用于冰川锋分割的AMD-HookNet
AMD-HookNet for Glacier Front Segmentation
摘要：
了解冰川崩解前沿位置的变化对评估冰川状况很重要。遥感图像提供了理想的数据库，监测崩解前的位置，但是，它是不可行的，手动执行这项任务，全球所有的崩解冰川由于时间的限制。基于深度学习的方法已经显示出从光学和雷达卫星图像中描绘冰川崩解锋的巨大潜力。冰解前缘被表示为海洋和冰川之间的一条细线，这使得这项任务容易受到不准确预测的影响。由于有注释的冰川图像有限，导致数据缺乏多样性（数据中并非存在不同天气条件、终点形状、传感器等的所有可能组合），这加剧了准确分割的难度。在本文中，我们提出了注意多挂钩深度监督钩网（AMD-HookNet），一种新的冰川崩解锋的合成孔径雷达（SAR）图像分割框架。该方法的目的是通过低分辨率和高分辨率输入之间的多个信息的相互作用的基础上的两个分支的U-网，以提高特征表示能力。注意力机制被集成到两个分支U-Net中，旨在在相应的粗粒度和细粒度特征图之间进行交互。这允许网络自动调整特征关系，从而实现准确的像素分类预测。在具有挑战性的冰川分割基准数据集CaFFe上进行的大量实验和比较表明，我们的AMD-HookNet实现了438 m的平均距离误差，比当前最先进的水平高出42%，这验证了其有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
