Improving Traffic Safety Through Video Analysis

Fellows: Joao Caldeira, Alex Fout, Aniket Kesari, Raesetje Sefala
Data Science Mentor(s): Joe Walsh
Project Manager: Katy Dupre
Project Partner: Jakarta Smart City & UN Global Pulse, Jakarta
[Short Presentation Video] [Project Blog Post] [Github Repository] [Paper]

UPDATE: We are pleased to announce that this project team won a Highlighted Paper Award at the AI For Social Good NIPS2018 Workshop! Congratulations to the Jakarta Fellows!

Nearly 2,000 people die annually as a result of being involved in traffic-related accidents in Jakarta, Indonesia. The city government has invested resources in thousands of traffic cameras to help identify potential short-term (e.g. vendor carts in a hazardous location) and long-term (e.g. poorly engineered intersections) safety risks. However, manually analysing the available footage is an overwhelming task for the city’s Transportation Agency. In support of the Jakarta Smart City initiative, our team hopes to build a video-processing pipeline to extract structured information from raw traffic footage. This information can be integrated with collision, weather, and other data in order to build models which can help public officials quickly identify and assess traffic risks with the goal of reducing traffic-related fatalities and severe injuries.