Files and links (2)
Computer aided Civil Eng - 2020 - Wijnands - Identifying safe intersection design through unsupervised feature extraction13.97 MB
Published VersionCC BY-NC-ND V4.0, Open Access
Published VersionCC BY-NC-ND V4.0, Open
Journal article
Identifying safe intersection design through unsupervised feature extraction from satellite imagery
Computer-Aided Civil and Infrastructure Engineering, Vol.36(3), pp.346-361
2021
Abstract
The World Health Organization has listed the design of safer intersections as a key intervention to reduce global road trauma. This article presents the first study to systematically analyze the design of all intersections in a large country, based on aerial imagery and deep learning. Approximately 900,000 satellite images were downloaded for all intersections in Australia and customized computer vision techniques emphasized the road infrastructure. A deep autoencoder extracted high-level features, including the intersection's type, size, shape, lane markings, and complexity, which were used to cluster similar designs. An Australian telematics data set linked infrastructure design to driving behaviors captured during 66 million kilometers of driving. This showed more frequent hard acceleration events (per vehicle) at four- than three-way intersections, relatively low hard deceleration frequencies at T-intersections, and consistently low average speeds on roundabouts. Overall, domain-specific feature extraction enabled the identification of infrastructure improvements that could result in safer driving behaviors, potentially reducing road trauma.
Details
- Title
- Identifying safe intersection design through unsupervised feature extraction from satellite imagery
- Authors
- Jasper S. Wijnands (Corresponding Author) - The University of MelbourneHaifeng Zhao (Author) - The University of MelbourneKerry A. Nice (Author) - The University of MelbourneJason Thompson (Author) - The University of MelbourneKatherine Scully (Author) - The University of MelbourneJingqiu Guo (Author) - Tongji UniversityMark Stevenson (Author) - The University of Melbourne
- Publication details
- Computer-Aided Civil and Infrastructure Engineering, Vol.36(3), pp.346-361
- Publisher
- Wiley-Blackwell Publishing, Inc.
- Date published
- 2021
- DOI
- 10.1111/mice.12623
- ISSN
- 1467-8667; 1093-9687
- Copyright note
- This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made. © 2020 The Authors. Computer-Aided Civil and Infrastructure Engineering published by Wiley Periodicals LLC on behalf of Editor
- Data Availability
- The following supporting information is available on Zenodo: Data set S1 (https://doi.org/10.5281/zenodo.2564253)
- Grants
- Grant note
- This research was supported by the ACT Road Safety Fund (grant number 17/8281). J.G. is supported by the Opening Foundation of the Key Laboratory of Road and Traffic Engineering of the Ministry of Education (China).
- Organisation Unit
- Centre for Human Factors and Systems Science
- Language
- English
- Record Identifier
- 991184301802621
- Output Type
- Journal article
Metrics
1 Record Views