首页 | 期刊介绍 | 编委会 | 道德声明 | 投稿指南 | 常用下载 | 过刊浏览 | In English
引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  下载PDF阅读器  关闭
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 131次   下载 0  
分享到: 微信 更多
一种增强型YOLOv3的SAR舰船检测方法
张明, 王子龙, 吕晓琪, 喻大华, 张宝华, 李建军
内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室
摘要:
近年来,海战场成为现代战争的主要作战区域之一,舰船目标逐渐成为海上重点监测对象,能否快速准确地识别海战场舰船目标的战术意图,给指挥员的决策提供必要的支持,这关系到一场海上战役的成败。随着合成孔径雷达(Synthetic Aperture Radar, SAR)成像技术的不断发展,大量SAR图像可用于舰船目标检测与识别。现在利用SAR图像进行舰船目标检测与识别,已经成为重要的海洋应用之一。针对传统SAR图像舰船检测方法准确率较低的问题,本文在YOLOv3的基础上,结合感受野(Receptive Field Block,RFB)模块,提出一种增强型的SAR舰船检测方法。该方法在最近公开的SAR图像舰船检测数据集上平均准确率(mAP)值达到了91.50%,与原YOLOv3相比提高了0.92%。实验结果充分表明本文提出的算法在SAR舰船的检测中具有较好的检测效果。
关键词:  舰船检测  SAR  YOLO  遥感图像
DOI:
分类号:TP751
基金项目:国家自然科学(61771266, 81871430, 61663036, 62066036);内蒙古自治区高等学校科学研究项目(NJZY18150);内蒙古杰出青年培育(2018JQ02)。
An enhanced YOLOv3 method for SAR ship detection
ZHANG Ming, WANG Zi-long, LV Xiao-qi, YU Da-hua, ZHANG Bao-hua, LI Jian-jun
Key Laboratory of Pattern Recognition and Intelligent Image Processing,College of Information Engineering,Inner Mongolia University of Science and Technology,Baotou,Inner Mongolia
Abstract:
Recently, the naval battlefield has become one of the main operational areas of modern war, ship targets have gradually become the key monitoring objects at sea. The success of a maritime battle is related to the ability to quickly and accurately identify the tactical intent of ship targets in the naval battlefield, and to provide necessary support for the commander’s decision-making. With the development of Synthetic Aperture Radar (SAR) imaging technology, a large number of SAR images can be used for ship target detection and recognition. It has become one of the most important Marine applications of SAR data to detect and identify Marine targets using SAR images. In order to solve the problem of low accuracy of traditional SAR image ship detection, this paper proposes an enhanced SAR ship detection based on the algorithm YOLOv3 and the DarkNet-53 network structure, combined with the Receptive Field Block (RFB) module. This method achieves the average accuracy (mAP) value of 91.50% in the recently published SAR image detection data set, and improves 0.92% compared with the original YOLOv3. The experimental results show that the algorithm proposed in this paper has a good detection effect in SAR ship detection.
Key words:  SAR  Ship detection  Remote sensing image  YOLO
版权所有 《海洋科学》 Copyright©2008 All Rights Reserved
主管单位:中国科学院 主办单位:中国科学院海洋研究所
地址:青岛市市南区福山路32号  邮编:266071  电话:0532-82898755  E-mail:marinesciences@qdio.ac.cn
技术支持:北京勤云科技发展有限公司