Non-Gaussian clustering of SAR images for glacier change detection

• Main Authors: Vahid Akbari, Anthony Doulgeris, Torbjørn Eltoft
• Other Authors: The Pennsylvania State University CiteSeerX Archives
• Format: Text
• Language: English
• Subjects: Non-Gaussian; Statistical modeling; Arctic; Asar
• Online Access: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1025.6812; http://munin.uit.no/bitstream/handle/10037/3092/article.pdf%3Bjsessionid%3D88B41996396680CEEA152500EA279589?sequence%3D5

Our aim is to use unsupervised, non-Gaussian cluster-ing of Arctic glaciers for post-classification change de-tection. Firstly, we demonstrate the consistency of non-Gaussian clustering algorithms for Envisat ASAR im-ages by characterizing the expected random error level for different SAR acquisition conditions (such as inci-dence angle).This allows us to determine whether an ob-served variation is statistically significant and therefore can be used for post-classification change detection of Arctic glaciers. Real significant change was not detected with mixed configurations during the time period of this study.