Change detection of polarimetric SAR images based on the KummerU Distribution

Quan Chen; Pengfei Zou; Zhen Li; Ping Zhang

doi:10.1117/12.2069198

Translator Disclaimer

8 November 2014 Change detection of polarimetric SAR images based on the KummerU Distribution

Quan Chen, Pengfei Zou, Zhen Li, Ping Zhang

Author Affiliations +

Proceedings Volume 9260, Land Surface Remote Sensing II; 92603V (2014) https://doi.org/10.1117/12.2069198
Event: SPIE Asia-Pacific Remote Sensing, 2014, Beijing, China

Abstract

In the society of PolSAR image segmentation, change detection and classification, the classical Wishart distribution has been used for a long time, but it especially suit to low-resolution SAR image, because in traditional sensors, only a small number of scatterers are present in each resolution cell. With the improving of SAR systems these years, the classical statistical models can therefore be reconsidered for high resolution and polarimetric information contained in the images acquired by these advanced systems. In this study, SAR image segmentation algorithm based on level-set method, added with distance regularized level-set evolution (DRLSE) is performed using Envisat/ASAR single-polarization data and Radarsat-2 polarimetric images, respectively. KummerU heterogeneous clutter model is used in the later to overcome the homogeneous hypothesis at high resolution cell. An enhanced distance regularized level-set evolution (DRLSE-E) is also applied in the later, to ensure accurate computation and stable level-set evolution. Finally, change detection based on four polarimetric Radarsat-2 time series images is carried out at Genhe area of Inner Mongolia Autonomous Region, NorthEastern of China, where a heavy flood disaster occurred during the summer of 2013, result shows the recommend segmentation method can detect the change of watershed effectively.

Citation Download Citation

Quan Chen, Pengfei Zou, Zhen Li, and Ping Zhang "Change detection of polarimetric SAR images based on the KummerU Distribution", Proc. SPIE 9260, Land Surface Remote Sensing II, 92603V (8 November 2014); https://doi.org/10.1117/12.2069198

ACCESS THE FULL ARTICLE