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

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.

23 pages, 8 figures

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SSD: Single Shot MultiBox Detector
• Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification
• An Introduction to Convolutional Neural Networks
• A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
• Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations
• Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks
• DOTA: A Large-scale Dataset for Object Detection in Aerial Images
• Multifractal to monofractal evolution of the London's street network
• How Image Degradations Affect Deep CNN-based Face Recognition?

Cited by in corpus (3)

• Towards the automated large-scale reconstruction of past road networks from historical maps
• Aligning geographic entities from historical maps for building knowledge graphs
• Neural networks for semantic segmentation of historical city maps: Cross-cultural performance and the impact of figurative diversity