Remote sensing with Spotter land mine detection

摘要

Spotter is a flexible extensible software tool for interactive development, application and testing of algorithms for detecting objects in multispectral imagery. Images from different sensors are registered, and low level features are extracted. Feature selection and reduction algorithms generate reduced dimension feature sets. Feature images are soft classified, pixel by pixel, and the output is used to drive a preliminary detection process to identify regions of interest (ROI). Geometric features are extracted from the ROI, which are then soft classified, and a detection decision is made for each. Many algorithms are provided, including Gaussian mixture model classifiers and shared mixture classifiers. Mixture of experts classifiers enable physically inspired classifiers to be incorporated to complement statistical designs.