Sea Ice Segmentation from SAR Data by Convolutional Transformer Networks
Authors:
- 16 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 168-171
Abstract
Sea ice is a crucial component of the Earth’s climate system and is highly sensitive to changes in temperature and atmospheric conditions. Accurate and timely measurement of sea ice parameters is important for understanding and predicting the impacts of climate change. Nevertheless, the amount of satellite data acquired over ice areas is huge, making the subjective measurements ineffective. Therefore, automated algorithms must be used in order to fully exploit the continuous data feeds coming from satellites. In this paper, we present a novel approach for sea ice segmentation based on SAR satellite imagery using hybrid convolutional transformer (ConvTr) networks. We show that our approach outperforms classical convolutional networks, while being considerably more efficient than pure transformer models. ConvTr obtained a mean intersection over union (mIoU) of 63.68% on the AI4Arctic data set, assuming an inference time of 120ms for a 400×400 km 2 product.Keywords
All Related Versions
Funding Information
- Ministry of Education
This publication has 13 references indexed in Scilit:
- SatViT: Pretraining Transformers for Earth ObservationIEEE Geoscience and Remote Sensing Letters, 2022
- Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet MethodRemote Sensing, 2022
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- CvT: Introducing Convolutions to Vision Transformers2021
- Self-Supervised Pretraining of Transformers for Satellite Image Time Series ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020
- Sea Ice and Open Water Classification of SAR Images Using a Deep Learning Model2020
- Deep Learning for SAR Image DespecklingRemote Sensing, 2019
- Transferred Deep Learning for Sea Ice Change Detection From Synthetic-Aperture Radar ImagesIEEE Geoscience and Remote Sensing Letters, 2019
- Focal Loss for Dense Object Detection2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015