Low-level processing of PolSAR images with binary partition trees
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessRestricted access - publisher's policy
This paper discusses the interest of Binary Partition Trees (BPTs) and the usefulness of graph cuts for low-level processing of PolSAR images. BPTs group pixels to form homogeneous regions, which are hierarchically structured by inclusion in a tree. They provide multiple resolutions of description and easy access to subsets of regions. Once constructed, BPTs can be used for many applications including filtering, segmentation, classification and object detection. Many processing strategies consist in populating the tree with a specific feature and in applying a graph-cut called pruning. Different graph-cuts are discussed and analyzed in the context of PolSAR images for speckle filtering and segmentation.
CitationSalembier, P.; Foucher, S.; Lopez, C. Low-level processing of PolSAR images with binary partition trees. A: IEEE International Geoscience and Remote Sensing Symposium. "2014 IEEE International Geoscience & Remote Sensing Symposium: proceedings: July 13–18, 2014, Québec City, Québec, Canada". Québec: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 1025-1028.