Volumetric Collision Course Modelling for Road Safety Analysis

Proactive road safety analysis allows for the pre-emptive diagnosis of road safety issues without direct observation of traffic accidents by observing traffic-conflict-like events, and this is made possible with large quantities of high-resolution road user trajectory data acquired from video data. However, several practical challenges exist in relation to the nature of this data for use in large-scale automated road safety analyses applications of this nature. Two small, but key, issues with deployment of such a system related to road user size are identified, studied, and addressed, namely: volumetric-based collision prediction modeling, and unsupervised camera calibration from estimated road user classification size and movement.

Paul St-Aubin
Faculty Supervisor: 
Liping Fu
Partner University: