Sense-Through-Foliage Target Detection Based on Sparse Representation and Gaussian Mixture Models

Abstract

This paper investigates the impact of weather on target recognition and classification based on ultra wideband (UWB) signal and proposes a new method, named sparse representation-gaussian mixture model (SR-GMM), to model targets in different weather conditions. Sparse representation is used for feature extraction and the likelihood ratio is calculated to obtain the corresponding target type to realize the identification and classification of targets. Finally, the SR-GMM algorithm is compared with other improved SVM methods. The experiment results demonstrate that SR-GMM is effective and stable for target detection under a variety of weather conditions and can adaptively recognize targets as the weather changes without relearning.