Quantifying London Traffic Dynamics for Air Pollution Estimation

Better insight extraction from traffic data can aid the effort to understand/reduce air pollution, and allow dynamic traffic flow optimization. As of 2019, London traffic statistics (counts of vehicle types, stops, and starts) were often obtained through high-cost manual labor (i.e. individuals counting vehicles by the road) and were extrapolated to annual averages. Furthermore, statistics were not detailed enough to evaluate traffic/air pollution initiatives.

This project was conducted during the 2019 Data Science for Social Good Fellowship, at Imperial College London. The purpose of the project was to create an open-source library to automate the collection of live traffic video data, and extract descriptive statistics (counts, stops, and starts by vehicle type) using computer vision techniques. With this library, municipalities can use traffic camera data to obtain real-time traffic statistics that are localized to the level of individual streets.

See the technical report and README on the GitHub for more details. Follow-ups to this project are currently being conducted by the Alan Turing Institute.

https://www.turing.ac.uk/research/research-projects/project-odysseus-understanding-london-busyness-and-exiting-lockdown https://www.forbes.com/sites/imperialinsights/2019/09/23/data-science-for-social-good/#5d8352db464b