Title :
Multispectral image feature selection for land mine detection
Author :
Clark, Gregory A. ; Sengupta, Sailes K. ; Aimonetti, William D. ; Roeske, Frank ; Donetti, John G.
Author_Institution :
Lawrence Livermore Nat. Lab., CA, USA
fDate :
1/1/2000 12:00:00 AM
Abstract :
The authors´ system uses a camera that acquires registered images in six spectral bands and a supervised-learning algorithm to detect metal and plastic land mines. Results show that even with a small sample size, the detection performance is good and holds promise for future work with larger data sets
Keywords :
buried object detection; feature extraction; geophysical signal processing; geophysical techniques; image processing; military systems; multidimensional signal processing; remote sensing; terrain mapping; IR method; buried object detection; camera; detection performance; feature extraction; geophysical measurement technique; image feature selection; image processing; infrared imaging; land mine detection; land surface; landmine; metal; military system; multispectral remote sensing; optical imaging; plastic land mine; registered image; supervised-learning algorithm; terrain mapping; visible region; Cameras; Cascading style sheets; Helicopters; Landmine detection; Layout; Multispectral imaging; Pixel; Plastics; Sea measurements; Target recognition;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
