Saliency-Based SAR Target Detection via Convolutional Sparse Feature Enhancement and Bayesian Inference

Abstract

Traditional synthetic aperture radar (SAR) target detection methods use matched filtered SAR images as input, and the detection performance is restricted due to the high sidelobes and speckle noise of these images. Sparse SAR imaging methods developed in recent years provide the advantages of reducing sidelobes, noise, and clutter. The imaging results obtained with these methods could help improve the SAR target detection performance. In this article, to improve the target detection performance using sparse SAR images as input, we proposed a convolutional sparse feature enhancement method to meet the needs of Bayesian saliency detection. The proposed Bayesian saliency joint target detection method comprised the following three steps: first, to obtain sparse SAR images with continuous contours and fewer holes in the target area, we proposed a convolutional L 1 sparse regularization method. Second, a regularization parameter optimization method was derived to quickly obtain optimal regularization parameters for saliency detection. Finally, target detection results were obtained through a superpixel-based Bayesian saliency joint detector. Extensive experiments verified that the proposed method could improve the SAR target detection accuracy in complex backgrounds.

Multi-scale contrastive learning method for PolSAR image classification

“…Polarimetric synthetic aperture radar (PolSAR) is a type of active microwave imaging radar, which uses polarimetric radar waves to measure and analyze the properties of natural surfaces. 1 Due to its all-day and all-weather characteristics, PolSAR image has been widely used in various fields of remote sensing applications and has made remarkable achievements, such as terrain classification, 2 target detection, 3 and environmental monitoring. 4 PolSAR image classification has become a widely studied topic in the field of interpreting PolSAR images.…”