Integrated 1D, 2D, and 3D CNNs Enable Robust and Efficient Land Cover Classification from Hyperspectral Imagery
Remote Sensing · 01.10.2023 · 15 (19) · 4797
DOI: 10.3390/rs15194797 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 01.10.2023. Verfasst von Jinxiang Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, Construction Program of Space-Air-Ground-Well Cooperative Awareness Spatial Information Project, 2022 Jiangsu Provincial Science and Technology Initiative-Special Fund for International Science and Technology Cooperation.
Abstract (Originalsprache)
Convolutional neural networks (CNNs) have recently been demonstrated to be able to substantially improve the land cover classification accuracy of hyperspectral images. Meanwhile, the rapidly developing capacity for satellite and airborne image spectroscopy as well as the enormous archives of spectral data have imposed increasing demands on the computational efficiency of CNNs. Here, we propose a novel CNN framework that integrates one-dimensional (1D), two-dimensional (2D), and three-dimensional (3D) CNNs to obtain highly accurate and fast land cover classification from airborne hyperspectral images. To achieve this, we first used 3D CNNs to derive both spatial and spectral features from hyperspectral images. Then, we successively utilized a 2D CNN and a 1D CNN to efficiently acquire higher-level representations of spatial or spectral features. Finally, we leveraged the information obtained from the aforementioned steps for land cover classification. We assessed the performance of the proposed method using two openly available datasets (the Indian Pines dataset and the Wuhan University dataset). Our results showed that the overall classification accuracy of the proposed method in the Indian Pines and Wuhan University datasets was 99.65% and 99.85%, respectively. Compared to the state-of-the-art 3D CNN model and HybridSN model, the training times for our model in the two datasets were reduced by an average of 60% and 40%, respectively, while maintaining comparable classification accuracy. Our study demonstrates that the integration of 1D, 2D, and 3D CNNs effectively improves the computational efficiency of land cover classification with hyperspectral images while maintaining high accuracy. Our innovation offers significant advantages in terms of efficiency and robustness for the processing of large-scale hyperspectral images.
Förderung
- Natural Science Foundation of China
- Construction Program of Space-Air-Ground-Well Cooperative Awareness Spatial Information Project
- 2022 Jiangsu Provincial Science and Technology Initiative-Special Fund for International Science and Technology Cooperation
- Wuhan University Specific Fund for Major School-level Internationalization Initiatives
- China Scholarship Council
Zitieren
APA
Liu, J., Wang, T., Skidmore, A., Sun, Y., Jia, P., & Zhang, K. (2023). Integrated 1D, 2D, and 3D CNNs Enable Robust and Efficient Land Cover Classification from Hyperspectral Imagery. Remote Sensing, 15(19), 4797. https://doi.org/10.3390/rs15194797
Vancouver
Liu J, Wang T, Skidmore A, Sun Y, Jia P, Zhang K. Integrated 1D, 2D, and 3D CNNs Enable Robust and Efficient Land Cover Classification from Hyperspectral Imagery. Remote Sensing. 2023;15(19):4797. doi:10.3390/rs15194797
BibTeX
@article{Liu2023,
author = {Liu, Jinxiang and Wang, Tiejun and Skidmore, Andrew and Sun, Yaqin and Jia, Peng and Zhang, Kefei},
title = {Integrated 1D, 2D, and 3D CNNs Enable Robust and Efficient Land Cover Classification from Hyperspectral Imagery},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {19},
pages = {4797},
doi = {10.3390/rs15194797}
}
EUVIMED