PURSUIT: an automatic classification tool for remote sensing data

PURSUIT (Projection Understanding and Recognition from a SUite of intelligent Tools) has been under development at the Naval Research Laboratory for a number of years. It is a versatile software tool designed to address the problem of automatic feature extraction and classification from remote sensing data. Although the tool can be applied to a variety of applications outside of the field of remote sensing, it is particularly useful for automated remote sensing imagery analysis. To date, the package has been applied to imagery from a variety of different sensor types including: multispectral, hyperspectral, synthetic aperture radar (SAR), and multi-sensor data. Because of its modular design, PURSUIT is re-configurable and the suite of algorithms that comprise it can be flexibly combined to address new applications as they arise. As such, new algorithms can be easily added. Algorithms included in the present corpus consist of a variety of in-house algorithms, as well as standard algorithms derived from many areas of the statistical pattern recognition literature, including adaptive vector quantization, unsupervised and supervised feature extraction and classification, and neural networks. Each module contains a number of different preprocessing and post-processing options, and the input data may be spectral, spatial, or spatial-spectral. The modular design of the package allows data from multiple sources to be combined in the same overall automatic classification model.