Vehicle and Pedestrian Trajectory and Gap Estimation for Traffic Conflict Prediction
We have developed components of a system to identify and measure vehicle and pedestrian trajectories, speed, inter-vehicle gaps and using video feeds from arbitrary traffic surveillance cameras. The potential impact to transportation safety is the ability to detect crashes in real-time and capturing near crashes or accidents and their context. Real-time analysis allows for immediate notification, detecting traffic density and speeds. Alerting safety planners to near-miss crash events and related contextual information, could provide critical information for safety enhancement through appropriate infrastructure safety modifications. This project’s main research focus was to build a system to identify and measure vehicle trajectories, speed, inter vehicle gaps and vehicle-pedestrian gaps using video feeds from arbitrary traffic surveillance cameras, most of which will not have been specially calibrated and where no training data is available. This work showed that it is possible to create a system that can monitor a video stream in real-time for the purpose of traffic monitoring and improving safety.
The potential impact of such a system to transportation safety is in the ability to detect car crashes. This allows real-time capturing near crashes in real-time, allowing for immediate notification, detecting traffic density and speeds, and alerting safety planners to near-miss crash events and related contextual information, which could be mitigated through appropriate infrastructure safety modifications.
Over time, we also generalized this research to deal with large scale analysis of vehicle activities, and tracking of multiple cars with the ability to re-identify the same cars at different city roads from different cameras. This work resulted in a system that won first prize at the Road Challenge competition and also placed first at the NVidia AI City Challenge. Details can be found below.
Read the full report here.