Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks

TL;DR

This paper introduces a hybrid convolutional transformer network for sea ice segmentation from SAR satellite images, achieving higher accuracy and efficiency than traditional methods, aiding climate monitoring.

Contribution

A novel hybrid ConvTr network that improves sea ice segmentation accuracy and efficiency over classical and pure transformer models.

Findings

ConvTr achieved a mean IoU of 63.68%.

Inference time was 120ms for a 400x400 km area.

Outperformed classical convolutional networks.

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 x 400 squared km product.