Multi-source remote sensing data cross scene classification based on multi-graph matching
- Author
- Mengmeng Zhang, Xudong Zhao, Wei Li and Yuxiang Zhang
- Organization
- Abstract
- Multi-source joint classification has been extensively investigated in single scenario setting; however, for cross scene (CS) classification, few studies have been conducted for evaluating the collaborative performance of multi-sources. In this paper, using hyperspectral image (HSI) and light detection and ranging (LiDAR) data, we propose a multi-source CS classification method, and build source-related alignment to reduce statistical shift. Both geometrical and statistical alignments are considered to learn common-subspaces of each source with preserving discrimination information. Finally, the aligned features from both sources are integrated for final classification. Experimental results demonstrate the superior of the proposed method over other state-of-the-art CS approaches.
- Keywords
- Deep learning, joint classification, cross scene, distribution alignment
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 3.58 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HVRFC5DAEQA11RTW0PHG83Z6
- MLA
- Zhang, Mengmeng, et al. “Multi-Source Remote Sensing Data Cross Scene Classification Based on Multi-Graph Matching.” 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), IEEE, 2022, pp. 827–30, doi:10.1109/IGARSS46834.2022.9884311.
- APA
- Zhang, M., Zhao, X., Li, W., & Zhang, Y. (2022). Multi-source remote sensing data cross scene classification based on multi-graph matching. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 827–830. https://doi.org/10.1109/IGARSS46834.2022.9884311
- Chicago author-date
- Zhang, Mengmeng, Xudong Zhao, Wei Li, and Yuxiang Zhang. 2022. “Multi-Source Remote Sensing Data Cross Scene Classification Based on Multi-Graph Matching.” In 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 827–30. IEEE. https://doi.org/10.1109/IGARSS46834.2022.9884311.
- Chicago author-date (all authors)
- Zhang, Mengmeng, Xudong Zhao, Wei Li, and Yuxiang Zhang. 2022. “Multi-Source Remote Sensing Data Cross Scene Classification Based on Multi-Graph Matching.” In 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 827–830. IEEE. doi:10.1109/IGARSS46834.2022.9884311.
- Vancouver
- 1.Zhang M, Zhao X, Li W, Zhang Y. Multi-source remote sensing data cross scene classification based on multi-graph matching. In: 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022). IEEE; 2022. p. 827–30.
- IEEE
- [1]M. Zhang, X. Zhao, W. Li, and Y. Zhang, “Multi-source remote sensing data cross scene classification based on multi-graph matching,” in 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), Kuala Lumpur, MALAYSIA, 2022, pp. 827–830.
@inproceedings{01HVRFC5DAEQA11RTW0PHG83Z6,
abstract = {{Multi-source joint classification has been extensively investigated in single scenario setting; however, for cross scene (CS) classification, few studies have been conducted for evaluating the collaborative performance of multi-sources. In this paper, using hyperspectral image (HSI) and light detection and ranging (LiDAR) data, we propose a multi-source CS classification method, and build source-related alignment to reduce statistical shift. Both geometrical and statistical alignments are considered to learn common-subspaces of each source with preserving discrimination information. Finally, the aligned features from both sources are integrated for final classification. Experimental results demonstrate the superior of the proposed method over other state-of-the-art CS approaches.}},
author = {{Zhang, Mengmeng and Zhao, Xudong and Li, Wei and Zhang, Yuxiang}},
booktitle = {{2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022)}},
isbn = {{9781665427920}},
issn = {{2153-6996}},
keywords = {{Deep learning,joint classification,cross scene,distribution alignment}},
language = {{eng}},
location = {{Kuala Lumpur, MALAYSIA}},
pages = {{827--830}},
publisher = {{IEEE}},
title = {{Multi-source remote sensing data cross scene classification based on multi-graph matching}},
url = {{http://doi.org/10.1109/IGARSS46834.2022.9884311}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: