Semi-Supervised Sea Ice Classification of SAR Imagery Based on Graph Convolutional Network
Authors:
- 17 July 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1031-1034
Abstract
Monitoring sea ice in polar regions is essential for environmental modeling and ship navigation. National ice agencies expect robust sea ice classification methods for operational use. However, fully supervised machine learning models require large training datasets, which are usually limited to the sea ice classification domain. Therefore, a semi-supervised sea ice classification model is proposed to address this challenge. First, the IRGS segmentation is applied to generate superpixels that construct the graph. Then, two graph convolutional layers are utilized to learn the features of each node. Finally, a softmax layer assigns labels to the nodes in the graph. The proposed model is named IRGS-GCN and tested on four RADARSAR-2 dual-polarized scenes. The experimental results show that the IRGS-GCN achieves an overall accuracy of 95.17% and outperforms fully-supervised random foreset and ResNet trained on limited data. Most of the sea ice boundary and leads are successfully preserved in the results.Keywords
This publication has 10 references indexed in Scilit:
- Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- Prediction of Categorized Sea Ice Concentration From Sentinel-1 SAR Images Based on a Fully Convolutional NetworkIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- Automatic Sea-Ice Classification of SAR Images Based on Spatial and Temporal Features LearningIEEE Transactions on Geoscience and Remote Sensing, 2021
- Extraction of Sea Ice Cover by Sentinel-1 SAR Based on Support Vector Machine With Unsupervised Generation of Training DataIEEE Transactions on Geoscience and Remote Sensing, 2020
- Dual Attention Network for Scene Segmentation2019
- Deep Residual Learning for Image Recognition2016
- Towards sea ice classification using simulated RADARSAT Constellation Mission compact polarimetric SAR imageryRemote Sensing of Environment, 2014
- Automated Ice–Water Classification Using Dual Polarization SAR Satellite ImageryIEEE Transactions on Geoscience and Remote Sensing, 2013
- IRGS: Image Segmentation Using Edge Penalties and Region GrowingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- SAR Sea-Ice Image Analysis Based on Iterative Region Growing Using SemanticsIEEE Transactions on Geoscience and Remote Sensing, 2007