BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:An Automated Computer Vision System for Damage Detection and Monit
 oring in Tunnel Inspection - Krisada Chaiyasarn\, CUED
DTSTART:20110304T160000Z
DTEND:20110304T170000Z
UID:TALK29593@talks.cam.ac.uk
CONTACT:Anama Lowday
DESCRIPTION:One of the greatest challenges facing civil engineers in the 2
 1st century is the stewardship of aging civil engineering infrastructure. 
 Maintainance and repair works are regularly carried out to ensure safety a
 nd serviceability of these structures. One common practice in such mainten
 ance work is visual inspection in order to detect and to monitor anomalies
  (e.g. cracks\, spalling and staining) on the tunnel surface. This routine
  inspection work has a number of drawbacks\, including\, labour-intensive\
 , costly\, and inaccurate. In this project\, a prototype of an automated d
 amage detection system based on state-of-the-art computer vision technolog
 y was develped to assist the inspection work. The system is composed of tw
 o parts: (1) a novel method in inspection reporting\; and (2) automatic de
 tection of changes from images. \n\nThe first part of the system created a
  mosaic image from a large image database taken from real underground envi
 ronment. The system is composed of two main components: a Structure from M
 otion (SfM) system\; and the 3D surface fitting of a point cloud. These co
 mponents enable our system to mosaic images obtained from free camera moti
 on as well as to cope with a complex geometry of the scene\, unlike most s
 tandard image stitching software packages that fail to generate good mosai
 cs because they rely on a number of strong assumptions on the camera motio
 n or on the scene geometry. The main advantage of our system is that it ca
 n create a large mosaic image of the tunnel surface with little distortion
 . Subsequently\, it can be used as an inspection report.\n\nThe second par
 t of the system automatically performs image analysis by change detection\
 , which is an approach to monitor structural changes from images taken at 
 different times. Although\, there have been some promising change detectio
 n algorithms in the civil engineering literatures\; all of them assume ima
 ges are taken at the same camera positions. On the contrary\, our system c
 an perform change detection on images obtained from arbitrary camera posit
 ions\, which was made possible by accurate registration from the SfM syste
 m. The output from the first part\, i.e. a mosaic image\, is used as a dat
 abase in which a newly acquired image will be compared in order to detect 
 changes on the tunnel surface. \n\nIn this talk\, the framework of our sys
 tem will be explained. The contributions made in each component in our sys
 tem pipeline will be highlighted and some key results will be presented.\n
LOCATION:Engineering Department - Lecture Room 6
END:VEVENT
END:VCALENDAR