Title :
A forward looking infrared sensor for landmine detection that incorporates a novel method of identifying regions of interest and a fuzzy inference system
Author_Institution :
Geo-Centers Inc., Newton Centre, MA
Abstract :
Methods used to display image data, define regions of interest in the images and to automatically classify targets in a forward looking infrared sensor are described in this paper. The forward looking infrared sensor is used in conjunction with a vehicular based landmine detection system. Specific examples of performance attained on mine calibration lanes both with and without a fuzzy inference system classifier are provided. These results clearly demonstrate the efficacy and advantages of this classification approach
Keywords :
buried object detection; fuzzy logic; image classification; image sensors; inference mechanisms; infrared imaging; military computing; uncertainty handling; forward looking infrared sensor; fuzzy inference system; image classification; image data display; landmine detection; mine calibration lanes; performance; regions of interest; Cameras; Displays; Dynamic range; Image resolution; Infrared detectors; Infrared image sensors; Infrared sensors; Landmine detection; Target recognition; Vehicle detection;
Conference_Titel :
Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American
Conference_Location :
New York, NY
Print_ISBN :
0-7803-5211-4
DOI :
10.1109/NAFIPS.1999.781724
