Discovery of Semantic Relationships in PolSAR Images Using Latent Dirichlet Allocation

Radu Tanase, Reza Bahmanyar, Gottfried Schwarz, Mihai Datcu
2017 IEEE Geoscience and Remote Sensing Letters  
We propose a multi-level semantics discovery approach for bridging the semantic gap when mining highresolution Polarimetric Synthetic Aperture Radar (PolSAR) remote sensing images. First, an Entropy/Anisotropy/Alpha-Wishart classifier is employed to discover low-level semantics as classes representing the physical scattering properties of targets (e.g., low-entropy/surface-scattering/high-anisotropy). Then, the images are tiled into patches and each patch is modeled as a Bag-of-Words (BoW), a
more » ... stogram of the class labels. Next, Latent Dirichlet Allocation is applied to discover their higher-level semantics as a set of topics. Our results demonstrate that topic semantics are close to human semantics used for basic land-cover types (e.g., grassland). Therefore, using the topic description (Bag-of-Topics) of PolSAR images leads to a narrower semantic gap in image mining. Additionally, a visual exploration of the topic descriptions helps to find semantic relationships which can be used for defining new semantic categories (e.g., mixed landcover types) and designing rule-based categorization schemes.
doi:10.1109/lgrs.2016.2636663 fatcat:tjwmyyfrobaibb5sj7p65ma6mu