Publication:
Multiple Object Tracking for Robust Quantitative Analysis of Passenger Motion While Boarding and Alighting a Metropolitan Train

Loading...
Thumbnail Image
Identifiers
Publication date
2021-03-17
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IET Digital Library
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
To achieve significant improvements in public transport it is necessary to develop an autonomous system that locates and counts passengers in real time in scenarios with a high level of occlusion, providing tools to efficiently solve problems such as reduction and stabilization in travel times, greater fluency, better control of fleets and less congestion. A deep learning method based in transfer learning is used to accomplish this: You Only Look Once (YOLO) version 3 and Faster R-CNN Inception version 2 architectures are fine tuned using PAMELA-UANDES dataset, which contains annotated images of the boarding and alighting of passengers on a subway platform from a superior perspective. The locations given by the detector are passed through a multiple object tracking system implemented based on a Markov decision process that associates subjects in consecutive frames and assigns identities considering overlaps between past detections and predicted positions using a Kalman filter.
Description
Procedings in: 11th International Conference on Pattern Recognition Systems (ICPRS-21), conference paper, 17-19 mar, 2021, Universidad de Talca, Curicó, Chile.
Keywords
Deep learning, Object detection, Passenger counting, YOLO v3, Faster R-CNN
Bibliographic citation
Gómez Meza, J. S., et al. (2021, march). Multiple Object Tracking for Robust Quantitative Analysis of Passenger Motion While Boarding and Alighting a Metropolitan Train. In: 11th International Conference on Pattern Recognition Systems (ICPRS-21), conference paper, 17-19 mar, 2021, Universidad de Talca, Curicó, Chile.