Artificial Intelligence v. Austin Traffic

Researchers from UT, TACC and City of Austin develop AI tools to automatically analyze road behavior and create searchable databases

Look above the traffic light at a busy intersection in your city and you will probably see a camera. These devices monitor traffic conditions and provide visuals in the case of a collision. But can they do more?

Researchers from TACC, The University of Texas Center for Transportation Research, and the City of Austin developed a tool that uses artificial intelligence to recognize cars, bikes, and pedestrians in raw traffic camera footage and characterize how they move and interact. This information can then be analyzed by traffic engineers and officials to improve the safety and performance of the city's transportation network.

The project earned a 2018 Smart 50 Award, recognizing it as one of the most innovative and influential smart cities projects in the world.

The team at TACC is now working on a more sophisticated algorithm for pedestrian detection and tracking to enable the City of Austin to identify potential areas of concern and ultimately improve pedestrian safety.