SAR image segmentation based on dynamical K-means clustering algorithm

doi:10.7523/j.issn.2095-6134.2016.05.015

Abstract

Abstract:

We present our study on SAR image segmentation based on K-means clustering. We analyze dynamical K-means clustering algorithms and improve the adaptation degree function computation method which divides the raw adaptation degree function by a direct ratio function of the sample number in clustering. Millimeter SAR image segmentation results verify that, for urban area, road, and bridge scenes segmentation, dynamical K-means clustering algorithm and adaptive dynamical K-means clustering algorithm with the improved adaptation degree function computation method have the same segmentation quality while the segmentation efficiency is higher than before.

Key words: synthetic aperture radar(SAR), image segmentation, clustering, K-means

CLC Number:

TN957

XING Tao, HUANG Youhong, HU Qingrong, LI Jun, WANG Guanyong. SAR image segmentation based on dynamical K-means clustering algorithm[J]. , 2016, 33(5): 674-678.

References

[1] Ghasr M T, Case J T, Zoughi R. Novel reflectometer for millimeter-wave 3-D holographic imaging[J]. IEEE Instrumentation and Measurement Society, 2014, 63(5):1328-1336.
[2] Fjortoft R, Gaudin J, Pourthie N, et al. KaRIn on SWOT:characteristics of near-nadir Ka-band interferometric SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(4):2172-2185.
[3] Anghel A, Vasile G, Cacoveanu R, et al. Short-range wideband FMCW radar for millimetric displacement measurements[J]. IEEE Transactions on Geoscience and Remote Sensing,2014, 52(9):5633-5642.
[4] Zhang S X, Xing M D, Xia X G, et al. Focus improvement of high-squint SAR based on azimuth dependence of quadratic range cell migration correction[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(1):150-154.
[5] Fiss J, Curless B, Szeliski R. Refocusing plenoptic images using depth-adaptive splatting[C]//Proc of IEEE International Conference on Computational Photography. 2014:1-9.
[6] Garren D A. Smear signature morphology of surface targets with arbitrary motion in spotlight synthetic aperture radar imagery[J]. IET Radar, Sonar & Navigation, 2014, 8(5):435-448.
[7] 折小强, 仇晓兰, 韩冰, 等. 一种基于变换域的滑动聚束SAR调频率估计方法[J]. 雷达学报, 2014, 3(4):419-427.
[8] 邢涛, 李军, 王冠勇, 等. 基于非均匀快速傅里叶变换的SAR方位向运动补偿算法[J]. 电子与信息学报, 2014, 36(5):1023-1029.
[9] 赵冠雄, 沈汀. 高分辨率SAR图像桥梁自动提取算法[J]. 计算机工程与设计, 2014, 35(8):2793-2797.
[10] 陈祥,孙俊,尹奎英, 等. 基于Otsu与海域统计特性的SAR图像海陆分割算法[J]. 数据采集与处理, 2014, 29(4):603-608.
[11] 张新野. 基于聚类分析的图像分割方法研究[D].大连:大连海事大学,2012.
[12] 梁烨炜. K-均值聚类算法的改进及其应用[D].长沙:湖南大学,2012.
[13] Sulaiman S N, Isa N A M. Adaptive fuzzy-K-means clustering algorithm for image segmentation[J]. IEEE Transactions on Consumer Electronics, 2010, 56(14):2661-2668.
[14] 赵丽. 全局K-均值聚类算法研究与改进[D].西安:西安电子科技大学,2013.
[15] Likas, Vlassis M, Verbeek J. The global k-means clustering algorithm[J]. Pattern Recognition, 2003, 36(2):451-461.
[16] Mashor M Y. Hybrid training algorithm for RBF network[J]. International Journal of the Computer, 2000, 8(2):50-65.
[17] Borsotti M, Campadelli P, Schettini R. Quantitative evaluation of color image segmentation results[J]. Pattern Recognition Letters, 1998, 19(8):741-747.