Complex-valued reservoir computing for aspect classification and slope-angle estimation with low computational cost and high resolution in interferometric synthetic aperture radar

TL;DR

This paper introduces complex-valued reservoir computing (CVRC) for interferometric SAR image classification and slope-angle estimation, achieving higher resolution and significantly lower computational costs compared to traditional CNNs.

Contribution

The paper presents a novel CVRC approach tailored for complex-valued InSAR data, reducing learning and classification time while maintaining high accuracy.

Findings

CVRC achieves one-hundredth of CNN's learning time

CVRC reduces classification time to one-fifth of CNN's

CVRC effectively handles both classification and continuous estimation tasks

Abstract

Synthetic aperture radar (SAR) is widely used for ground surface classification since it utilizes information on vegetation and soil unavailable in optical observation. Image classification often employs convolutional neural networks. However, they have serious problems such as long learning time and resolution degradation in their convolution and pooling processes. In this paper, we propose complex-valued reservoir computing (CVRC) to deal with complex-valued images in interferometric SAR (InSAR). We classify InSAR image data by using CVRC successfully with a higher resolution and a lower computational cost, i.e., one-hundredth learning time and one-fifth classification time, than convolutional neural networks. We also conduct experiments on slope angle estimation. CVRC is found applicable to quantitative tasks dealing with continuous values as well as discrete classification tasks with a higher accuracy.