北京交通大学学报2017，Vol.41Issue(6)：1-7,7.DOI:10.11860/j.issn.1673-0291.2017.06.001
基于低复杂度卷积神经网络的星载SAR舰船检测
Spaceborne SAR ship detection based on low complexity convolution neural network
摘要
Abstract
Spaceborne SAR(Synthetic Aperture Radar)ship detection has been widely used in the sea rescue,territorial security and so on.As the traditional detection methods still have some shortages like high false alarm rate,this paper introduces the convolutional neural network (CNN)that has a powerful characterization for the spaceborne SAR ship detection.Aiming at the accurate and rapid demand of SAR ship detection,it proposes a spaceborne SAR ship detection al-gorithm based on low complexity CNN.The algorithm first combines the characteristics of space-borne SAR images,uses the ROI extraction method to achieve the target rough extraction,get-ting the suspicious target slices and their corresponding location information,then accurately classifies all the suspicious target slices by the constructed CNN with low complexity to determine the target of the ship so as to realize the target detection of the ship.The experimental results show that the algorithm can achieve accurate spaceborne SAR ship detection.Compared with the traditional two-parameter CFAR and the methods based on the existing network frame-works (LeNet, GoogLeNet ), the proposed algorithm has better performance and shorter detection time,which can effectively reduce the missed rate and the false alarm rate.关键词
图像处理/目标检测/星载SAR舰船/卷积神经网络/低复杂度Key words
image processing/target detection/spaceborne SAR ship/convolutional neural network/low complexity分类
信息技术与安全科学引用本文复制引用
赵保军,李珍珍,赵博雅,冯帆,邓宸伟..基于低复杂度卷积神经网络的星载SAR舰船检测[J].北京交通大学学报,2017,41(6):1-7,7.基金项目
国家自然科学基金(91438203) （91438203）
国家高技术研究发展计划(863 项目)(2015AA8012011C,2015AA8017032K) Foundation items:National Natural Science Foundation of China(91438203) （863 项目）
National High-tech R&D Program of China (863 Program) (2015AA8012011C ,2015AA8017032K) （863 Program）
