A Bilateral Filter of Polarimetric SAR Images Based on Semantic Co-occurrence Matrix

Conference: EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar
06/04/2018 - 06/07/2018 at Aachen, Germany

Proceedings: EUSAR 2018

Pages: 6Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Pan, Ting; Yang, Wen (School of Electronic Information, Wuhan University, Wuhan 430072, China & The CETC Key Laboratory of Aerospace Information Applications, Shijiazhuang 050081, China)
Yang, Xiangli (School of Electronic Information, Wuhan University, Wuhan 430072, China)
Huang, Pingping (College of Information Engineering, Inner Mongolia University of Technology, 101051 Hohhot, China)

Abstract:
For polarimetric SAR (PolSAR) images, speckle noise filtering remains a challenging task due to the difficulty to reduce a scatterer-dependent noise while preserving the polarimetric and the spatial information. This paper introduces a modified bilateral filter, Bilateral Semantic Co-Occurrence Filter (BSCF), to preserve the edges and details of data effectively. The weight of the BSCF is defined in terms of spatial distance and polarimetric distance described by the semantic co-occurrence matrix which takes the scattering mechanism and the semantic similarity into account. Experiments show that BSCF performs well in preserve spatial and polarimetric information while dealing with edges and details effectively.