|
|
论文:2019,Vol:37,Issue(3):587-593 |
|
|
引用本文： |
|
|
魏松杰, 蒋鹏飞, 袁秋壮, 刘梅林. 深度神经网络下的SAR舰船目标检测与区分模型[J]. 西北工业大学学报 |
|
|
WEI Songjie, JIANG Pengfei, YUAN Qiuzhuang, LIU Meilin. Detection and Recognition of SAR Small Ship Objects Using Deep Neural Network[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 深度神经网络下的SAR舰船目标检测与区分模型 |
|
| 魏松杰1,2, 蒋鹏飞1, 袁秋壮1, 刘梅林2 |
|
1. 南京理工大学 计算机科学与工程学院, 南京 210094;
2. 上海卫星工程研究所, 上海 200240 |
| 摘要: |
| 合成孔径雷达（SAR）舰船目标检测在海洋监测中发挥着越来越重要的作用。针对SAR图像中舰船目标尺寸较小，传统方法易受外部干扰无法提取精细目标特征等问题，基于深度学习技术提出一种改进的SAR图像舰船小目标检测模型，主要由候选区域提取网络（RPN）和目标检测网络组成。首先设计并训练一个能精确识别舰船小目标的CNN模型，然后利用该模型对目标检测模型共享特征提取层进行参数初始化，最后利用自采集的Sentinel-1 SAR图像舰船小目标数据集对其进行训练。实验结果表明，提出的目标检测模型对SAR图像中舰船弱小比例目标有较好的检测区分性能和抗干扰能力，对SAR图像小目标检测领域研究具有一定的参考价值。 |
| 关键词:
SAR图像
舰船目标
深度神经网络
目标检测
特征提取
候选区域提取
|
|
| Detection and Recognition of SAR Small Ship Objects Using Deep Neural Network |
|
| WEI Songjie1,2, JIANG Pengfei1, YUAN Qiuzhuang1, LIU Meilin2 |
|
1. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China;
2. Shanghai Institute of Satellite Engineering, Shanghai 200240, China |
| Abstract: |
| Synthetic aperture radar(SAR) ship target detection plays an increasingly important role in marine monitoring. Aimed at the problems of recognizing small size of ship targets in SAR images and the inability of traditional methods to extract fine target features due to external disturbances, we propose an improved SAR small target detection model based on the deep learning technology. The proposed model mainly consists of two parts:region proposal network(RPN) and object detection network. Firstly, a CNN model is designed and trained to accurately identify small ship targets. Then, the model is used to initialize the parameters of the shared feature extraction layer. Last, we train the proposed object detection model using a self-collected Sentinel-1 SAR small target dataset. The experimental results show that the proposed target detection model has better detection and recognition performance and anti-interference ability for small ship scalable targets in SAR images, and has certain reference value for the research of small target detection in SAR images. |
| Key words:
SAR image
ship target
deep neural network
target detection
feature extraction
candidate region extraction
|
|
| 收稿日期: 2018-05-31
修回日期:
|
| DOI: 10.1051/jnwpu/20193730587 |
| 基金项目: 国家自然科学基金（61472189，61802186）、航天科技创新基金（F2016020013）、赛尔网络下一代互联网技术创新项目（NGⅡ20170119）与江苏省研究生科研与实践创新（SJCX17_0103）资助 |
| 通讯作者: 刘梅林(1981-),上海卫星工程研究所副研究员,主要从事卫星总体设计研究。E-mail:meilinliu51@outlook.com
Email：meilinliu51@outlook.com |
| 作者简介: 魏松杰(1977-),南京理工大学副教授,主要从事计算机网络协议、智能服务与云计算研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] MAZZARELLA F, VESPE M, SANTAMARIA C. SAR Ship Detection and Self-Reporting Data Fusion Based on Traffic Knowledge[J]. IEEE Trans on Geoscience & Remote Sensing Letters, 2015, 12(8):1685-1689
[2] WANG C, BI F, ZHANG W, et al. An Intensity-Space Domain CFAR Method for Ship Detection in HR SAR Images[J]. IEEE Trans on Geoscience and Remote Sensing Letters, 2017, 14(4):529-533
[3] WANG S, SUN L, FAN W, et al. An Automated CNN Recommendation System for Image Classification Tasks[C]//IEEE International Conference on Multimedia and Expo, 2017:283-288
[4] BAPPY J H, ROY-CHOWDHURY A K. CNN bAsed Region Proposals for Efficient Object Detection[C]//IEEE International Conference on Image Processing, 2016:3658-3662
[5] DENG L, YANG M, QIAN Y, et al. CNN Based Semantic Segmentation for Urban Traffic Scenes Using Fisheye Camera[C]//Intelligent Vehicles Symposium, 2017:231-236
[6] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014:580-587
[7] GIRSHICK R. Fast R-CNN[C]//IEEE International Conference on Computer Vision Computer Society, 2015:1440-1448
[8] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[C]//Advances in Neural Information Processing Systems, 2015:91-99
[9] HUANG Z, PAN Z, LEI B. Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data[J]. Remote Sensing, 2017, 9(9):907
[10] 袁秋壮, 魏松杰, 罗娜. 基于深度学习神经网络的SAR星上目标识别系统研究[J]. 上海航天, 2017, 34(5):46-53 YUAN Qiuzhuang, WEI Songjie, LUO Na. Research on SAR Satellite Target Recognition System Based on Deep Learning Neural Network[J]. Aerospace Shanghai, 2017, 34(5):46-53(in Chinese)
[11] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017:2117-2125 |
|
|
|
相关文献: |
|
|
1．周德云, 曾丽娜, 张堃.基于多尺度SIFT特征的SAR目标检测[J]. 西北工业大学学报, 2015,33(5): 867-873 |
|
|
|
|
|
|
