Detection of land mines with hyperspectral data

Abstract

The objective of the U.S. Army Hyperspectral Mine Detection Phenomenology (HMDP) program was to determine if spectral discriminants exist that are useful for the detection of land mines. Statistically significant mine signature data were collected over a wide spectral range (0.35 to 14 im) and analyzed to identify robust spectral features that might serve as discriminants for new airborne sensor concepts. Detection metrics which characterize the detectability of land mines and which predict the detection performance of a general class of hyperspectral detection algorithms were selected and applied. Detection performance of land mines was analyzed against background type, age of buried mines and possible sensor design parameters. This paper describes the results of this analysis and presents EO/IR hyperspectral sensor and algorithm design concepts that could potentially be used to operationally detect buried land mines.

A survey of landmine detection using hyperspectral imaging

“…Therefore, they collected high quality hyperspectral signatures of background materials and mines, measured temporal effects on buried landmines and measured a statistically significant set of hyperspectral signatures of surface and buried mines in natural soils, under variations of controlled variables. The spectral analysis results obtained during the HMDP project recordings are presented in [40]. The authors concluded that uncontrolled variables, mainly wind and rainfall, usually affect the results.…”

Thermal Signature Characteristics of Vehicle/Terrain Interaction Disturbances: Implications for Battlefield Vehicle Classification

“…Separate studies of soil thermal emission signatures related to disturbance/compaction have also noted results quite similar to our own. Kenton et al 17 observed a progressive increase in spectral contrast in emissivity spectra of buried mine emplacements recorded over a 4week period after burial, which they attributed to the diminishing spectral effect of fine particles adhering to larger soil grains as fines weathered deeper into the soil. Johnson et al 13 noted that emissivity spectra of pristine soils recorded in the field tended to exhibit greater contrast than reflectance spectra of samples of the same soils measured in the laboratory and that tamping of a sample increased contrast in its spectrum.…”

The Application of Remote Sensing for Detecting Mass Graves: An Experimental Animal Case Study from Costa Rica*

“…This same data would also be applicable to larger sites where several pixels would represent the grave. For buried landmine detection, a problem analogous to the detection of graves, it was found that a resolution finer than half of the burial scar did not improve discrimination accuracy using hyperspectral data (61,62). Additional studies are necessary to examine data with a coarser spatial resolution such as imagery from civilian hyperspectral satellite sensors (e.g., 17 m for the PROBA‐CHRIS sensor).…”