Answers are grounded in this paper and cite their sources.
With the development of deep learning (DL), research on ship classification in synthetic aperture radar (SAR) images has made remarkable progress. However, such research has primarily focused on classifying large ships with distinct features, such as cargo ships, containers, and tankers. The classification of SAR fishing vessels is extremely challenging because of two main reasons: 1) the small size and minor interclass differences of fishing vessels make learning fine-grained features difficult, and 2) determining fishing vessel types is difficult, resulting in a lack of labeled data. Hence, after designing a process framework for vessel tagging, we construct a high-resolution fine-grained fishing vessel classification dataset (FishingVesselSAR), which contains 116 gillnetters, 72 seiners, and 181 trawlers. We then propose a novel DL model (FishNet) that aims to strengthen feature extraction and utilization. In FishNet, we introduce four innovative modules to ensure superior performance in SAR fishing vessel classification: a multipath feature extraction (MUL) module, a feature fusion (FF) module, a multilevel feature aggregation (MFA) module and a parallel channel and spatial attention (PCSA) module. Furthermore, we design an adaptive loss function to achieve better classification performance by mitigating the effects of class imbalance. In this paper, we report extensive ablation studies conducted to confirm the efficacy of the five improvements listed above. Sufficient comparisons with 33 advanced methods from the DL and SAR target classification communities demonstrate that FishNet achieves a SAR fishing vessel classification accuracy of 89.79%, which is 6.77% higher than that of the second-best method.
No takes yet. Share an insight, caveat, or question.
Guan et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: