HyFormer: Hybrid Transformer and CNN for Pixel-Level Multispectral Image Land Cover Classification
International Journal of Environmental Research and Public Health · 2023
DOI: 10.3390/ijerph20043059 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Environmental Research and Public Health, 2023. Verfasst von Chuan Yan und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China. Hauptthemen laut MEDLINE: Electric Power Supplies, Neural Networks, Computer. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
To effectively solve the problems that most convolutional neural networks cannot be applied to the pixelwise input in remote sensing (RS) classification and cannot adequately represent the spectral sequence information, we propose a new multispectral RS image classification framework called HyFormer based on Transformer. First, a network framework combining a fully connected layer (FC) and convolutional neural network (CNN) is designed, and the 1D pixelwise spectral sequences obtained from the fully connected layers are reshaped into a 3D spectral feature matrix for the input of CNN, which enhances the dimensionality of the features through FC as well as increasing the feature expressiveness, and can solve the problem that 2D CNN cannot achieve pixel-level classification. Secondly, the features of the three levels of CNN are extracted and combined with the linearly transformed spectral information to enhance the information expression capability, and also used as the input of the transformer encoder to improve the features of CNN using the powerful global modelling capability of the Transformer, and finally the skip connection of the adjacent encoders to enhance the fusion between different levels of information. The pixel classification results are obtained by MLP Head. In this paper, we mainly focus on the feature distribution in the eastern part of Changxing County and the central part of Nanxun District, Zhejiang Province, and conduct experiments based on Sentinel-2 multispectral RS images. The experimental results show that the overall accuracy of HyFormer for the study area classification in Changxing County is 95.37% and that of Transformer (ViT) is 94.15%. The experimental results show that the overall accuracy of HyFormer for the study area classification in Nanxun District is 95.4% and that of Transformer (ViT) is 94.69%, and the performance of HyFormer on the Sentinel-2 dataset is better than that of the Transformer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China.
- Guangxi Collaborative Innovation Centre for Earthmoving Machinery, Guangxi University of Science and Technology, Liuzhou 545006, China.
- National Satellite Meteorological Center, China Meteorological Administration, Beijing 100081, China.
ORCID-Profile: Chuan Yan, Xiangsuo Fan
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yan, C., Fan, X., Fan, J., Yu, L., Wang, N., Chen, L., & Li, X. (2023). HyFormer: Hybrid Transformer and CNN for Pixel-Level Multispectral Image Land Cover Classification. International Journal of Environmental Research and Public Health. https://doi.org/10.3390/ijerph20043059
Vancouver
Yan C, Fan X, Fan J, Yu L, Wang N, Chen L, et al. HyFormer: Hybrid Transformer and CNN for Pixel-Level Multispectral Image Land Cover Classification. International Journal of Environmental Research and Public Health. 2023. doi:10.3390/ijerph20043059
BibTeX
@article{Yan2023,
author = {Yan, Chuan and Fan, Xiangsuo and Fan, Jinlong and Yu, Ling and Wang, Nayi and Chen, Lin and Li, Xuyang},
title = {HyFormer: Hybrid Transformer and CNN for Pixel-Level Multispectral Image Land Cover Classification},
journal = {International Journal of Environmental Research and Public Health},
year = {2023},
doi = {10.3390/ijerph20043059}
}
EUVIMED