AMD-HookNet for Glacier Front Segmentation

TL;DR

This paper introduces AMD-HookNet, a novel deep learning framework that improves glacier calving front segmentation in SAR images by using attention mechanisms and multi-scale feature interactions, achieving state-of-the-art accuracy.

Contribution

The paper presents AMD-HookNet, a new segmentation framework that enhances feature representation and accuracy for glacier front delineation in SAR imagery, outperforming existing methods.

Findings

Achieves a mean distance error of 438 m, outperforming previous methods by 42%.

Utilizes attention mechanisms for better feature interaction between different resolution inputs.

Demonstrates effectiveness on the challenging CaFFe glacier segmentation benchmark dataset.

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 paper, we propose Attention-Multi-hooking-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 of 438 m to the ground truth outperforming the current state of the art by 42%, which validates its effectiveness.