崔宗勇,,
曹宗杰,
杨建宇
电子科技大学信息与通信工程学院 成都 611731
基金项目:国家自然科学基金(61971101, 61801098)，自动目标识别国家重点实验室基金(6142503190201)
详细信息
作者简介:周正：周 正(1995–)，男，四川眉山人，电子科技大学信息与通信工程学院在读博士研究生，主要研究方向为SAR目标检测识别等
崔宗勇(1984–)，男，山东菏泽人，电子科技大学信息与通信工程学院副教授，主要研究方向为SAR图像处理、目标识别、深度学习等
曹宗杰(1977–)，男，山西太谷人，电子科技大学信息与通信工程学院教授，主要研究方向为SAR目标检测识别、图像处理、人工智能等
杨建宇(1963–)，男，电子科技大学教授，博士生导师，主要研究方向为雷达前视成像、实孔径超分辨成像、双多基合成孔径雷达成像。获国家出版基金资助出版专著1部。获省部级奖6项、国家技术发明二等奖2项
通讯作者:崔宗勇 zycui@uestc.edu.cn
责任主编：计科峰 Corresponding Editor: JI Kefeng中图分类号:TN959.72
计量
文章访问数:444
HTML全文浏览量:74
PDF下载量:164
被引次数:0
出版历程
收稿日期:2021-05-06
修回日期:2021-07-14
网络出版日期:2021-07-29
Feature-transferable Pyramid Network for Cross-scale Object Detection in SAR Images
ZHOU Zheng,CUI Zongyong,,
CAO Zongjie,
YANG Jianyu
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Funds:The National Natural Science Foundation of China (61971101, 61801098), Science and Technology on Automatic Target Recognition Laboratory (ATR) Fund (6142503190201)
More Information
Corresponding author:CUI Zongyong, zycui@uestc.edu.cn
摘要
摘要:SAR图像多尺度目标检测能够实现大场景SAR图像中关键目标的定位与识别，是SAR图像解译的关键技术之一。然而针对尺寸相差较大的SAR目标的同时检测，即跨尺度目标检测问题，现有目标检测方法难以实现。该文提出一种基于特征转移金字塔网络(FTPN)的SAR图像跨尺度目标检测方法。在特征提取阶段采用特征转移方法，实现各层特征图的有效连接，实现不同尺度特征图的提取；同时采用空洞卷积群方法，增大特征提取的感受野，促使网络提取到大尺度目标特征。上述环节能够有效保留不同尺寸目标特征，从而实现SAR图像中跨尺度目标的同时检测。基于高分三号SAR数据、SSDD数据集及高分辨率SAR舰船检测数据集-2.0等数据集的试验表明，该文方法能够实现SAR图像中机场、舰船等跨尺度目标的检测，在已有数据集上mAP达96.5%，较特征金字塔网络算法提升8.1%，并且整体性能优于现阶段最新的YOLOv4等目标检测算法。
关键词:SAR目标检测/
特征金字塔/
特征转移/
空洞卷积群/
跨尺度
Abstract:Multiscale object detection in Synthetic Aperture Radar (SAR) images can locate and recognize key objects in large-scene SAR images, and it is one of the key technologies in SAR image interpretation. However, for the simultaneous detection of SAR objects with large size differences, that is, cross-scale object detection, existing object detection methods are difficult to extract the features of cross-scale objects, and also difficult to realize cross-scale object simultaneous detection. In this study, we propose a multiscale object detection method based on the Feature-Transferable Pyramid Network (FTPN) for SAR images. In the feature extraction stage, the feature migration method is used to obtain an effective mosaic of the feature images of each layer and extract feature images with different scales. Simultaneously, the void convolution method is used to increase the receptive field of feature extraction and aid the network in extracting large object features. These steps can effectively preserve the features of objects of different sizes, to realize the simultaneous detection of cross-scale objects in SAR images. The experiments based on the GaoFen-3 SAR dataset, SAR Ship Detection Dataset (SSDD), and high-resolution SSDD-2.0 show that the proposed method can detect cross-scale objects, such as airports and ships in SAR images, and the mean Average Precision (mAP) can reach 96.5% on the existing dataset, which is 8.1% higher than that of the characteristic pyramid network algorithm. Moreover, the overall performance of the proposed method is better than that of the latest YOLOv4 and other object detection algorithms.
Key words:SAR object detection/
Feature pyramid/
Feature-transfer/
Dilated convolution group/
Cross-scale
PDF全文下载地址:
https://plugin.sowise.cn/viewpdf/198_a85d1b61-fbbf-4ee8-aa2e-1582bd21d62b_R21059
