Abstract To accurately model the complicated statistical characteristics of pixel intensities in a homogeneous region and obtain accurate segmentation results, a high resolution synthetic aperture radar(SAR) image segmentation algorithm based on hierarchical Gamma mixture model(HGaMM) is proposed. HGaMM is constructed by several Gamma mixture models to model the asymmetrical, heavy-tailed and multimodal distribution of pixel intensities. To reduce the influence of image noise on segmentation, Markov random field is employed to model the label field for introducing the spatial neighboring relationship between pixels into HGaMM. Based on Bayesian theory, the segmentation model is built by posterior distribution of model parameters. Markov Chain Monte Carlo algorithm is designed to simulate the segmentation model. Segmentation experiment is conducted on simulated and real SAR images. The results show that the proposed algorithm obtains more accurate segmentation results than other algorithms.
Fund:Supported by National Natural Science Foundation of China(No.41301479,41271435), Natural Science Foundation of Liaoning Province(No.2015020090)
Corresponding Authors:
LI Yu(Corresponding author), Ph.D., professor. His research interests include remote sensing image processing.
About author:: SHI Xue, Ph.D. candidate. Her research interests include remote sensing image processing.ZHAO Quanhua, Ph.D., professor. Her research interests include remote sensing image processing.
[1] HUANG Y, LEVY-VEHEL J, FERRO-FAMIL L, et al. Three-Dimensional Imaging of Objects Concealed Below a Forest Canopy Using SAR Tomography at L-Band and Wavelet-Based Sparse Estimation. IEEE Geoscience & Remote Sensing Letters, 2017, 14(9): 1454-1458. [2] XU L L, WONG A, CLAUSI D A. An Enhanced Probabilistic Posterior Sampling Approach for Synthesizing SAR Imagery with Sea Ice and Oil Spills. IEEE Geoscience and Remote Sensing Letters, 2017, 14(2): 188-192. [3] 赵泉华,王 玉,李 玉.利用SAR影像区域分割方法提取海洋暗斑特征.地理科学, 2016, 36(1): 121-127. (ZHAO Q H, WANG Y, LI Y. Feature Extraction of Dark Spot Based on the SAR Image Segmentation. Scientia Geographica Sinica, 2016, 36(1): 121-127.) [4] 李敏花,柏 猛,吕英俊.自适应阈值图像边缘检测方法.模式识别与人工智能, 2016, 29(2): 177-184. (LI M H, BAI M, LÜ Y J. Adaptive Thresholding Based Edge Detection Approach for Images. Pattern Recognition and Artificial Intelligence, 2016, 29(2): 177-184.) [5] JI J, LU X J, HAN L Y, et al. Fast and Adaptive Region Merging Based on Perceptual Hashing via Multi-thresholding for SAR Image Segmentation. Remote Sensing Letters, 2016, 7(12): 1199-1208. [6] 赵泉华,赵雪梅,李 玉.基于双随机场能量函数的区域化图像分割.模式识别与人工智能, 2017, 30(1): 32-42. (ZHAO Q H, ZHAO X M, LI Y. Regional Image Segmentation Based on Energy Functions for Double Random Fields. Pattern Re-cognition and Artificial Intelligence, 2017, 30(1): 32-42.) [7] AHMED M N, YAMANY S M, MOHAMED N, et al. A Modified Fuzzy c-means Algorithm for Bias Field Estimation and Segmentation of MRI Data. IEEE Transactions on Medical Imaging, 2002, 21(3): 193-199. [8] ZHENG J, ZHANG D H, HUANG K D, et al. An Adaptive Image Segmentation Method Based on the Fuzzy c-means with Spatial Information. IET Image Processing, 2017, 12(5): 785-792. [9] CHATZIS S P. A Fuzzy Clustering Approach toward Hidden Markov Random Field Models for Enhanced Spatially Constrained Image Segmentation. IEEE Transactions on Fuzzy Systems, 2008, 16(5): 1351-1361. [10] 赵雪梅,李 玉,赵泉华.