机械制造与自动化2017，Vol.46Issue(1)：111-115,5.DOI:10.19344/j.cnki.issn1671-5276.2017.01.030
基于卷积神经网络的SAR目标多维度特征提取
SAR Target Multi-Dimension Feature Extraction via Convolutional Neural Network
摘要
Abstract
Target recognition based on SAR sensor plays more and more important role in military and civil fields.The feature extraction is the key process in SAR target recognition.Two problems exist in the traditional recognition process based on the pattern features:one,the pattern features belongs to one-dimension representation,so the ability of representing the targets in the complex background is limited;two the is pattem feature selection mainly depends on the experience,so the ability of self-learning and automatic recognition has to be significantly improved.The SAR target recognition method based on deep convolutional neural network (DCNN) is proposed in this paper.The model of deep convolutional neural network is built to obtain the hierarchical feature representation for SAR targets.The feature selection problem is solved with the self-learning ability of convolutional neural network to achieve SAR target automatic recognition.Experiments on the MSTAR dataset show that SAR target recognition rate based on the proposed convolutional neural network model reaches 93.99％.Compared with the traditional one-dimension pattern recognition method,the proposed method is better.关键词
雷达/目标识别/多维度特征/特征提取/合成孔径雷达/卷积神经网络Key words
radar/target recognition/multi-dimension feature/feature extraction/synthetic aperture radar/convolutional neural network分类
信息技术与安全科学引用本文复制引用
张慧,肖蒙,崔宗勇..基于卷积神经网络的SAR目标多维度特征提取[J].机械制造与自动化,2017,46(1):111-115,5.基金项目
四川省教育厅科研项目(16ZB0446) （16ZB0446）
