Single-view 3D tracking and trajectory classification of road users at intersections

The goal of the project is to research and develop computer vision algorithms, software, and specialized hardware for the analysis of mixed traffic at intersections. Road users will be detected and classified as motor vehicles, pedestrians and bicycles. Road users will be geo-located within a 3D model of the intersection, tracked and classified according to trajectory. Our partner TransPlan will benefit in that they will be the Canadian receptor for the algorithms and software that Shahab generates. They will use this to automatic their current manual traffic analysis process, which will make them more efficient and improve their competitiveness in the market. With TransPlan, we will also explore wider licensing or sales of the technology as a product globally. As a leading technology-oriented transportation engineering company in the GTA with a long list of clients, TransPlan is well-placed to take advantage of this technology.

Faculty Supervisor:

James Elder

Student:

Shahab Nabavi

Partner:

TransPlan Inc.

Discipline:

Other

Sector:

Transportation and warehousing

University:

York University