|University of Cambridge > Engineering Department|
PhD student in the Machine Intelligence Laboratory and at Queens' College
supervised by Professor Roberto Cipolla
funded by Toshiba (2012-16)
for more up-to-date info, please see my webpage here.
An Image-Based System for Change Detection on Tunnel Linings
Stent, S., Gherardi, R., Stenger, B., Soga, K. and Cipolla, R.
IAPR International Conference on Machine Vision Applications, 2013
(oral, best paper award)
This paper presents an automated system for detecting visual changes on tunnel linings. By registering new images to a three-dimensional tunnel surface model, recovered using Structure and Motion techniques, we are able to detect and localize changes accurately in order to assist visual inspection by a human expert. We formulate the problem of detecting changes probabilistically and exploit different feature maps and a novel geometric prior to achieve invariance to noise and nuisance sources such as parallax and lighting changes. System performance is assessed on a real data set labelled with ground-truth and collected with a prototype capture device. By localizing, organising and classifying image data automatically, our system is a step towards higher frequency visual inspection at a reduced cost.
|email:||Simon Stent (sais2)|
|address:||Department of Engineering. University of Cambridge, Trumpington Street, Cambridge CB2 1PZ|
© Cambridge University Engineering Department
||| Cambridge University | CUED | MIL ||
Information provided by
Simon Stent (sais2)|
Last updated: Jan 2014