A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification
Remote Sensing · 01.10.2023 · 15 (19) · 4801
DOI: 10.3390/rs15194801 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 01.10.2023. Verfasst von Yihui Ren und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Polarimetric synthetic aperture radar (PolSAR) image classification has been an important area of research due to its wide range of applications. Traditional machine learning methods were insufficient in achieving satisfactory results before the advent of deep learning. Results have significantly improved with the widespread use of deep learning in PolSAR image classification. However, the challenge of reconciling the complex-valued inputs of PolSAR images with the real-valued models of deep learning remains unsolved. Current complex-valued deep learning models treat complex numbers as two distinct real numbers, providing limited assistance in PolSAR image classification results. This paper proposes a novel, complex-valued deep learning approach for PolSAR image classification to address this issue. The approach includes amplitude-based max pooling, complex-valued nonlinear activation, and a cross-entropy loss function based on complex-valued probability. Amplitude-based max pooling reduces computational effort while preserving the most valuable complex-valued features. Complex-valued nonlinear activation maps feature into a high-dimensional complex-domain space, producing the most discriminative features. The complex-valued cross-entropy loss function computes the classification loss using the complex-valued model output and dataset labels, resulting in more accurate and robust classification results. The proposed method was applied to a shallow CNN, deep CNN, FCN, and SegNet, and its effectiveness was verified on three public datasets. The results showed that the method achieved optimal classification results on any model and dataset.
Förderung
- Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Ren, Y., Jiang, W., & Liu, Y. (2023). A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification. Remote Sensing, 15(19), 4801. https://doi.org/10.3390/rs15194801
Vancouver
Ren Y, Jiang W, Liu Y. A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification. Remote Sensing. 2023;15(19):4801. doi:10.3390/rs15194801
BibTeX
@article{Ren2023,
author = {Ren, Yihui and Jiang, Wen and Liu, Ying},
title = {A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {19},
pages = {4801},
doi = {10.3390/rs15194801}
}
EUVIMED