Imperial College London
Portrait Picture

DrEdwardJohns

Faculty of Engineering, Department of Computing

Senior Lecturer
 
 
 
//

Contact

 

e.johns Website

 
 
//

Location

 

365ACE ExtensionSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Ye:2014:10.1007/978-3-319-10470-6_40,
author = {Ye, M and Johns, E and Giannarou, S and Yang, G-Z},
doi = {10.1007/978-3-319-10470-6_40},
pages = {316--323},
publisher = {Springer International Publishing},
title = {Online Scene Association for Endoscopic Navigation},
url = {http://dx.doi.org/10.1007/978-3-319-10470-6_40},
year = {2014}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Endoscopic surveillance is a widely used method for moni-toring abnormal changes in the gastrointestinal tract such as Barrett'sesophagus. Direct visual assessment, however, is both time consumingand error prone, as it involves manual labelling of abnormalities on alarge set of images. To assist surveillance, this paper proposes an onlinescene association scheme to summarise an endoscopic video into scenes,on-the-y. This provides scene clustering based on visual contents, andalso facilitates topological localisation during navigation. The proposedmethod is based on tracking and detection of visual landmarks on thetissue surface. A generative model is proposed for online learning of pair-wise geometrical relationships between landmarks. This enables robustdetection of landmarks and scene association under tissue deformation.Detailed experimental comparison and validation have been conductedon in vivo endoscopic videos to demonstrate the practical value of ourapproach.
AU  - Ye,M
AU  - Johns,E
AU  - Giannarou,S
AU  - Yang,G-Z
DO  - 10.1007/978-3-319-10470-6_40
EP  - 323
PB  - Springer International Publishing
PY  - 2014///
SN  - 0302-9743
SP  - 316
TI  - Online Scene Association for Endoscopic Navigation
UR  - http://dx.doi.org/10.1007/978-3-319-10470-6_40
UR  - http://hdl.handle.net/10044/1/27120
ER  -
Download