Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy

Abstract: 

This paper introduces a structure from motion (SfM)-based surface reconstruction method for images including weak textures and structures. In SfM, the quality of the determination of homologous points between images plays a key role in terms of reconstruction performances. However, classical feature matching-based methods as integrated in the state-ofthe-art SfM algorithms are often inoperative for images with weak structures and textures. This contribution describes a dense optical flow-based solution enabling the point correspondence determination in such scenes. The accuracy and robustness of the proposed method were validated using results obtained for a phantom with known dimensions and with real medical data, respectively. Complex internal stomach wall surfaces were constructed using gastroscopic images.

up
0 users have voted:

Comments

No comment

Paper Details

Authors:
Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf
Submitted On:
11 September 2019 - 11:39am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Tan-Binh Phan
Paper Code:
1132
Document Year:
2019
Cite

Document Files

ICIP2019_Poster.pdf

(6)

Subscribe

[1] Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf , "Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4591. Accessed: Sep. 15, 2019.
@article{4591-19,
url = {http://sigport.org/4591},
author = {Tan-Binh Phan; Dinh-Hoan Trinh; Dominique Lamarque; Didier Wolf },
publisher = {IEEE SigPort},
title = {Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy},
year = {2019} }
TY - EJOUR
T1 - Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy
AU - Tan-Binh Phan; Dinh-Hoan Trinh; Dominique Lamarque; Didier Wolf
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4591
ER -
Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf . (2019). Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy. IEEE SigPort. http://sigport.org/4591
Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf , 2019. Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy. Available at: http://sigport.org/4591.
Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf . (2019). "Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy." Web.
1. Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf . Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4591