Abstract
This study presents an innovative approach for automatic road detection with deep learning, employing fusion strategies to utilize both lower-resolution satellite imagery and GPS trajectory data, a concept never explored before. We rigorously investigate both early and late fusion strategies and assess deep learning-based road detection performance using different fusion settings. Our extensive ablation studies evaluate the efficacy of our framework under diverse model architectures, loss functions, and geographic domains (Istanbul and Montreal). For an unbiased and complete evaluation of road detection results, we use both region-based and boundary-based evaluation metrics for road segmentation. The outcomes reveal that the ResUnet model outperforms U-Net and D-Linknet in road extraction tasks, achieving superior results over the benchmark study using low-resolution Sentinel-2 data. This research not only contributes to the field of automatic road detection but also offers novel insights into the utilization of data fusion methods in diverse applications.
Original language | English (US) |
---|---|
Pages (from-to) | 1013-1029 |
Number of pages | 17 |
Journal | Earth Science Informatics |
Volume | 17 |
Issue number | 2 |
DOIs | |
State | Published - Apr 2024 |
Funding
The numerical calculations reported in this paper were fully performed at TUBITAK ULAKBIM, High Performance and Grid Computing Center (TRUBA resources). The authors would like to thank the Istanbul Metropolitan Municipality and City of Montreal for the GPS trajectory dataset, the European Space Agency (ESA) for Sentinel-2 data, and the OpenStreetMap Foundation and OpenStreetMap Contributors for OpenStreetMap data. This study is part of the Ph.D. thesis conducted at Istanbul Technical University by the first author. The authors would like to thank the Ph.D. thesis advancement monitoring committee members, Gulsen Kaya Taskin and Taskin Kavzoglu.
Keywords
- Data fusion
- Deep learning
- GPS trajectory
- Multi-modal data
- Road detection
ASJC Scopus subject areas
- General Earth and Planetary Sciences