AMD-HookNet for Glacier Front Segmentation

Wu F, Gourmelon N, Seehaus T, Zhang J, Braun M, Maier A, Christlein V (2023)

Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2023

Journal

Book Volume: 61

Pages Range: 1-12

URI: https://ieeexplore.ieee.org/document/10044700

DOI: 10.1109/TGRS.2023.3245419

Abstract

Knowledge on changes in glacier calving front positions is important for assessing the status of glaciers. Remote sensing imagery provides the ideal database for monitoring calving front positions; however, it is not feasible to perform this task manually for all calving glaciers globally due to time constraints. Deep-learning-based methods have shown great potential for glacier calving front delineation from optical and radar satellite imagery. The calving front is represented as a single thin line between the ocean and the glacier, which makes the task vulnerable to inaccurate predictions. The limited availability of annotated glacier imagery leads to a lack of data diversity (not all possible combinations of different weather conditions, terminus shapes, sensors, etc. are present in the data), which exacerbates the difficulty of accurate segmentation. In this article, we propose attention-multihooking-deep-supervision HookNet (AMD-HookNet), a novel glacier calving front segmentation framework for synthetic aperture radar (SAR) images. The proposed method aims to enhance the feature representation capability through multiple information interactions between low-resolution and high-resolution inputs based on a two-branch U-Net. The attention mechanism, integrated into the two branch U-Net, aims to interact between the corresponding coarse and fine-grained feature maps. This allows the network to automatically adjust feature relationships, resulting in accurate pixel classification predictions. Extensive experiments and comparisons on the challenging glacier segmentation benchmark dataset CaFFe show that our AMD-HookNet achieves a mean distance error (MDE) of 438 m to the ground truth outperforming the current state of the art by 42%, which validates its effectiveness.

Authors with CRIS profile

Related research project(s)

Involved external institutions

University of Chinese Academy of Sciences (UCAS) / 中国科学院大学 China (CN)

How to cite

APA:

Wu, F., Gourmelon, N., Seehaus, T., Zhang, J., Braun, M., Maier, A., & Christlein, V. (2023). AMD-HookNet for Glacier Front Segmentation. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-12. https://doi.org/10.1109/TGRS.2023.3245419

MLA:

Wu, Fei, et al. "AMD-HookNet for Glacier Front Segmentation." IEEE Transactions on Geoscience and Remote Sensing 61 (2023): 1-12.

BibTeX: Download