IEEE Transactions on Geoscience and Remote Sensing · 2010 · 14 citations · 14 references
ComputingEarth SciencesGeoinformaticsComputer VisionMine SurveyingRemote SensingGeospatial Computer VisionImage ClassificationMine MappingRemote Sensing Image AnalysisRemote Sensing ImageryHyperspectral AnalysisHyperspectral Imagery AnalysisLandmine DetectionPattern MatchingPatternsPredictionRemote Sensing In Mine SurveysSpectral Characteristics
Whereas overhead infrared imagery shows promise for detecting buried landmines, detection algorithms must deal with the daunting challenge of distinguishing between landmines and clutter objects which frequently possess similar spatial and spectral characteristics to landmines. However, groups of clutter features are rarely related spatially in the same way that groups of mines are related. For this reason, the recognition of minefield patterns in overhead landmine imagery can be useful to the detection of mines in minefields. In this paper, we present a simple method for detecting grid patterns in imagery, discuss means by which the method may be extended to a more general category of patterns, provide a method for the automated prediction of the locations of undetected mines based upon the observed pattern, and finally we discuss applications. Examples are provided using longwave infrared hyperspectral imagery.
14