Toronto faces some of the worst traffic congestion in the world. In 2023, driving 10 km downtown took nearly 30 minutes on average, and by 2024 drivers were still losing more than 70 hours each year to congestion. Rush hour stretches from early morning until evening, with travel times nearly doubling during peak periods. While drivers lose time, the impacts reach further. Pedestrians and cyclists passing through busy intersections are exposed to elevated levels of exhaust, and air quality hotspots near highways and traffic corridors regularly record particulate matter several times higher than the city average.
Our project uses widely available traffic data and low-cost sensors to pursue innovations in sensing and detection technologies for road safety, exploring new ways to capture traffic flow, vehicle activity, and environmental conditions. Together, these approaches aim to create tools that inform not only congestion management and collision prevention but also the hidden health and environmental risks of city travel.
GitHub Repository: <to be updated>
Skills and Expertise Involved
- Key areas of work include:
- Applied machine learning for prediction and pattern recognition
- Building and integrating sensing hardware
- Developing software tools to support data collection and analysis
- Designing and conducting user studies in real-world settings
- Applying computer vision methods to traffic and environmental data
- Working with audio and other complex signals
- Investigating links between environmental health and exposure
- Core competencies required are:
- Programming in Python
- Data wrangling and cleaning large, noisy datasets
- Statistical modeling and evaluation of analytical methods
We are seeking students who are interested in gaining experience in these areas. Opportunities may be offered on either a volunteer basis or through paid positions, depending on project needs and available resources.