4.7 Article

Deep Learning-Based Road Extraction From Historical Maps

Journal

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2022.3204817

Keywords

Convolutional neural networks; historical maps; multiclass road segmentation; road type detection

Funding

  1. European Research Council (ERC) under the European Union [679097]

Ask authors/readers for more resources

The research aimed to propose an ideal architecture, encoder, and hyperparameter settings for historical road extraction, achieving the best results with the combination of Unet++ architecture and split-attention network (Timm-resnest200e) encoder, which can directly be used for inference of other historical maps and transfer learning.
Automatic road extraction from historical maps is an important task to understand past transportation conditions and conduct spatiotemporal analysis revealing information about historical events and human activities over the years. This research aimed to propose the ideal architecture, encoder, and hyperparameter settings for the historical road extraction task. We used a dataset including 7076 patches with the size of 256 x 256 pixels generated from scanned historical Deutsche Heereskarte 1:200 000 Turkei (DHK 200 Turkey) maps and their corresponding digitized ground truth masks for five different roads types. We first tested the widely used Unet++ and Deeplabv3 architectures. We also evaluated the contribution of attention models by implementing Unet++ with the concurrent spatial and channel-squeeze and excitation block and multiscale attention net. We achieved the best results with split-attention network (Timm-resnest200e) encoder and Unet++ architecture, with 98.99% overall accuracy, 41.99% intersection of union, 51.41% precision, 69.7% recall, and 57.72% F1 score values. Our output weights could be directly used for the inference of other DHK maps and transfer learning for similar or different historical maps. The proposed architecture could also be implemented in different road extraction studies.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available