Multiple object tracking for robust quantitative analysis of passenger motion while boarding and alighting a metropolitan train

José Sebastián Gómez Meza, José Delpiano, Sergio A. Velastin, Rodrigo Fernández, Sebastián Seriani Awad

Research output: Contribution to conferencePaperpeer-review

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 RCNN 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.

Original languageEnglish
Pages231-238
Number of pages8
DOIs
StatePublished - 7 Oct 2021
Event11th International Conference of Pattern Recognition Systems, ICPRS 2021 - Virtual, Online
Duration: 17 Mar 202119 Mar 2021

Conference

Conference11th International Conference of Pattern Recognition Systems, ICPRS 2021
CityVirtual, Online
Period17/03/2119/03/21

Bibliographical note

Publisher Copyright:
© 2021 Institution of Engineering and Technology. All rights reserved.

Keywords

  • Deep learning
  • Faster R-CNN
  • Object detection
  • Passenger counting
  • YOLO v3

Fingerprint

Dive into the research topics of 'Multiple object tracking for robust quantitative analysis of passenger motion while boarding and alighting a metropolitan train'. Together they form a unique fingerprint.

Cite this