Abstract Manager

As more and more cities and municipalities are updating their transportation master plans, a trend is emerging: an increase in mode shift targets. Specifically, cities are looking to increase the number of cyclists and pedestrians on their networks while reducing the presence of single occupancy vehicles. Barriers can arise at each stage of mode-shift projects, requiring decision makers to utilize novel technologies to alleviate public concern and achieve desired outcomes.

A key barrier to arise and address in any active transportation project is managing public perceptions from the perspective of all transportation network users. Citizens - regardless of mode choice - require assurance that they can move within a system safely and efficiently. Upon completion of an AT project, citizens also want to know that their tax dollars were well-utilized. Additional data insights including vulnerable road-user-to-vehicle conflicts, facility uptake, and signal performance measures related to pedestrians and cyclists can help address public concerns from the planning stage of an AT project through to completion and monitoring. It is difficult to improve upon what is not currently being measured, and cutting-edge technologies like artificial intelligence (AI) and computer vision (CV) may be able to help. When applied to video, these technologies can support AT projects through accurate data collection and analysis in pre and post implementation of the project to ensure that the project will be successful.

This informative session discusses the common challenges of collecting bicycle data and how technology, specifically AI and CV, can be used in every stage of a bicycle facility project, from planning to post-implementation. Additionally, we will provide real-world examples of how cities throughout Canada have been using this data to improve their AT projects operationally and from a safety standpoint.