Enhanced Detection of Hidden Targets Using Multi-Discriminant Ladar

To achieve the optimal detection and classification of hidden targets, a tightly linked sensor and algorithm design effort will be required. The Phase II work described here focuses on using data from an existing Ladar sensor to explore how high-dimensional spatial, spectral and polarimetric data can be used to detect and classify hidden targets. The general approach will be to apply specific dimensionality reduction techniques to experimental data to map the data into a lower dimension feature space. A point-surface invariant metric technique will be used to compare the identified features to a set of target CAD models. The statistical properties of the resulting classification will be examined in terms of detectability, separability, and robustness to noise. The following dimensionality reduction techniques will be explored: Diffusion Mapping and ISOMAP.