Multisource remote sensing data classification using deep hierarchical random walk networks
- Author
- Xudong Zhao, Ran Tao and Wei Li
- Organization
- Abstract
- Collaborative classification of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data is investigated using effective hierarchical random walk networks, denoted as HRWN. The proposed HRWN jointly optimizes dual tunnel CNN, pixelwise affinity and seeds map via a novel random walk layer, which enforces spatial consistency in the deepest layers of the network. In designed random walk layer, the predicted distribution of dual-tunnel CNN serves as global prior while pixelwise affinity reflects local similarity of pixel pairs, which preserves boundary localization and spatial consistency well. Experimental results validated with two real multisource remote sensing data demonstrate that the proposed HRWN can significantly outperform other state-of-art methods.
- Keywords
- Hierarchical random walk, convolutional neural network (CNN), hyperspectral image (HSI), multi-source remote sensing classification
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.35 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8714089
- MLA
- Zhao, Xudong, et al. “Multisource Remote Sensing Data Classification Using Deep Hierarchical Random Walk Networks.” 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 2019, pp. 2187–91, doi:10.1109/ICASSP.2019.8683032.
- APA
- Zhao, X., Tao, R., & Li, W. (2019). Multisource remote sensing data classification using deep hierarchical random walk networks. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2187–2191. https://doi.org/10.1109/ICASSP.2019.8683032
- Chicago author-date
- Zhao, Xudong, Ran Tao, and Wei Li. 2019. “Multisource Remote Sensing Data Classification Using Deep Hierarchical Random Walk Networks.” In 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2187–91. IEEE. https://doi.org/10.1109/ICASSP.2019.8683032.
- Chicago author-date (all authors)
- Zhao, Xudong, Ran Tao, and Wei Li. 2019. “Multisource Remote Sensing Data Classification Using Deep Hierarchical Random Walk Networks.” In 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2187–2191. IEEE. doi:10.1109/ICASSP.2019.8683032.
- Vancouver
- 1.Zhao X, Tao R, Li W. Multisource remote sensing data classification using deep hierarchical random walk networks. In: 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). IEEE; 2019. p. 2187–91.
- IEEE
- [1]X. Zhao, R. Tao, and W. Li, “Multisource remote sensing data classification using deep hierarchical random walk networks,” in 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), Brighton, ENGLAND, 2019, pp. 2187–2191.
@inproceedings{8714089,
abstract = {{Collaborative classification of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data is investigated using effective hierarchical random walk networks, denoted as HRWN. The proposed HRWN jointly optimizes dual tunnel CNN, pixelwise affinity and seeds map via a novel random walk layer, which enforces spatial consistency in the deepest layers of the network. In designed random walk layer, the predicted distribution of dual-tunnel CNN serves as global prior while pixelwise affinity reflects local similarity of pixel pairs, which preserves boundary localization and spatial consistency well. Experimental results validated with two real multisource remote sensing data demonstrate that the proposed HRWN can significantly outperform other state-of-art methods.}},
author = {{Zhao, Xudong and Tao, Ran and Li, Wei}},
booktitle = {{2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)}},
isbn = {{9781479981311}},
issn = {{1520-6149}},
keywords = {{Hierarchical random walk,convolutional neural network (CNN),hyperspectral image (HSI),multi-source remote sensing classification}},
language = {{eng}},
location = {{Brighton, ENGLAND}},
pages = {{2187--2191}},
publisher = {{IEEE}},
title = {{Multisource remote sensing data classification using deep hierarchical random walk networks}},
url = {{http://doi.org/10.1109/ICASSP.2019.8683032}},
year = {{2019}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: