Ship Detection in Large-scale SAR Images Based on Dense Spatial Attention and Multi-level Feature Fusion

摘要：

　　In recent years,ship detection in large-scale synthetic aperture radar(SAR)images attracts more attentions and becomes a re-search hotspot.But it still faces some challenges,such as strong interference of background noise and very small ship targets.This paper proposes a novel anchor-free detector,small target detector(STDet),based on dense spatial attention(DSA)and multi-level fea-ture fusion(MFF).DSA is applied first to the backbone(Resnet50)in order to filter out the background noise and obtain more advanced semantic features.Then,a MFF network is used after the backbone to improve the detection accuracy,especially for small targets,by fusing the location and semantic information of different level fea-ture maps.Finally,the refined features are fed to detection head to get the final results.Experiments are conducted on the public dataset LS-SSDD-v1.0.Experimental results prove our STDet has good performance for ship detection in large-scale SAR images.

关键词： SAR image ship detection anchor-free dense spatial attention multi-level feature fusion

作者: Limin Zhang Yingjian Liu Qingxiang Guo Haoyu Yin Yue Li Pengting Du

作者单位: Department of Computer Science and Technology,Ocean University of China Qingdao,Shandong,China

会议类型: 国际会议

会议名称: 2021中国图灵大会(ACM Turing Celebration conference-China 2021

会议地点: 合肥

会议语种:英文

页码: 87-91

在线出版日期: 2021-07-30（万方平台首次上网日期，不代表论文的发表时间）