TNN-STME: A Matrix Decomposition Method for SAR Ship Real-Time Detection Using 2-D Asymmetric Resolution Mode

Maritime ship detection is an essential prerequisite for targeting key objectives and safeguarding the security of territorial waters. The all-day and all-weather operational capability of synthetic aperture radar (SAR) makes SAR-based ship detection indispensable for maritime surveillance. Marine surveillance requires extensive coverage for large-scale searches. But there is a contradiction between high resolution and wide swath, which cannot be taken into account. Most existing marine surveillance modes generally exchange extensive coverage at the expense of spatial resolution. The 2-D detailed information is lost in this way, which is not conducive to target classification. Furthermore, real-time detection becomes a challenge under the constraints of limited on-board conditions. In this article, a novel marine surveillance mode is proposed. It divides the target search task into two parts: wide-area target detection in 2-D asymmetric resolution mode (2-D-ARM) and key target focusing in 2-D high-resolution mode. In the context of 2-D-ARM, the sparsity of the targets and the joint sparse low-rank characteristics of the background are studied, and a low-rank approximation model is developed to accomplish the task of real-time ship detection. The experiments show that the proposed method can realize the sparse target matrix extraction (STME) through matrix decomposition. Using Sentinel-1A, Japanese Advanced Land Observing Satellite (ALOS) PALSAR, and Gaofen3 single-polarization single-look complex data, the 2-D-ARM imaging is simulated, and a dataset is built to verify the processing performance of the proposed method.