基于表征转换机的SAR图像目标分割方法

赵晓辉; 姜义成; 朱同宇

doi:10.12000/JR16066

基于表征转换机的SAR图像目标分割方法

doi: 10.12000/JR16066

(哈尔滨工业大学哈尔滨 150001)

基金项目:

国家自然科学基金资助项目（201306120111）

详细信息

作者简介:
赵晓辉(1988–),男,内蒙古赤峰人,哈尔滨工业大学博士研究生,主要研究方向为机器学习和图像目标识别;姜义成(1964–),男,黑龙江哈尔滨人,教授,哈尔滨工业大学电子与信息学院电子工程系主任,博士生导师,主要研究方向为雷达信号处理;朱同宇(1992–),男,黑龙江哈尔滨人,哈尔滨工业大学硕士研究生,主要研究方向为雷达成像与目标识别。

通讯作者:
姜义成jiangyc@hit.edu.cn

计量
- 文章访问数: 2052
- HTML全文浏览量: 312
- PDF下载量: 1111
- 被引次数: 0
出版历程
- 收稿日期: 2016-04-05
- 修回日期: 2016-06-20
- 网络出版日期: 2016-08-28

Target Segmentation Method in SAR Images Based on Appearance Conversion Machine

(Harbin Institute of Technology, Harbin 150001, China)

Funds:

The National Natural Science Foundation of China (201306120111)

摘要

摘要: 针对SAR(Synthetic Aperture Radar)图像中的目标分割问题，由于目标与杂波空间模式(像素强度和分布)不同，通过分析图像空间模式的方式可达到分辨目标和杂波并分割目标的目的。该文基于表征转换机理论提出一种有效的SAR图像目标分割方法，该算法分析SAR图像中的空间模式，计算其与参考杂波图像的相似程度，最后将与参考杂波相似程度较高的部分消除以达到分割目标的目的，并在衡量相似度部分使用基于累积直方图的自动阈值选取办法。仿真和实测数据的实验验证了此算法的有效性。
- 合成孔径雷达 /
- 目标分割 /
- 表征转换机 /
- 极限学习机
Abstract: Differences between the spatial pattern (pixel intensity and distribution) of targets and clutter allow target segmentation to be achieved by analyzing spatial patterns in Synthetic Aperture Radar (SAR) images. This paper thus proposes a target segmentation method for SAR images based on the appearance conversion machine theory. The proposed method analyses the spatial patterns in SAR images and calculates the degree of similarity between the SAR image and the reference clutter images. Subsequently, regions that show high similarity to reference clutter images are erased so that segmentation can be achieved. To evaluate the degree of similarity, we also use an automatic threshold selection method based on the cumulative histogram of the similarity imge. Experimental results using simulation and real data verify the effectiveness of the proposed method.
- Synthetic Aperture Radar (SAR) /
- Target segmentation /
- Appearance Conversion Machine (ACM) /
- Extreme Learning Machine (ELM)

HTML全文

参考文献(20)

[1]	程江华, 高贵, 库锡树, 等. 高分辨率SAR图像道路交叉口检测与识别新方法[J]. 雷达学报, 2012, 1(1): 100-108. Cheng Jiang-hua, Gao Gui, Ku Xi-shu, et al.. A novel method for detecting and identifying road junctions from high resolution SAR images[J]. Journal of Radars, 2012, 1(1): 100-108.
[2]	李光廷, 杨亮, 黄平平, 等. SAR图像相干斑抑制中的像素相关性测量[J]. 雷达学报, 2012, 1(3): 301-308. Li Guang-ting, Yang Liang, Huang Ping-ping, et al.. The pixel-similarity measurement in SAR image despeckling[J]. Journal of Radars, 2012, 1(3): 301-308.
[3]	Sauvola J and Pietikinen M. Adaptive document image binarization[J]. Pattern Recognition, 2000, 33(2): 225-236.
[4]	Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[5]	Zhao X, Jiang Y, and Zhang Y. Automatic binarization method in ISAR image[C]. IEEE International Geoscience and Remote Sensing Symposium, Milan, 2015: 5415-5418.
[6]	Stagliano D, Lupidi A, Berizzi F, et al.. Exploitation of COSMO-SkyMed system for detection of ships responsible for oil spills[C]. 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, 2012: 915-918.
[7]	Leng X, Ji K, Yang K, et al.. A bilateral CFAR algorithm for ship detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(7): 1536-1540.
[8]	Liao M, Wang C, Wang Y, et al.. Using SAR images to detect ships from sea clutter[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(2): 194-198.
[9]	Mcconnell A I and Oliver C J. Comparison of segmentation methods with standard CFAR for point target detection[C]. Proceedings SPIE 3497, SAR Image Analysis, Modeling, and Techniques, 1998. doi: 10.1117/12.331364.
[10]	Lankoande O, Hayat M M, and Santhanam B. Segmentation of SAR images based on Markov random field model[C]. IEEE International Conference on Systems, Man and Cybernetics, 2005, 3: 2956-2961.
[11]	HUANG Yu, FU Kun, and WU Yi-Rong. Image segmentation method using K-means based on Markov random field[J]. Acta Electronica Sinica, 2009, 37(12): 2700-2704.
[12]	Fowlkes C, Belongie S, Fan C, et al.. Spectral grouping using the Nystrm method[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 214-225.
[13]	Zhang X, Hao L, Liu F, et al.. Spectral clustering ensemble applied to SAR image segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(7): 2126-2136.
[14]	Kusakunniran W, Wu Q, Zhang J, et al.. A new view-invariant feature for cross-view gait recognition[J]. IEEE Transactions on Information Forensics and Security, 2013, 8(10): 1642-1653.
[15]	Zhao X, Jiang Y, Stathaki T, et al.. Gait recognition method for arbitrary straight walking paths using appearance conversion machine[J]. Neurocomputing, 2015, 173(3): 530-540.
[16]	Huang G B, Zhou H, Ding X, et al.. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2012, 42(2): 513-529.
[17]	Huang G B, Chen L, and Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Transactions on Neural Networks, 2006, 17(4): 879-892.
[18]	Huang G B and Chen L. Enhanced random search based incremental extreme learning machine[J]. Neurocomputing, 2008, 71(16/18): 3460-3468.
[19]	Huang G B, Zhu Q Y, and Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1/3): 489-501.
[20]	Gao G, Zhao L, Zhang J, et al.. A segmentation algorithm for SAR images based on the anisotropic heat diffusion equation[J]. Pattern recognition, 2008, 41(10): 3035-3043.