UBC Theses and Dissertations
Segmentation and classification of polarimetric SAR data using spectral graph partitioning Ersahin, Kaan
Polarimetric Synthetic Aperture Radar (POLSAR) data have been commercially available for the last few years, which has increased demand for its operational use in remote sensing applications. Segmentation and classification of image data are important tasks for POLSAR data analysis and interpretation, which often requires human interaction. Existing strategies for automated POLSAR data analysis have utilized the polarimetric attributes of pixels, which involve target decompositions based on physical, mathematical or statistical models. A well-established and widely-used technique is the Wishart classifier, which is used as the benchmark in this work. In this thesis, a new methodology is used that exploits both the polarimetric attributes of pixels, and the visual aspect of the image data through computer vision principles. In this process, the performance level of humans is desired, and several features or cues, inspired by perceptual organization, are utilized, i.e., patch-based similarity of intensity, contour, spatial proximity, and the polarimetric cue. The pair-wise grouping technique of Spectral Graph Partitioning (SGP) is employed to perform the segmentation and classification tasks based on graph cuts. A new classification algorithm is developed for POLSAR data, where segmentation based on the contour and spatial proximity cues is followed by classification based on the polarimetric cue (i.e., similarity of coherency matrices). It offers a way to utilize the complete polarimetric information through the coherency matrix representation in the SGP framework. The proposed unsupervised technique aims to automate the data analysis process for the mapping of distributed targets. Two fully polarimetric data sets in L-, and C-bands acquired by AIRSAR and the Convair-580, both containing agricultural fields, were used to obtain the experimental results and analysis. The results suggest quantitative and qualitative improvements over the Wishart classifier. This method is suitable for applications where homogeneity within each separated region is desirable, such as mapping crops or other types of terrain. The SGP methodology used in the developed scheme is flexible in the definition of affinity functions and will likely allow further improvements through the addition of different image features and data sources.
Item Citations and Data
Attribution-NonCommercial-NoDerivatives 4.0 International