Multimodal deep learning framework for traffic volume estimation: a city-scale case study in Edmonton, Alberta
Canadian Journal of Civil Engineering · 01.01.2026 · 53 · 1-15
DOI: 10.1139/cjce-2025-0547 ↗Kurz gefasst
Fachartikel in der Zeitschrift Canadian Journal of Civil Engineering, erschienen am 01.01.2026. Verfasst von Abhinav Parbhakar und 2 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: City of Edmonton.
Abstract (Originalsprache)
Traffic volume is essential for transportation planning, safety analysis, and infrastructure investment. Achieving comprehensive spatial coverage across road networks faces budgetary and logistical constraints, necessitating reliable estimation for unmonitored segments. This study addresses this gap by developing a multimodal deep learning framework that fuses aerial imagery with parametric data to estimate annual average weekday traffic. Using 749 ground-truth locations spanning over 5000 km of roadway, a citywide case-study is conducted in Edmonton, Alberta, representing one of the most spatially extensive and heterogeneous applications in literature to date. The proposed model is benchmarked against several established methodologies including multivariate linear regression, support vector regression, random forest, XGBoost, and neural networks. Results demonstrate that the framework reduces mean absolute percentage error by 7%–85% relative to these models. Thus, the research yields a robust methodology that integrates multiple data sources to assist transportation agency decision-making by providing city-wide traffic volume estimation.
Förderung
- City of Edmonton
Zitieren
APA
Parbhakar, A., Huynh, N., & Kwon, T. J. (2026). Multimodal deep learning framework for traffic volume estimation: a city-scale case study in Edmonton, Alberta. Canadian Journal of Civil Engineering, 53, 1-15. https://doi.org/10.1139/cjce-2025-0547
Vancouver
Parbhakar A, Huynh N, Kwon TJ. Multimodal deep learning framework for traffic volume estimation: a city-scale case study in Edmonton, Alberta. Canadian Journal of Civil Engineering. 2026;53:1-15. doi:10.1139/cjce-2025-0547
BibTeX
@article{Parbhakar2026,
author = {Parbhakar, Abhinav and Huynh, Nancy and Kwon, Tae J.},
title = {Multimodal deep learning framework for traffic volume estimation: a city-scale case study in Edmonton, Alberta},
journal = {Canadian Journal of Civil Engineering},
year = {2026},
volume = {53},
pages = {1--15},
doi = {10.1139/cjce-2025-0547}
}
EUVIMED