Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·
 

Sensor fusion for antipersonnel landmine detection, a case study

Attachments

Author: Breejen, E. den · Schutte, K. · Cremer, F.
Type:article
Date:1999
Publisher: SPIE
Place: Bellingham, WA.
Institution: TNO Fysisch en Elektronisch Laboratorium
Source:Dubey, A.C.Harvey, J.F.Broach, J.T.Dugan, R.E., Detection and Remediation Technologies for Mines and Minelike Targets IV, 5-9 April 1999, Orlando, FL, 1235-1245
series:
Proceedings of SPIE
Identifier: 95196
doi: doi:10.1117/12.357003
Keywords: Fuzzy sets · Infrared imaging · Metal detectors · Ordnance · Sensor data fusion · Anti-personnel landmine detection · Ground explosive ordnance detection system (GEODE) · Split clusters on oversized patches (SCOOP) · Explosives

Abstract

In this paper the multi sensor fusion results obtained within the European research project GEODE (Ground Explosive Ordnance Detection system) are presented. The lay out of the test lane and the individual sensors used are described. The implementation of the SCOOP algorithm improves the ROC curves, as the false alarm surface and the number of false alarms both are taken into account. The confidence grids, as produced by the sensor manufacturers, of the sensors are used as input for the different sensor fusion methods implemented. The multi sensor fusion methods implemented are Bayes, Dempster-Shafer, fuzzy probabilities and rules. The mapping of the confidence grids to the input parameters for fusion methods is an important step. Due to limited amount of the available data the entire test lane is used for training and evaluation. All four sensor fusion methods provide better detection results than the individual sensors.