Subpixel detection of surface mines in hyperspectral images

Glenn E. Healey; David Slater

doi:10.1117/12.542344

21 September 2004 Subpixel detection of surface mines in hyperspectral images

Glenn E. Healey, David Slater

Proceedings Volume 5415, Detection and Remediation Technologies for Mines and Minelike Targets IX; (2004) https://doi.org/10.1117/12.542344
Event: Defense and Security, 2004, Orlando, Florida, United States

Abstract

Hyperspectral signatures for surface mines in airborne images can have substantial variability due to the environmental conditions and subpixel mixing. Signatures are also affected by the condition of the mine. We show that a subspace representation for mine spectral properties can be used as the basis for an algorithm for subpixel mine detection that is invariant to the illumination and atmospheric conditions. A background model is estimated from the image data to support subpixel detection. The intrinsic spectral reflectance of the mine is the only input required by the algorithm. We demonstrate the performance of the algorithm for several mine types over a range of conditions and altitudes in visible through near-infrared hyperspectral images. Several of the mine types appear at a scale that is significantly smaller than a pixel.

Citation Download Citation

Glenn E. Healey and David Slater "Subpixel detection of surface mines in hyperspectral images", Proc. SPIE 5415, Detection and Remediation Technologies for Mines and Minelike Targets IX, (21 September 2004); https://doi.org/10.1117/12.542344

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available