论文:2015,Vol:33,Issue(5):867-873
引用本文:
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
Zhou Deyun, Zeng Lina, Zhang Kun. A Novel SAR Target Detection Algorithm via Multi-Scale SIFT Features[J]. Northwestern polytechnical university

基于多尺度SIFT特征的SAR目标检测
周德云, 曾丽娜, 张堃
西北工业大学 电子信息学院, 陕西 西安 710072
摘要:
提出一种用于SAR图像目标检测的多尺度SIFT特征提取及降维方法。针对在单一尺度下无法完整描述SAR目标的问题,采用高斯尺度空间和多组种子点的方式实现多尺度SIFT特征描述,并对同一尺度和不同尺度间的描述冗余和结构冗余分别采取稀疏编码和特征统计的降维方式实现去冗余处理。在多尺度因子和尺度层数的选择上,通过定量计算选取最优描述参数,使得代表目标特征的向量既包括目标整体轮廓信息又包含图像细节描述。与传统双参数恒虚警率、单尺度SIFT特征、多尺度SIFT-PCA等方法进行对比测试,验证了该方法的有效性。
关键词:    SAR图像    目标检测    多尺度    尺度不变特征变换(SIFT)   
A Novel SAR Target Detection Algorithm via Multi-Scale SIFT Features
Zhou Deyun, Zeng Lina, Zhang Kun
Department of Electronics Engieering, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
A detection method for SAR targets based on extraction and dimensionality reduction of multi-scale SIFT features is proposed. Aiming at the problem that SAR target features cannot be completely described in single scale, we put Gaussian scale space and multi-group of seed points into use to achieve the extraction of multi-scale SIFT features. Meanwhile, there are description redundancies and structural redundancies in the same and different scales, so the method of sparse coding and features statistics is introduced to reduce redundancies and dimensionality for feature vectors. Through quantitative analysis, the most optimal parameters of multi-scale factor and number are fixed, this makes the target features contain both the overall target contour information and the image details. Comparison with traditional target detectors, such as CFAR, SIFT features and multi-scale SIFT-PCA features etc, is performed in detail. The experimental results and their analysis show preliminarily the superiorities of the proposal.
Key words:    algorithms    feature extraction    mathematical operators    optimization    principal component analysis    redundancy    synthetic aperture radar    statistics    support vector machines    target tracking    vector    multi-scale    SAR (synthetic aperture radar) images    SIFT (scale invariant feature transform)    target detection   
收稿日期: 2015-03-20     修回日期:
DOI:
基金项目: 国家自然科学基金(61401363)资助
通讯作者:     Email:
作者简介: 周德云(1964—),西北工业大学教授、博士生导师,主要从事智能控制、复杂系统建模及航空武器系统工程等研究。
相关功能
PDF(3271KB) Free
打印本文
把本文推荐给朋友
作者相关文章
周德云  在本刊中的所有文章
曾丽娜  在本刊中的所有文章
张堃  在本刊中的所有文章

参考文献:
[1] 李开明, 张群, 罗迎. 地面车辆目标识别研究综述[J]. 电子学报, 2014, 42(3):538-546 Li Kaiming, Zhang Qun, Luo Ying. Review of Ground Vehicles Recognition[J]. Acta Electronica Sinica, 2014, 42(3):538-546 (in Chinese)
[2] 王彦情, 马雷, 田原. 光学遥感图像舰船目标检测与识别综述[J]. 自动化学报, 2011, 37(9):1029-1039 Wang Yanqing, Ma Lei, Tian Yuan. State-of-the-Art of Ship Detection and Recognition in Optical Remotely Sensed Imagery[J]. Acta Automatica Sinica, 2011, 37(9):1029-1039 (in Chinese)
[3] 赵明波, 何峻, 付强. SAR图像CFAR检测的快速算法综述[J]. 自动化学报, 2012, 38(12):1885-1895 Zhao Mingbo, He Jun, Fu Qiang. Survey on Fast CFAR Detection Algorithms for SAR Image Targets[J]. Acta Automatica Sinica, 2012, 38(12):1885-1895 (in Chinese)
[4] 林旭, 洪峻, 孙显, 等. 一种基于自适应背景杂波模型的宽幅SAR图像CFAR舰船检测算法[J]. 遥感技术与应用, 2014, 29(1):75-81 Lin Xu, Hong Jun, Sun Xian, et al. New CFAR Ship Detection Algorithm Based on Adaptive Background Clutter Model in Wide Swatch SAR Images[J]. Remote Sensing Technology and Application, 2014, 29(1):75-81 (in Chinese)
[5] Shuo L, Caoe Z. SAR Image Target Detection in Complex Environments Based on Improved Visual Attention Algorithm[J]. Eurasip Journal on Wireless Communications and Networking, 2014, 2014(1):2-8
[6] Marr D. A Compututational Investigation into the Human Representation and Processing of Visual Information[M]. Cambridge, USA, MIT Press, 1998
[7] Suri S, Schwind P, Uhl J, et al. Modifications in the SIFT Operator for Effective SAR Image Matching[J]. Image Data Fusion, 2010, 1(3):243-256
[8] Wang S, You H, Fu K. BFSIFT:A Novel Method to Find Feature Matches for SAR Image Registration[J]. IEEE Trans on Geosci Remote Sense, 2012, 9(4):649-653
[9] Yang J, Yu K, Gong Y, et al. Linear Spatial Pyramid Matching Using Aparse Coding for Image Classification[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2009
[10] Liu S, Hu S, Xiao Y, et al. SAR Image Edge Detection Using Sparse Representation and LS-SVM[J]. Journal of Information & Computational Science, 2014, 11(11):3941-3947
[11] Zhao J, Guo H, Wu J. Attribute Reduction for SIFT Local Descriptors Using PCA and CAIM[C]//Proceedings of 2014 7th International Congress on Image and Signal Processing, 2015:269-274