基于改进快速区域卷积神经网络的视频SAR运动目标检测算法研究  

Research on Video SAR Moving Target Detection Algorithm Based on Improved Faster Region-based CNN

作　　者：闫贺[1] 黄佳 李睿安 王旭东[1] 张劲东[1] 朱岱寅[1] YAN He;HUANG Jia;LI Ruian;WANG Xudong;ZHANG Jingdong;ZHU Daiyin(College of Electronic Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210000,China)

机构地区：[1]南京航空航天大学电子信息工程学院,南京210000

出　　处：《电子与信息学报》2021年第3期615-622,共8页Journal of Electronics & Information Technology

基　　金：中央高校基本科研业务费专项资金(NS2019024)。

摘　　要：针对传统视频SAR(ViSAR)运动目标检测方法存在的帧间配准难度大、快速运动目标阴影特征不明显、虚警概率高等问题,该文提出一种基于改进快速区域卷积神经网络(Faster R-CNN)的视频SAR运动目标检测方法。该方法结合Faster R-CNN深度学习算法,利用K-means聚类方法对anchor box的长宽及长宽比进行预处理,并采用特征金字塔网络(FPN)架构对视频SAR运动目标的“亮线”特征进行检测。与传统方法相比,该方法具有实现简单、检测概率高、虚警概率低等优势。最后,通过课题组研制的Mini-SAR系统获取的实测视频SAR数据验证了新方法的有效性。To solve the problems of inter-frame registration difficult,unclear shadow characteristics of fast moving targets and high false alarm probability in traditional Video Synthetic Aperture Radar(ViSAR)moving target detection methods,a novel video SAR moving target detection method based on improved Faster Region-based Convolutional Neural Networks(Faster R-CNN)is proposed.Combining with the deep learning algorithm of Faster R-CNN,the new method applies the K-means clustering method to preprocess the length,width and aspect ratio of the anchor box.Besides,the Feature Pyramid Networks(FPN)network architecture is used to detect the‘bright line’feature of the video SAR moving targets.Compared with traditional methods,the proposed method has the advantages of simple implementation,high detection probability and low false alarm probability.Finally,the effectiveness of the new method is verified by the measured video SAR data obtained from the Mini-SAR system developed by our project team.

关 键 词：视频SAR 运动目标检测 快速区域卷积神经网络 特征金字塔网络 K-MEANS 

分 类 号：TN957.51[电子电信—信号与信息处理]