Complex Scene Classification of PolSAR Imagery based on a Self-paced Learning Approach

TL;DR

This paper introduces a novel self-paced learning based SVM classifier with neighborhood constraints for improved complex scene classification in PolSAR imagery, demonstrating superior performance on real datasets.

Contribution

A new SPL-based SVM algorithm with neighborhood constraints tailored for complex PolSAR scene classification is proposed, enhancing accuracy and robustness.

Findings

Effective in handling complex scenes with noise and similar scattering properties

Outperforms existing methods on three real PolSAR datasets

Gradually incorporates samples to improve classifier robustness

Abstract

Existing polarimetric synthetic aperture radar (PolSAR) image classification methods cannot achieve satisfactory performance on complex scenes characterized by several types of land cover with significant levels of noise or similar scattering properties across land cover types. Hence, we propose a supervised classification method aimed at constructing a classifier based on self-paced learning (SPL). SPL has been demonstrated to be effective at dealing with complex data while providing classifier. In this paper, a novel Support Vector Machine (SVM) algorithm based on SPL with neighborhood constraints (SVM_SPLNC) is proposed. The proposed method leverages the easiest samples first to obtain an initial parameter vector. Then, more complex samples are gradually incorporated to update the parameter vector iteratively. Moreover, neighborhood constraints are introduced during the training process to further improve performance. Experimental results on three real PolSAR images show that the proposed method performs well on complex scenes.