结合高斯回归模型和隐马尔可夫随机场的模糊聚类图像分割.电子与信息学报, 2014, 36(11): 2730-2736. (ZHAO X M, LI Y, ZHAO Q H. Image Segmentation by Fuzzy Clustering Algorithm Combining Hidden Markov Random Field and Gaussian Regression Model. Journal of Electronics and Information Technology, 2014, 36(11): 2730-2736.) [11] GAO G. Statistical Modeling of SAR Images: A Survey. Sensors, 2010, 10(1): 775-795. [12] 王 玉,李 玉,赵泉华.利用RJMCMC算法的可变类SAR图像分割.信号处理, 2014, 30(10): 1193-1203. (WANG Y, LI Y, ZHAO Q H. SAR Image Segmentation with Variable Classes Using RJMCMC Algorithm. Journal of Signal Processing, 2014, 30(10): 1193-1203.) [13] WANG Y, LI Y, ZHAO Q H. Segmentation of High-Resolution SAR Image with Unknown Number of Classes Based on Regular Tessellation and RJMCMC Algorithm. International Journal of Remote Sensing, 2015, 36(5): 1290-1306. [14] 张金静,李 玉,赵泉华.多主体框架下结合最大期望值和遗传算法的SAR图像分割.中国图象图形学报, 2016, 21(1): 86-94. (ZHANG J J, LI Y, ZHAO Q H. Combining the Expectation Maximization and Genetic Algorithms for SAR Image Segmentation within a MAS Framework. Journal of Image and Graphics, 2016, 21(1): 86-94.) [15] MCLACHLAN G, PEEL D. Finite Mixture Models. New York, USA: John Wiley & Sons, 2004. [16] SONG W Y, LI M, ZHANG P, et al. Unsupervised PolSAR Image Classification and Segmentation Using Dirichlet Process Mixture Model and Markov Random Fields with Similarity Measure. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(8): 3556-3568. [17] 赵泉华,石 雪,王 玉,等.可变类空间约束高斯混合模型遥感图像分割.通信学报, 2017, 38(2): 34-43. (ZHAO Q H, SHI X, WANG Y, et al. Remote Sensing Image Segmentation Based on Spatially Constrained Gaussian Mixture Model with Unknown Class Number. Journal on Communications, 2017, 38(2): 34-43.) [18] ZHUANG Y, CHEN H, BI F K, et al. Context Segmentation of Oceanic SAR Images: Application to Oil Spill Detection[C/OL]. [2018-02-20]. http://or.nsfc.gov.cn/bitstream/00001903-5/424091/1/1000014614813.pdf. [19] ZHANG H, WU Q M J, NGUYEN T M, et al. Synthetic Aperture Radar Image Segmentation by Modified Student′s T-Mixture Model. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(7): 4391-4403. [20] 赵泉华,李晓丽,赵雪梅,等.基于空间约束Student′s-T混合模型的模糊聚类图像分割.控制与决策, 2016, 31(11): 2065-2070. (ZHAO Q H, LI X L, ZHAO X M, et al. Fuzzy Clustering Algorithm Based on Spatially Constrained Student′s-T Mixture Model for Image Segmentation. Control and Decision, 2016, 31(11): 2065-2070.) [21] ZHAO Q H, LI X L, LI Y. Multilook SAR Image Segmentation with an Unknown Number of Clusters Using a Gamma Mixture Mo-del and Hierarchical Clustering. Sensors, 2017, 17(5). DOI: 10.3390/s17051114. [22] 张英海,李 玉,赵雪梅,等.ECM算法的多视SAR影像分割.遥感学报, 2016, 20(6): 1391-1401. (ZHANG Y H, LI Y, ZHAO X M, et al. ECM-Based Segmentation for Multi-look SAR Image. Journal of Remote Sensing, 2016, 20(6): 1391-1401.)
2018, Vol. 31 
