Remote sensing image processing with graph cut of binary partition trees
Document typeConference report
PublisherInstituto Politécnico Nacional
Rights accessRestricted access - publisher's policy
This paper discusses the interest of hierarchical region-based representations of images such as Binary Partition Trees (BPTs) and the usefulness of graph cut to process them. BPTs can be considered as an initial abstraction from the signal in which raw pixels are grouped by similarity to form regions, which are hierarchically structured by inclusion in a tree. They provide multiple resolutions of description and easy access to subsets of regions. Their construction is often based on an iterative region-merging algorithm. 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 features of interest for the application and in applying a specific graph cut called pruning. Different graph cut approaches are discussed and analyzed in the context of Polarimetric Synthetic Aperture Radar (PolSAR) images.
CitationSalembier, P., Foucher, S. Remote sensing image processing with graph cut of binary partition trees. A: International Research and Academic Congress. "Research in Computing Science: Advances in Computing Science, Control and Communications: vol. 69, 2014". Tijuana: Instituto Politécnico Nacional, 2014, p. 185-196.