Share Email Print

Proceedings Paper

Change detection on UGV patrols with respect to a reference tour using VIS imagery
Author(s): Thomas Müller
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Autonomous driving robots (UGVs, Unmanned Ground Vehicles) equipped with visual-optical (VIS) cameras offer a high potential to automatically detect suspicious occurrences and dangerous or threatening situations on patrol. In order to explore this potential, the scene of interest is recorded first on a reference tour representing the 'everything okay' situation. On further patrols changes are detected with respect to the reference in a two step processing scheme. In the first step, an image retrieval is done to find the reference images that are closest to the current camera image on patrol. This is done efficiently based on precalculated image-to-image registrations of the reference by optimizing image overlap in a local reference search (after a global search when that is needed). In the second step, a robust spatio-temporal change detection is performed that widely compensates 3-D parallax according to variations of the camera position. Various results document the performance of the presented approach.

Paper Details

Date Published: 19 May 2015
PDF: 12 pages
Proc. SPIE 9460, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications XII, 94600I (19 May 2015); doi: 10.1117/12.2182663
Show Author Affiliations
Thomas Müller, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)

Published in SPIE Proceedings Vol. 9460:
Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications XII
Daniel J. Henry; Gregory J. Gosian; Davis A. Lange; Dale Linne von Berg; Thomas J. Walls; Darrell L. Young, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?