Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unsupervised Classification of PolSAR Data Using a Scattering Similarity Measure Derived from a Geodesic Distance

Debanshu Ratha, Avik Bhattacharya, Alejandro C. Frery

TL;DR

This work tackles unsupervised PolSAR image classification while preserving physical scattering characteristics by introducing a geodesic-distance based similarity measure between Kennaugh matrices. The method computes per-target scattering components $w_a$, $w_b$, $w_{rv}$ using a normalized similarity $\gamma_i$ modulated by Span, and then applies an ML-Wishart classifier within each canonical category to produce labeled maps. Compared with Freeman-Durden-based approaches, the GD-Wishart scheme yields improved delineation of urban areas and ocean/vegetation boundaries, and it ensures nonnegative scattering components. The approach is extensible to more canonical targets and possibly to bistatic configurations, offering a robust alternative to traditional decompositions for PolSAR analysis.

Abstract

In this letter, we propose a novel technique for obtaining scattering components from Polarimetric Synthetic Aperture Radar (PolSAR) data using the geodesic distance on the unit sphere. This geodesic distance is obtained between an elementary target and the observed Kennaugh matrix, and it is further utilized to compute a similarity measure between scattering mechanisms. The normalized similarity measure for each elementary target is then modulated with the total scattering power (Span). This measure is used to categorize pixels into three categories i.e. odd-bounce, double-bounce and volume, depending on which of the above scattering mechanisms dominate. Then the maximum likelihood classifier of [J.-S. Lee, M. R. Grunes, E. Pottier, and L. Ferro-Famil, Unsupervised terrain classification preserving polarimetric scattering characteristics, IEEE Trans. Geos. Rem. Sens., vol. 42, no. 4, pp. 722731, April 2004.] based on the complex Wishart distribution is iteratively used for each category. Dominant scattering mechanisms are thus preserved in this classification scheme. We show results for L-band AIRSAR and ALOS-2 datasets acquired over San Francisco and Mumbai, respectively. The scattering mechanisms are better preserved using the proposed methodology than the unsupervised classification results using the Freeman-Durden scattering powers on an orientation angle (OA) corrected PolSAR image. Furthermore, (1) the scattering similarity is a completely non-negative quantity unlike the negative powers that might occur in double- bounce and odd-bounce scattering component under Freeman Durden decomposition (FDD), and (2) the methodology can be extended to more canonical targets as well as for bistatic scattering.

Unsupervised Classification of PolSAR Data Using a Scattering Similarity Measure Derived from a Geodesic Distance

TL;DR

This work tackles unsupervised PolSAR image classification while preserving physical scattering characteristics by introducing a geodesic-distance based similarity measure between Kennaugh matrices. The method computes per-target scattering components , , using a normalized similarity modulated by Span, and then applies an ML-Wishart classifier within each canonical category to produce labeled maps. Compared with Freeman-Durden-based approaches, the GD-Wishart scheme yields improved delineation of urban areas and ocean/vegetation boundaries, and it ensures nonnegative scattering components. The approach is extensible to more canonical targets and possibly to bistatic configurations, offering a robust alternative to traditional decompositions for PolSAR analysis.

Abstract

In this letter, we propose a novel technique for obtaining scattering components from Polarimetric Synthetic Aperture Radar (PolSAR) data using the geodesic distance on the unit sphere. This geodesic distance is obtained between an elementary target and the observed Kennaugh matrix, and it is further utilized to compute a similarity measure between scattering mechanisms. The normalized similarity measure for each elementary target is then modulated with the total scattering power (Span). This measure is used to categorize pixels into three categories i.e. odd-bounce, double-bounce and volume, depending on which of the above scattering mechanisms dominate. Then the maximum likelihood classifier of [J.-S. Lee, M. R. Grunes, E. Pottier, and L. Ferro-Famil, Unsupervised terrain classification preserving polarimetric scattering characteristics, IEEE Trans. Geos. Rem. Sens., vol. 42, no. 4, pp. 722731, April 2004.] based on the complex Wishart distribution is iteratively used for each category. Dominant scattering mechanisms are thus preserved in this classification scheme. We show results for L-band AIRSAR and ALOS-2 datasets acquired over San Francisco and Mumbai, respectively. The scattering mechanisms are better preserved using the proposed methodology than the unsupervised classification results using the Freeman-Durden scattering powers on an orientation angle (OA) corrected PolSAR image. Furthermore, (1) the scattering similarity is a completely non-negative quantity unlike the negative powers that might occur in double- bounce and odd-bounce scattering component under Freeman Durden decomposition (FDD), and (2) the methodology can be extended to more canonical targets as well as for bistatic scattering.

Paper Structure

This paper contains 8 sections, 12 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Methodology
  3. Geodesic Distance
  4. Normalized Scattering Similarity Measure
  5. Unsupervised Classification
  6. Mixed Category
  7. Results and discussion
  8. Conclusion

Figures (4)

  • Figure 1: The Pauli RGB image and the similarity measures $f_{i}$ for the San-Francisco, USA AIRSAR L-band PolSAR data.
  • Figure 2: Classification results using FDD and GD and their comparison for San-Francisco, USA AIRSAR L-band PolSAR data.
  • Figure 3: The Pauli RGB image and the similarity measures $f_{i}$ for the Mumbai, India ALOS-2 L-band PolSAR data.
  • Figure 4: Classification results using FDD and GD and their comparison for Mumbai, India ALOS-2 L-band PolSAR data.