Ice floe segmentation and floe size distribution in airborne and high-resolution optical satellite images: towards an automated labelling deep learning approach

• Published in: The Cryosphere
• Main Authors: Zhang, Qin, Hughes, Nick
• Format: Article in Journal/Newspaper
• Language: English
• Published: Copernicus Publications 2023
• Subjects: article; Verlagsveröffentlichung; Sea ice; The Cryosphere
• Online Access: https://doi.org/10.5194/tc-17-5519-2023; https://noa.gwlb.de/receive/cop_mods_00070760; https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00069092/tc-17-5519-2023.pdf; https://tc.copernicus.org/articles/17/5519/2023/tc-17-5519-2023.pdf

Floe size distribution (FSD) has become a parameter of great interest in observations of sea ice because of its importance in affecting climate change, marine ecosystems, and human activities in the polar ocean. A most effective way to monitor FSD in the ice-covered regions is to apply image processing techniques to airborne and satellite remote sensing data, where the segmentation of individual ice floes is a challenge in obtaining FSD from remotely sensed images. In this study, we adopt a deep learning (DL) semantic segmentation network to fast and adaptive implement the task of ice floe instance segmentation. In order to alleviate the costly and time-consuming data annotation problem of model training, classical image processing technique is applied to automatically label ice floes in local-scale marginal ice zone (MIZ). Several state-of-the-art (SoA) semantic segmentation models are then trained on the labelled MIZ dataset and further applied to additional large-scale optical Sentinel-2 images to evaluate their performance in floe instance segmentation and to determine the best model. A post-processing algorithm is also proposed in our work to refine the segmentation. Our approach has been applied to both airborne and high-resolution optical (HRO) satellite images to derive acceptable FSDs at local and global scales.