New Framework for Airborne Minefield Detection Using Markov Marked Point Processes

摘要

This dissertation is an investigation into how shape/spectral similarity of the mine signature and the minefield-like spatial distribution can be exploited simultaneously to improve the performance for patterned and unpatterned minefield detection in highly cluttered environments. The minefield decision is based on the detected targets obtained by an anomaly detector, such as the RX algorithm, in the image of a given field segment. Spectral, shape or texture features at the target locations are used to model the likelihood of the targets being potential mines. The spatial characteristic of the minefield structure is captured by the expected distribution of nearest neighbor distances of the detected mine locations. The clutter targets in the minefield are assumed to constitute a Poisson point process. The overall minefield detection problem is formulated as a Markov marked point process (MMPP) that is based on local attributes and relative spatial distribution of the target signatures. Minefield decision is formulated under binary hypothesis testing using maximum log-likelihood ratio. A quadratic heuristic search algorithm is developed to identify a set of detections that maximizes the minefield log- likelihood ratio.