Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (7): 2150-2155.DOI: 10.11772/j.issn.1001-9081.2020081187

Special Issue: 前沿与综合应用

• Frontier and comprehensive applications • Previous Articles     Next Articles

Synthetic aperture radar ship detection method based on self-adaptive and optimal features

HOU Xiaohan, JIN Guodong, TAN Lining, XUE Yuanliang   

  1. School of Nuclear Engineering, Rocket Force University of Engineering, Xi'an Shaanxi 710025, China
  • Received:2020-08-10 Revised:2021-01-11 Online:2021-07-10 Published:2021-02-09

基于自适应和最优特征的合成孔径雷达舰船检测方法

侯笑晗, 金国栋, 谭力宁, 薛远亮   

  1. 火箭军工程大学 核工程学院, 西安 710025
  • 通讯作者: 侯笑晗
  • 作者简介:侯笑晗(1995-),女,河南林州人,硕士研究生,主要研究方向:深度学习、SAR目标检测;金国栋(1979-),男,安徽无为人,副教授,博士,主要研究方向:人工智能、计算机视觉;谭力宁(1985-),男,河南南阳人,讲师,博士,主要研究方向:人工智能、计算机视觉;薛远亮(1996-),男,四川遂宁人,硕士研究生,主要研究方向:深度学习、SAR目标检测。

Abstract: In order to solve the problem of poor small target detection effect in Synthetic Aperture Radar (SAR) target ship detection, a self-adaptive anchor single-stage ship detection method was proposed. Firstly, on the basis of Feature Selective Anchor-Free (FSAF) algorithm, the optimal feature fusion method was obtained by using the Neural Architecture Search (NAS) to make full use of the image feature information. Secondly, a new loss function was proposed to solve the imbalance of positive and negative samples while enabling the network to regress the position more accurately. Finally, the final detection results were obtained by combining the Soft-NMS filtering detection box which is more suitable for ship detection. Several groups of comparison experiments were conducted on the open SAR ship detection dataset. Experimental results show that, compared with the original target detection algorithm, the proposed method significantly reduces the missed detections and false positives of small targets, and improves the detection performance for inshore ships to a certain extent.

Key words: target detection, deep learning, Synthetic Aperture Radar (SAR) image, ship target, self-adaptive

摘要: 针对合成孔径雷达(SAR)目标舰船检测中对小目标检测效果不佳的问题,提出一种自适应锚框单阶段舰船检测方法。首先,在单阶段无锚框特征选择(FSAF)算法的基础上利用神经架构搜索(NAS)得到最优特征融合方式,以充分利用图像特征信息;然后提出新的损失函数,在解决正负样本不均衡的同时使网络能够更加精确地对位置进行回归;最后结合更适用于舰船检测的Soft-NMS过滤检测框得到最后的检测结果。在公开的SAR舰船检测数据集上进行了多组对比实验,结果表明,相比基础目标检测算法,所提出的方法对小目标的漏检和误报明显减少,且对靠岸舰船检测性能有一定提升。

关键词: 目标检测, 深度学习, 合成孔径雷达图像, 舰船目标, 自适应

CLC Number: