Target Recognition Using Linear Classification of High Range Resolution Radar Profiles

摘要

High Range Resolution (HRR) radar profiles map three-dimensional target characteristics onto one-dimensional signals that represent reflected radar intensity along target extent. In this thesis, second through fourth statistical moments are extracted from HRR profiles and input to Fisher Linear Discriminant (FLD) classifiers. An iterative classification process is applied that gradually minimizes required a priori knowledge about the target data. It is found that the second through fourth statistical moments of HRR profiles are useful features in the FLD classification of dissimilar targets and they provide reasonable discrimination of similar targets. Greater than 69% correct classification for two-target scenarios and greater than 60% correct classification for three-target scenarios is obtained using a single HRR profile extracted from a full 360-degree aspect angle window. A key contribution of this thesis is the demonstration that simple statistical moment features and simple linear classifiers can be used to effectively classify HRR profiles.