Segmentation of SAR image based on Kullback-Leibler distance and regular tessellation

被引：0
|
作者：
Zhao Q.-H. [1 ]
Gao J. [2 ]
Zhao X.-M. [1 ]
Li Y. [1 ]
机构：
[1] School of Geomatics, Liaoning Technical University, Fuxin
[2] China Sciences Group Remote Sensing Group Technology Co Ltd, Tianjin
来源：
Kongzhi yu Juece/Control and Decision | 2018年 / 33卷 / 10期
关键词：
KL distance; M-H algorithm; Regular tessellation; SAR image segmentation;
D O I：
10.13195/j.kzyjc.2017.0758
中图分类号：
学科分类号：
摘要：
In this paper, a segmentation method for synthetic aperture radar(SAR) images based on Kullback-Leibler(KL) distance and regular tessellation is proposed. Firstly, the image domain is divided into several sub-blocks by a regular tessellation, and the divided blocks are considered as basic processing units during segmentation. It is assumed that all pixels in a sub-block follow Gaussian distribution, while to modeling feature field of a given image. Then a general Potts model is utilized to model relationship between neighbor sub-blocks in label field. According to Bayes theorem, the posterior probability model is obtained by combining pixels' feature and sub-blocks' labels. Thereafter, the heterogeneity coefficient between classes is characterized with KL distance, and the corresponding probability distribution function is constructed by a non-constrained Gibbs distribution. Combining the posterior probability model and the non-constrained Gibbs distribution, the image segmentation model is established. In order to simulate the segmentation model, a Metropolis-Hastings(M-H) sampling method is designed, including the operations of changing label and splitting sub-blocks. By analyzing the segmentation results of the proposed algorithm and the comparing algorithms, the validity and superiority of the proposed algorithm are fully verified. © 2018, Editorial Office of Control and Decision. All right reserved.
引用
收藏
页码：1767 / 1774
页数：7
相关论文
共 28 条
  • [1] Wu S.H., Wu Y.Q., Zhou J.J., Et al., SAR river image segmentation based on reciprocal gary entropy and improved Chan-Vese model, Acta Geodaetica et Cartographica Sinica, 44, 11, pp. 1255-1262, (2015)
  • [2] Hu Z.L., An unsupervised change detection approach based on KI dual thresholds under the generalized Guass model assumption in SAR images, Acta Geodaetica et Cartographica Sinica, 42, 1, pp. 116-122, (2013)
  • [3] Qin X.X., Zou H.X., Zhou S.L., Et al., Region based classification of SAR images using Kullback-Leibler distance between generalized Gamma distributions, IEEE Geoscience and Remote Sensing Letters, 12, 8, pp. 1655-1659, (2015)
  • [4] Chen J.H., Zhao Y.J., Lai T., Et al., Geometric parameters extraction method of ship target in high resolution TerraSAR-X image, Control and Decision, 30, 6, pp. 1135-1138, (2015)
  • [5] Xu Y.X., Chen F., Scene matching algorithm based on CenSurE for SAR/INS integrated navigation system, Control and Decision, 26, 8, pp. 1175-1180, (2011)
  • [6] Chen Y.F., SAR image segmentation based on GLCM of geometric region and region map, (2014)
  • [7] Li Q.J., Yang X.Z., Wu K.W., Et al., Synthetic Aperture Radar image segmentation using a regional gamma mixture model, J of Remote Sensing, 18, 5, pp. 1024-1033, (2014)
  • [8] Zhang Z.J., Shui P.L., SAR image segmentation algorithm using hierarchical region merging with edge penalty, J Electronics & Information Technology, 37, 2, pp. 261-267, (2015)
  • [9] Wu Y., Jiao J.M., Yang X.L., Et al., Segmentation algorithm for SAR images based on fusion of HMT in the contourlet domain and D-S theory of evidence, Acta Geodaetica et Cartographica Sinica, 40, 2, pp. 148-155, (2011)
  • [10] Zhao W., Tian Z., Yang L.J., Et al., SARimage segmentation using local smoothing weighted graph cut, J of Optoelectronics·Laser, 25, 11, pp. 2212-2217, (2014)
123