Since Synthetic Aperture Radar (SAR) targets are full of coherent speckle noise, the traditional deep learning models are difficult to effectively extract key features of the targets and share high computational complexity. To solve the problem, an effective lightweight Convolutional Neural Network (CNN) model incorporating transfer learning is proposed for better handling SAR targets recognition tasks. In this work, firstly we propose the Atrous-Inception module, which combines both atrous convolution and inception module to obtain rich global receptive fields, while strictly controlling the parameter amount and realizing lightweight network architecture. Secondly, the transfer learning strategy is used to effectively transfer the prior knowledge of the optical, non-optical, hybrid optical and non-optical domains to the SAR target recognition tasks, thereby improving the model's recognition performance on small sample SAR target datasets. Finally, the model constructed in this paper is verified to be 97.97% on ten types of MSTAR datasets under standard operating conditions, reaching a mainstream target recognition rate. Meanwhile, the method presented in this paper shows strong robustness and generalization performance on a small number of randomly sampled SAR target datasets.
Abstract-Synthetic aperture radar (SAR) automatic target recognition (ATR) has been receiving more and more attention in the past two decades. But the problem of how to overcome SAR target ambiguities and azimuth angle variations has still left unsolved. In this paper, a multi-scale local phase quantization plus biomimetic pattern recognition (BPR) method is presented to solve these two difficulties. By applying multiple scales local phase quantization (LPQ) on the observed SAR images, the blur and azimuth invariant features can be extracted, and these features are fusion at consecutive multiple scales to achieve better results. Then PCA method is applied to further reduce the feature dimension and achieve its efficiency. Finally, high dimensional space geometry covering method based on BPR theory is adopted to construct hyper sausage neuron links for target recognition. Experiments on the MSTAR database show that the proposed method can achieve satisfying recognition accuracy compared with other stateof-the-art methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.