Abstract
Increasing the number of bike commutes can provide numerous benefits for individuals and communities. However, several factors including the availability of cycle paths, traffic char- acteristics, and pavement quality, can either encourage or discourage the use of bicycles. To promote cycling and understand how cyclists interact with the urban environment, it is crucial to assess the quality of cyclist routes. This paper proposes a pipeline that calculates the level of safety and comfort for cyclists by examining route segments using computer vision models trained on YOLOv5 to classify pavement types, detect pavement defects and detect the presence of cycle paths. The models for pavement type and cyclist paths had good results but the pave- ment defect model will demand more training to be used. The first experiment with the pipeline did not achieve high accuracy but helped to identify the next steps.
Paper Type
Full Paper
DOI
10.62036/ISD.2023.13
Cyclist Route Assessment Using Machine Learning
Increasing the number of bike commutes can provide numerous benefits for individuals and communities. However, several factors including the availability of cycle paths, traffic char- acteristics, and pavement quality, can either encourage or discourage the use of bicycles. To promote cycling and understand how cyclists interact with the urban environment, it is crucial to assess the quality of cyclist routes. This paper proposes a pipeline that calculates the level of safety and comfort for cyclists by examining route segments using computer vision models trained on YOLOv5 to classify pavement types, detect pavement defects and detect the presence of cycle paths. The models for pavement type and cyclist paths had good results but the pave- ment defect model will demand more training to be used. The first experiment with the pipeline did not achieve high accuracy but helped to identify the next steps.
Recommended Citation
Caetano, A., Estima, J.,& Lima, E. (2023). Cyclist Route Assessment Using Machine Learning. In A. R. da Silva, M. M. da Silva, J. Estima, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Information Systems Development, Organizational Aspects and Societal Trends (ISD2023 Proceedings). Lisbon, Portugal: Instituto Superior Técnico. ISBN: 978-989-33-5509-1. https://doi.org/10.62036/ISD.2023.13