16 Jun Student | Alexander Virgona | Design, Modelling and Simulation
PhD students
Alexander Virgona
University of Technology Sydney (Supervisors: Alen Alempijevic, Teresa Vidal Calleja)
PhD topic – Robotic Perception of Pedestrians: Detecting, Tracking, and Trajectory Prediction in Crowded Environments
Research summary
The University of Technology Sydney, together with Downer, created a diagnostic tool that uses 3D depth sensing cameras and algorithms, to anonymously monitor passenger numbers and movement on train station platforms. Alex’s thesis involved developing the algorithms at the heart of this technology which interpret the raw 3D data to detect the locations of passengers and track their movements in crowded conditions. Named Dwell Track, the technology can quantify passenger congestion on platforms and near train doors that can lead to extended dwell times. Data from Dwell Track could enable train operators to improve platform management procedures and communications to passengers and real time outputs from this system could be used to enable smart responsive infrastructure of the future.
Expected completion date
September 2020
Key achievements
- Developed novel algorithms for person detection and tracking, leveraging insights into social behaviour to improve robustness in crowded environments that typically challenge such algorithms.
- Worked part time alongside completing research as a software engineer with a team at UTS to convert the research work into a functional prototype of the Dwell Track system.
- Dwell Track able to automatically detect the platform edge, train door status and position/orientation of up to 50 passengers per camera on a railway platform.
- A network of 16 Dwell Track devices were installed along the length of Wynyard’s platform three, providing real-time data on mobile devices of platform staff via dashboards in a trial conducted with Sydney Trains.