Multispectral image feature selection for land mine detection

Journal Article · Fri Dec 31 23:00:00 EST 1999 · IEEE Transactions on Geoscience and Remote Sensing (Institute of Electrical and Electronics Engineers)

DOI:https://doi.org/10.1109/36.823923· OSTI ID:20080339

Clark, G A; Sengupta, S K; Aimonetti, W D; Roeske, F; Donetti, J G

The 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. The goal of this work is to detect and locate buried and surface land mines, given multiple registered images of regions of the earth obtained from a Xybion six-band (400, 500, 600, 700, 800, and 900 nm) visible-wavelength, filter-wheel camera mounted in a Cessna 172 helicopter.

• Research Organization: Lawrence Livermore National Lab., CA (US); Univ. of California, Livermore, CA (US)
• Sponsoring Organization: US Department of Energy
• DOE Contract Number: W-7405-ENG-48
• OSTI ID: 20080339
• Journal Information: IEEE Transactions on Geoscience and Remote Sensing (Institute of Electrical and Electronics Engineers), Journal Name: IEEE Transactions on Geoscience and Remote Sensing (Institute of Electrical and Electronics Engineers) Journal Issue: 1PT1 Vol. 38; ISSN 0196-2892; ISSN IGRSD2
• Country of Publication: United States
• Language: English

Related Subjects

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE
ARMS CONTROL
EXPLOSIVES
IMAGE PROCESSING
MILITARY EQUIPMENT
MULTISPECTRAL SCANNERS
PATTERN RECOGNITION
VERIFICATION
VISIBLE SPECTRA