What is it about?

This classification algorithm can classify the dataset collected by hybrid-polarimetric SAR unsupervised into categories with certain physical scattering mechanisms. The colors of the classification are rendered with certain meanings, which is red, blue, and green for double-bounce scattering (mostly in urban areas), surface scattering, and volume scattering (mostly in forests), and brighter color for stronger backscattering.

Featured Image

Why is it important?

Previous similar classification algorithms can hardly guarantee both texture features and accuracy of the classification. The proposed algorithm can reach this goal through applying the Wishart classifier with non-filtered dataset and some refining progresses.

Perspectives

Unsupervised classification of hybrid-polarity dataset has reached its bottleneck if the degree of polarization (m) is used for decomposition, for m will inevitably lead to the overestimation of volume scattering. One possible solution to increase the accuracy of classfication is to use statistical property of the hybrid-polarimetry jointly for unsupervised classification.

Mr Shiqiang Chen
Institute of Electronics, Chinese Academy of Sciences

Read the Original

This page is a summary of: Unsupervised classification for hybrid polarimetric SAR data based on scattering mechanisms and Wishart classifier, Electronics Letters, September 2015, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/el.2015.1627.
You can read the full text:

Read

Contributors

The following have contributed to this page