MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition

Abstract

Deep learning has offered new ideas in SAR ship target recognition. Although many methods improve the recognition performance through the improvement of loss function and migration of deep networks, scattering features as the important intrinsic features of SAR targets, need to be considered in the SAR ship recognition tasks. To introduce the scattering features into the deep network and characterize the features of ship targets more comprehensively, a multi-scale global scattering feature association network (MGSFA-Net) for SAR ship target recognition is proposed in this paper. In the network, the SAR ship target is firstly separated from the background by fine target segmentation. Then, the scattering centers (SCs) of ship targets are extracted and converted to local graph structures based on the k-Nearest Neighbors (KNN) algorithm. The local graph structures are associated by the scattering center feature association (SCFA) module and enhanced by the multi-scale feature enhancement (MSFE) module to produce the multi-scale global scattering features. Moreover, the deep features of the targets are extracted by the multi-kernel deep feature extraction (MKDFE) module to characterize the high-dimensional information. Finally, the scattering features and deep features are fused by weighted integration to enrich the diversity of features. The experimental results on the FUSAR-Ship and OpenSARShip dataset show that, the MGSFA-Net can significantly improve the recognition performance, even on a few-shot condition with the accuracy increasing over 2%-3%. The feature distribution and visualization show the effectiveness of the MGSFA-Net to characterize the multi-scale global scattering association features.

Zero-Shot SAR Target Recognition Based on a Conditional Generative Network with Category Features from Simulated Images

“…Additionally, network architectures like recurrent neural networks (RNN) [10] and graphic neural networks (GNN) [11] can also play a unique role in the image recognition task. The deep learning methods have demonstrated an outstanding performance in SAR image recognition [12][13][14][15][16]. However, deep learning methods are data-driven and typically require a large amount of data for effective feature extraction.…”

SAR Multi-Angle Observation Method for Multipath Suppression in Enclosed Spaces

“…Neural network methods, renowned for their adaptability, processing capability, and robustness, have been widely used in various industries. Their application in SAR target detection and ghost image suppression has been thoroughly investigated, with research mainly focusing on training networks to distinguish targets from clutter, suppress clutter, and extract targets [13][14][15][16][17][18][19]. However, these methods demand significant data and parameter input and are characterized by high computational complexity.…”

Dual-Task Network for Terrace and Ridge Extraction: Automatic Terrace Extraction via Multi-Task Learning

“…Established methodologies include visual interpretation [7,8], texture-spectral techniques [9,10], and object-based classification [11,12]. Although traditional manually crafted features possess clear meanings and interpretable mathematical formulas, these types of features overly rely on the accumulation of expert knowledge, leading to limitations in achieving high recognition performance and excellent generalization capabilities [13]. As spatial resolution heightens, so does the semantic detail related to features, such as boundary definition and the spatial organization of diverse terrain attributes.…”