In practical applications of automated terrain classification from high-resolution polarimetric synthetic aperture radar (PolSAR) imagery, different terrain types may inherently contain a high level of internal variability, as when a broadly defined class (e.g., 'trees') contains elements arising from multiple subclasses (pine, oak, and willow). In addition, real-world factors such as the time of year of a collection, the moisture content of the scene, the imaging geometry, and the radar system parameters can all increase the variability observed within each class. Such variability challenges the ability of classifiers to maintain a high level of sensitivity in recognizing diverse elements that are within-class, without sacrificing their selectivity in rejecting out-of-class elements. In an effort to gauge the degree to which classifiers respond robustly in the presence of intraclass variability and generalize to untrained scenes and conditions, we compare the performance of a suite of classifiers across six broad terrain categories from a large set of polarimetric synthetic aperture radar (PolSAR) image sets. The main contributions of this article are as follows: 1) an analysis of the robustness of a variety of current state-of-the art classification algorithms to intraclass variability found in PolSAR image sets, and 2) the associated PolSAR image and feature data that Sandia is releasing to the research community with this publication. The analysis of the classification algorithms we provide will serve as a benchmark of performance for the future PolSAR terrain classification algorithm research and development enabled by the image sets and data provided. By sharing our analysis and high-resolution fully polarimetric Sandia data with the research community, we enable others to develop and assess a new generation of robust terrain classification algorithms for PolSAR.
A new method is introduced for combining information from multiple sources to support one-class classification. The contributing sources may represent measurements taken by different sensors of the same physical entity, repeated measurements by a single sensor, or numerous features computed from a single measured image or signal. The approach utilizes the theory of statistical hypothesis testing, and applies Fisher's technique for combining p-values, modified to handle nonindependent sources. Classifier outputs take the form of fused p-values, which may be used to gauge the consistency of unknown entities with one or more class hypotheses. The approach enables rigorous assessment of classification uncertainties, and allows for traceability of classifier decisions back to the constituent sources, both of which are important for high-consequence decision support. Application of the technique is illustrated in two challenge problems, one for skin segmentation and the other for terrain labeling. The method is seen to be particularly effective for relatively small training samples.