Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

TL;DR

This paper presents a deep learning approach using region-based CNNs to automatically detect road intersections in scanned historical USGS maps, improving accuracy over traditional methods especially for complex and double-line maps.

Contribution

The study introduces a CNN-based method for extracting road intersections from historical maps, demonstrating higher accuracy than traditional computer vision techniques.

Findings

Higher accuracy for double-line map representations

CNN outperforms traditional computer vision algorithms

Detection errors increase with map complexity and blurriness

Abstract

Road intersections data have been used across different geospatial applications and analysis. The road network datasets dating from pre-GIS years are only available in the form of historical printed maps. Before they can be analyzed by a GIS software, they need to be scanned and transformed into the usable vector-based format. Due to the great bulk of scanned historical maps, automated methods of transforming them into digital datasets need to be employed. Frequently, this process is based on computer vision algorithms. However, low conversion accuracy for low quality and visually complex maps and setting optimal parameters are the two challenges of using those algorithms. In this paper, we employed the standard paradigm of using deep convolutional neural network for object detection task named region-based CNN for automatically identifying road intersections in scanned historical USGS maps of several U.S. cities. We have found that the algorithm showed higher conversion accuracy for the double line cartographic representations of the road maps than the single line ones. Also, compared to the majority of traditional computer vision algorithms RCNN provides more accurate extraction. Finally, the results show that the amount of errors in the detection outputs is sensitive to complexity and blurriness of the maps as well as the number of distinct RGB combinations within them.