Deep Learning Detection and Recognition of Spot Elevations on Historical Topographic Maps
Deep Learning Detection and Recognition of Spot Elevations on Historical Topographic Maps
复制标题
DOI：
10.3389/fenvs.2022.804155
复制
发表时间：
2022-02
影响因子：
2.4
通讯作者：
S. Arundel;T. P. Morgan;Phillip T. Thiem
中科院分区：
文献类型：
--
作者：
S. Arundel;T. P. Morgan;Phillip T. Thiem
历史地形图中包含的一些信息尚未以数字方式捕获，这限制了自动查询此类数据的能力。例如，美国地质调查局的历史地形图集 (HTMC) 显示了经过精心挑选以最能代表当时地形的位置的数百万个点高程。尽管研究尝试重现这些数据点，但事实证明，它不足以自动检测和识别 HTMC 中的点高程。我们提出了一种使用大型基准文本数据集进行预训练的深度学习工作流程。我们向这些数据集添加手动制作的训练图像/标签对，并测试提高预测准确性所需的数量。我们发现，仅使用基准数据进行预训练的初始模型无法正确预测任何 HTMC 点高程，而仅添加 50 个自定义图像/标签对即可将预测能力提高约 50%，而包含 350 个数据对则将性能提高约 80%。以旋转、缩放和平移（偏移）形式进行的数据增强扩大了训练数据集的大小和多样性，并大大提高了识别准确率，最高可达 95%。可视化方法（例如热图生成和显着特征检测）可用于更好地理解某些预测失败的原因。
Some information contained in historical topographic maps has yet to be captured digitally, which limits the ability to automatically query such data. For example, U.S. Geological Survey’s historical topographic map collection (HTMC) displays millions of spot elevations at locations that were carefully chosen to best represent the terrain at the time. Although research has attempted to reproduce these data points, it has proven inadequate to automatically detect and recognize spot elevations in the HTMC. We propose a deep learning workflow pretrained using large benchmark text datasets. To these datasets we add manually crafted training image/label pairs, and test how many are required to improve prediction accuracy. We find that the initial model, pretrained solely with benchmark data, fails to predict any HTMC spot elevations correctly, whereas the addition of just 50 custom image/label pairs increases the predictive ability by ∼50%, and the inclusion of 350 data pairs increased performance by ∼80%. Data augmentation in the form of rotation, scaling, and translation (offset) expanded the size and diversity of the training dataset and vastly improved recognition accuracy up to ∼95%. Visualization methods, such as heat map generation and salient feature detection, can be used to better understand why some predictions fail.