New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis

TL;DR

This paper introduces a robust SAR target recognition method combining YOLOv4 detection, a deep CNN with small filters for noise reduction, and multi-canonical correlation analysis to enhance feature correlation and classification accuracy.

Contribution

It presents a novel fusion of YOLOv4, a deep CNN with small filters, and multi-canonical correlation analysis for improved SAR target recognition without pre-processing.

Findings

Outperforms state-of-the-art methods on MSTAR dataset

Deep CNN effectively extracts features without noise pre-processing

Multi-canonical correlation analysis improves feature correlation and classification accuracy

Abstract

Synthetic Aperture Radar (SAR) images are prone to be contaminated by noise, which makes it very difficult to perform target recognition in SAR images. Inspired by great success of very deep convolutional neural networks (CNNs), this paper proposes a robust feature extraction method for SAR image target classification by adaptively fusing effective features from different CNN layers. First, YOLOv4 network is fine-tuned to detect the targets from the respective MF SAR target images. Second, a very deep CNN is trained from scratch on the moving and stationary target acquisition and recognition (MSTAR) database by using small filters throughout the whole net to reduce the speckle noise. Besides, using small-size convolution filters decreases the number of parameters in each layer and, therefore, reduces computation cost as the CNN goes deeper. The resulting CNN model is capable of extracting very deep features from the target images without performing any noise filtering or pre-processing techniques. Third, our approach proposes to use the multi-canonical correlation analysis (MCCA) to adaptively learn CNN features from different layers such that the resulting representations are highly linearly correlated and therefore can achieve better classification accuracy even if a simple linear support vector machine is used. Experimental results on the MSTAR dataset demonstrate that the proposed method outperforms the state-of-the-art methods.