Lancaster EPrints

The influence of multi-sensor video fusion on object tracking using a particle filter

Mihaylova, L. and Loza, A. and Nikolov, S. G. and Lewis, J. J. and Canga, E.-F. and Li, J. and Dixon, T. and Canagarajah, C. N. and Bull, D. R. (2006) The influence of multi-sensor video fusion on object tracking using a particle filter. In: Informatik für Menschen. Gesellschaft für Informatik, Bonn, pp. 354-358. ISBN 978-3-88579-187-4

Full text not available from this repository.

Abstract

This paper investigates how the object tracking performance is affected by the fusion quality of videos from visible (VIZ) and infrared (IR) surveillance cameras, as compared to tracking in single modality videos. The videos have been fused using the simple averaging, and various multiresolution techniques. Tracking has been accomplished by means of a particle filter using colour and edge cues. The highest tracking accuracy has been obtained in IR sequences, whereas the VIZ video was affected by many artifacts and showed the worst tracking performance. Among the fused videos, the complex wavelet and the averaging techniques, offered the best tracking performance, comparable to that of IR. Thus, of all the methods investigated, the fused videos, containing complementary contextual information from both single modality input videos, are the best source for further analysis by a human observer or a computer program.

Item Type: Contribution in Book/Report/Proceedings
Uncontrolled Keywords: image fusion ; object tracking ; particle filtering ; infrared cameras ; visible cameras ; video data ; surveillance
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: Faculty of Science and Technology > School of Computing & Communications
Faculty of Arts & Social Sciences > History
ID Code: 1186
Deposited By: Dr L Mihaylov
Deposited On: 04 Feb 2008 08:48
Refereed?: No
Published?: Published
Last Modified: 17 Sep 2013 09:33
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/1186

Actions (login required)

View Item