Unsupervised Classification of PolSAR Images Based on CFAR Detection of Cluster Centers

For unsupervised classification of polarimetric synthetic aperture radar (PolSAR) images, it is a challenge task to determine an appropriate number of categories. Recently, a method called clustering by fast search and find of density peaks (CFSFDP) has provided a good solution. However, it requires to select the cluster centers by visual observation, which is not only less automated but also may be difficult to implement for some data sets. Focusing on this problem, this paper proposes a method of detecting cluster centers with the constant false alarm rate (CFAR) criterion, and also applies it to the unsupervised classification of PolSAR images. In our method, a variable called center-likelihood for each data point is constructed by multiplying its local density and distance that defined in the CFSFDP algorithm. Then, after estimating the probability density of the center-likelihood, the threshold to detect cluster centers is obtained with the CFAR criterion. The effectiveness of the proposed method is verified by the experimental results of two actual PolSAR images.

[1]  Xinwu Li,et al.  Unsupervised classification of polarimetric SAR images using deep embedding network , 2017, 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA).

[2]  Heng-Chao Li,et al.  On the Empirical-Statistical Modeling of SAR Images With Generalized Gamma Distribution , 2011, IEEE Journal of Selected Topics in Signal Processing.

[3]  Hui Song,et al.  Unsupervised classification of polarimetric SAR imagery using large-scale spectral clustering with spatial constraints , 2015 .

[4]  Bastian Leibe,et al.  Superpixels: An evaluation of the state-of-the-art , 2016, Comput. Vis. Image Underst..

[5]  David A. Clausi,et al.  Unsupervised Polarimetric SAR Image Segmentation and Classification Using Region Growing With Edge Penalty , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Shuang Wang,et al.  Unsupervised classification for polarimetric SAR images based on the improved CFSFDP algorithm , 2018, International Journal of Remote Sensing.

[7]  Thomas L. Ainsworth,et al.  Unsupervised classification using polarimetric decomposition and the complex Wishart classifier , 1999, IEEE Trans. Geosci. Remote. Sens..

[8]  Lei Shi,et al.  A Global Weighted Least-Squares Optimization Framework for Speckle Filtering of PolSAR Imagery , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Zhengqin Li,et al.  Superpixel segmentation using Linear Spectral Clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Thomas L. Ainsworth,et al.  Unsupervised classification of polarimetric synthetic aperture Radar images using fuzzy clustering and EM clustering , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Huanxin Zou,et al.  Superpixel-Based Unsupervised Classification of Polsar Images with Adaptive Number of Terrain Classes , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[12]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[13]  Wenxian Yu,et al.  Superpixel-Based Classification With an Adaptive Number of Classes for Polarimetric SAR Images , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Huanxin Zou,et al.  Superpixel Generation for PolSAR Images with Global Weighted Least-Squares Filtering and Linear Spectral Clustering , 2019, 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP).

[15]  Huanxin Zou,et al.  Region-Based Classification of SAR Images Using Kullback–Leibler Distance Between Generalized Gamma Distributions , 2015, IEEE Geoscience and Remote Sensing Letters.

[16]  Si-Wei Chen,et al.  PolSAR Image Classification Using Polarimetric-Feature-Driven Deep Convolutional Neural Network , 2018, IEEE Geoscience and Remote Sensing Letters.

[17]  Huanxin Zou,et al.  A CFAR Detection Algorithm for Generalized Gamma Distributed Background in High-Resolution SAR Images , 2013, IEEE Geoscience and Remote Sensing Letters.