This paper describes a system for detecting vehicles in airborne downward looking infrared linescan imagery, and in particular, the use of a Pearl-Bayes Network (PBN) to combine disparate sources of evidence. Here the primary source of evidence is a vehicle detection algorithm with supporting evidence being provided by vehicle track and shadow detectors. The spatial arrangement of the vehicles also provides useful contextual evidence since vehicles often move in convoy or are clustered into small groups when encamped. This observation is the basis for allowing neighbouring detections to re-enforce one another and for incorporating a feedback loop with which to increase the sensitivity of the vehicle detection algorithm within areas of suspected activity.
Vehicle detection in infrared linescan imagery using belief networks
01.01.1995
5 pages
Aufsatz (Zeitschrift)
Englisch
object detection , image classification , shadow detectors , belief networks , airborne downward looking imagery , vehicle track detectors , neighbouring detections , Bayes methods , vehicle detection , Pearl-Bayes network , contextual evidence , image segmentation , remote sensing , feedback loop , feature extraction , infrared imaging , tracking , infrared linescan imagery
Active airborne linescan experiment
SPIE | 1994
|Computational imaging using a multi-linescan light-field camera
British Library Online Contents | 2014
|Application of linescan vision system for rear cog alignment
Kraftfahrwesen | 1989
|6k-pixel 160-MHz CCD linescan sensor [3965-07]
British Library Conference Proceedings | 2000
|