Very high resolution Airborne PolSAR Image Classification using Convolutional Neural Networks

TL;DR

This paper demonstrates that using CNNs with polarimetric and structural tensor features significantly improves the classification accuracy of very high resolution airborne PolSAR images.

Contribution

It introduces a CNN-based approach combining polarimetric and structural tensor features for improved VHR PolSAR image classification.

Findings

SegNet achieves high accuracy in pixelwise classification of VHR PolSAR data.

Combining structural tensors with polarimetric features enhances classification performance.

Structural information helps CNNs focus on geometrical details for better results.

Abstract

In this work, we exploit convolutional neural networks (CNNs) for the classification of very high resolution (VHR) polarimetric SAR (PolSAR) data. Due to the significant appearance of heterogeneous textures within these data, not only polarimetric features but also structural tensors are exploited to feed CNN models. For deep networks, we use the SegNet model for semantic segmentation, which corresponds to pixelwise classification in remote sensing. Our experiments on the airborne F-SAR data show that for VHR PolSAR images, SegNet could provide high accuracy for the classification task; and introducing structural tensors together with polarimetric features as inputs could help the network to focus more on geometrical information to significantly improve the classification performance.