Abstract
Terrain classification is an important application of SAR data interpretation. The orientation between radar and the ground objects has great impact on the discrimination of polarimetric feature. Besides, the existed methods can not make sure that the pixels at the edge of a category are classified correctly as well as that pixels at a region of the same category are consistent. To solve these problems, a new supervised classification method based on Markov random filed model using Wishart distance (WD-MRF) for SAR image classification is proposed, which combines polarimetric feature with image spatial information. First, the feature space is constructed by polarimetric feature in the rotation domain and the texture feature obtained from the gray-level co-occurrence matrix. Then the initial result obtained from support vector machine is optimized with the proposed WD-MRF method. Experiments with the benchmark data sets of Flevoland show that the overall classification accuracy of WD-MRF is much higher than support vector machine.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
