract = "This paper presents a method named Depth-Assisted Rectification of Patches (DARP), which exploits depth information available in RGB-D consumer devices to improve keypoint matching of perspectively distorted images. This is achieved by generating a projective rectification of a patch around the keypoint, which is normalized with respect to perspective distortions and scale. The DARP method runs in real-time and can be used with any local feature detector and descriptor. Evaluations with planar and non-planar scenes show that DARP can obtain better results than existing keypoint matching approaches in oblique poses.",

author = "Lima, {Jo{\~a}o Paulo} and Francisco Sim{\~o}es and Hideaki Uchiyama and Veronica Teichrieb and Eric Marchand",

year = "2013",

month = may,

day = "31",

language = "English",

isbn = "9789898565471",

series = "VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications",

pages = "651--656",

booktitle = "VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications",

note = "8th International Conference on Computer Vision Theory and Applications, VISAPP 2013 ; Conference date: 21-02-2013 Through 24-02-2013",

}

TY - GEN

T1 - Depth-Assisted Rectification of Patches

T2 - 8th International Conference on Computer Vision Theory and Applications, VISAPP 2013

AU - Lima, João Paulo

AU - Simões, Francisco

AU - Uchiyama, Hideaki

AU - Teichrieb, Veronica

AU - Marchand, Eric

PY - 2013/5/31

Y1 - 2013/5/31

N2 - This paper presents a method named Depth-Assisted Rectification of Patches (DARP), which exploits depth information available in RGB-D consumer devices to improve keypoint matching of perspectively distorted images. This is achieved by generating a projective rectification of a patch around the keypoint, which is normalized with respect to perspective distortions and scale. The DARP method runs in real-time and can be used with any local feature detector and descriptor. Evaluations with planar and non-planar scenes show that DARP can obtain better results than existing keypoint matching approaches in oblique poses.

AB - This paper presents a method named Depth-Assisted Rectification of Patches (DARP), which exploits depth information available in RGB-D consumer devices to improve keypoint matching of perspectively distorted images. This is achieved by generating a projective rectification of a patch around the keypoint, which is normalized with respect to perspective distortions and scale. The DARP method runs in real-time and can be used with any local feature detector and descriptor. Evaluations with planar and non-planar scenes show that DARP can obtain better results than existing keypoint matching approaches in oblique poses.

UR - http://www.scopus.com/inward/record.url?scp=84878234516&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878234516&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878234516

SN - 9789898565471

T3 - VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications

SP - 651

EP - 656

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

Y2 - 21 February 2013 through 24 February 2013

ER -

Depth-Assisted Rectification of Patches: Using RGB-D consumer devices to improve real-time keypoint matching

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this