系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (12): 3631-3640.doi: 10.12305/j.issn.1001-506X.2022.12.06

• 电子技术 • 上一篇    下一篇

基于感知向量的光学遥感图像舰船检测

潘超凡, 李润生*, 许岩, 胡庆, 牛朝阳, 刘伟   

  1. 信息工程大学数据与目标工程学院, 河南 郑州 450001
  • 收稿日期:2021-07-20 出版日期:2022-11-14 发布日期:2022-11-24
  • 通讯作者: 李润生
  • 作者简介:潘超凡(1997—), 男, 硕士研究生, 主要研究方向为基于深度学习的目标检测|李润生(1985—), 男, 副教授, 博士, 主要研究方向为遥感目标检测|许岩(1993—), 女, 讲师, 博士, 主要研究方向为大数据分析|胡庆(1997—), 男, 硕士研究生, 主要研究方向为遥感影像目标检测|牛朝阳(1981—), 男, 副教授, 博士, 主要研究方向为雷达信息处理与对抗|刘伟(1981—), 男,副教授, 博士, 主要研究方向为智能信息处理、遥感图像分析
  • 基金资助:
    青年科学基金(41901378)

Ship detection of optical remote sensing images based on aware vectors

Chaofan PAN, Runsheng LI*, Yan XU, Qing HU, Chaoyang NIU, Wei LIU   

  1. School of Data and Target Engineering, University of Information Engineering, Zhengzhou 450001, China
  • Received:2021-07-20 Online:2022-11-14 Published:2022-11-24
  • Contact: Runsheng LI

摘要:

针对光学遥感图像中近岸舰船目标检测干扰大、虚警率高的问题, 在基于包围框边缘感知向量(box boundary-aware vectors, BBAVectors)检测网络的基础上提出了改进方法。首先在特征融合网络后加入一个有监督的注意力模块来增强目标区域信息, 削弱无关背景信息干扰; 然后利用边界感知向量间的几何关系设计了一个自监督损失函数, 用以加强向量间的耦合关系, 防止向量独立性导致包围框出现不规则形状。实验结果显示, 在HRSC2016数据集L2级检测任务中, 改进模型检测结果的平均精度相较于原网络提高了6.91%, 有效抑制了背景噪声的干扰, 降低了近岸舰船目标检测的虚警率, 证明了改进方法的有效性。

关键词: 光学遥感图像, 舰船目标检测, 包围框边缘感知向量, 监督, 注意力模块

Abstract:

To solve the problem of severe interference and high false positive rate in ship detection from remote sensing images, an enhanced method based on the box boundary-aware vectors (BBAVectors) detection network is proposed.Firstly, a supervised attention module is added to the feature fusion network to enhance the relevant information within the target region and reduce the interference of irrelevant background information. Then a self-supervised loss function is proposed based on the geometric relations among the boundary vectors to guarantee the coupling relation between vectors and prevent the irregular shape of the bounding boxes caused by vectors' independence. Experimental results in the L2 level detection task on the HRSC2016 dataset show that the mean average precision of the detection results for the proposed model gets improved by 6.91% compared with the original network. The proposed model can effectively suppress the interference of background noise and reduce the false alarm rates in near-shore ship detection, which demonstrates its effectiveness.

Key words: optical remote sensing images, ship targets detection, box boundary-aware vectors (BBAVectors), supervised, attention module

中图分类号: