Improved SIFT matching algorithm for 3D reconstruction from endoscopic images

Pengfei Du; Ya Zhou; Qiaona Xing; Xiaoming Hu

doi:10.1145/2087756.2087864

Improved SIFT matching algorithm for 3D reconstruction from endoscopic images

Pengfei Du^*, Ya Zhou, Qiaona Xing, Xiaoming Hu

^*Corresponding author for this work

Beijing Institute of Technology

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

12 Citations (Scopus)

Abstract

SIFT (Scale Invariant Feature Transform) is wildly used in image matching but suffered from low matching pairs when employed in endoscope image. This paper presented an improved algorithm based on SIFT, the core contribution of which is Zone Matching approach. By collecting all feature points in a neighbor patch around the coordinate of an objective feature in the key image and finding the closest one to the feature in current image, the Zone Matching can obtain more matching pairs in shorter time. The experiment result shows a good improvement on the matching results both in matching number and computing time.

Original language	English
Title of host publication	Proceedings of VRCAI 2011
Subtitle of host publication	ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry
Pages	561-564
Number of pages	4
DOIs	https://doi.org/10.1145/2087756.2087864
Publication status	Published - 2011
Event	10th International Conference on Virtual Reality Continuum and Its Applications in Industry, VRCAI'11 - Hong Kong, China Duration: 11 Dec 2011 → 12 Dec 2011

Publication series

Name	Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry

Conference

Conference	10th International Conference on Virtual Reality Continuum and Its Applications in Industry, VRCAI'11
Country/Territory	China
City	Hong Kong
Period	11/12/11 → 12/12/11

Keywords

3D reconstruction
Endoscopy
Feature matching
Improved SIFT

Access to Document

10.1145/2087756.2087864

Cite this

Du, P., Zhou, Y., Xing, Q., & Hu, X. (2011). Improved SIFT matching algorithm for 3D reconstruction from endoscopic images. In Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry (pp. 561-564). (Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry). https://doi.org/10.1145/2087756.2087864

Du, Pengfei ; Zhou, Ya ; Xing, Qiaona et al. / Improved SIFT matching algorithm for 3D reconstruction from endoscopic images. Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry. 2011. pp. 561-564 (Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry).

@inproceedings{8c4ccfdfe36147958e563aac4acea931,

title = "Improved SIFT matching algorithm for 3D reconstruction from endoscopic images",

abstract = "SIFT (Scale Invariant Feature Transform) is wildly used in image matching but suffered from low matching pairs when employed in endoscope image. This paper presented an improved algorithm based on SIFT, the core contribution of which is Zone Matching approach. By collecting all feature points in a neighbor patch around the coordinate of an objective feature in the key image and finding the closest one to the feature in current image, the Zone Matching can obtain more matching pairs in shorter time. The experiment result shows a good improvement on the matching results both in matching number and computing time.",

keywords = "3D reconstruction, Endoscopy, Feature matching, Improved SIFT",

author = "Pengfei Du and Ya Zhou and Qiaona Xing and Xiaoming Hu",

year = "2011",

doi = "10.1145/2087756.2087864",

language = "English",

isbn = "9781450310604",

series = "Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry",

pages = "561--564",

booktitle = "Proceedings of VRCAI 2011",

note = "10th International Conference on Virtual Reality Continuum and Its Applications in Industry, VRCAI'11 ; Conference date: 11-12-2011 Through 12-12-2011",

}

Du, P, Zhou, Y, Xing, Q & Hu, X 2011, Improved SIFT matching algorithm for 3D reconstruction from endoscopic images. in Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry. Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry, pp. 561-564, 10th International Conference on Virtual Reality Continuum and Its Applications in Industry, VRCAI'11, Hong Kong, China, 11/12/11. https://doi.org/10.1145/2087756.2087864

Improved SIFT matching algorithm for 3D reconstruction from endoscopic images. / Du, Pengfei; Zhou, Ya; Xing, Qiaona et al.
Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry. 2011. p. 561-564 (Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry).

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

TY - GEN

T1 - Improved SIFT matching algorithm for 3D reconstruction from endoscopic images

AU - Du, Pengfei

AU - Zhou, Ya

AU - Xing, Qiaona

AU - Hu, Xiaoming

PY - 2011

Y1 - 2011

N2 - SIFT (Scale Invariant Feature Transform) is wildly used in image matching but suffered from low matching pairs when employed in endoscope image. This paper presented an improved algorithm based on SIFT, the core contribution of which is Zone Matching approach. By collecting all feature points in a neighbor patch around the coordinate of an objective feature in the key image and finding the closest one to the feature in current image, the Zone Matching can obtain more matching pairs in shorter time. The experiment result shows a good improvement on the matching results both in matching number and computing time.

AB - SIFT (Scale Invariant Feature Transform) is wildly used in image matching but suffered from low matching pairs when employed in endoscope image. This paper presented an improved algorithm based on SIFT, the core contribution of which is Zone Matching approach. By collecting all feature points in a neighbor patch around the coordinate of an objective feature in the key image and finding the closest one to the feature in current image, the Zone Matching can obtain more matching pairs in shorter time. The experiment result shows a good improvement on the matching results both in matching number and computing time.

KW - 3D reconstruction

KW - Endoscopy

KW - Feature matching

KW - Improved SIFT

UR - http://www.scopus.com/inward/record.url?scp=84863066778&partnerID=8YFLogxK

U2 - 10.1145/2087756.2087864

DO - 10.1145/2087756.2087864

M3 - Conference contribution

AN - SCOPUS:84863066778

SN - 9781450310604

T3 - Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry

SP - 561

EP - 564

BT - Proceedings of VRCAI 2011

T2 - 10th International Conference on Virtual Reality Continuum and Its Applications in Industry, VRCAI'11

Y2 - 11 December 2011 through 12 December 2011

ER -

Du P, Zhou Y, Xing Q, Hu X. Improved SIFT matching algorithm for 3D reconstruction from endoscopic images. In Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry. 2011. p. 561-564. (Proceedings of VRCAI 2011: ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications to Industry). doi: 10.1145/2087756.2087864

Improved SIFT matching algorithm for 3D reconstruction from endoscopic images

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this