A Bus Crowdedness Sensing System Using Deep-Learning Based Object Detection

Wenhao Huang, Akira Tsuge, Yin Chen, Tadashi Okoshi, Jin Nakazawa

Research output: Contribution to journalArticlepeer-review

Abstract

Crowdedness of buses is playing an increasingly important role in the disease control of COVID-19. The lack of a practical approach to sensing the crowdedness of buses is a major problem. This paper proposes a bus crowdedness sensing system which exploits deep learningbased object detection to count the numbers of passengers getting on and off a bus and thus estimate the crowdedness of buses in real time. In our prototype system, we combine YOLOv5s object detection model with Kalman Filter object tracking algorithm to implement a sensing algorithm running on a Jetson nano-based vehicular device mounted on a bus. By using the driving recorder video data taken from real bus, we experimentally evaluate the performance of the proposed sensing system to verify that our proposed system system improves counting accuracy and achieves real-time processing at the Jetson Nano platform.

Original languageEnglish
Pages (from-to)1712-1720
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE105D
Issue number10
DOIs
Publication statusPublished - 2022 Oct

Keywords

  • bus crowdedness sensing
  • deep learning
  • edge computing
  • image processing
  • object detection
  • smart cities

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A Bus Crowdedness Sensing System Using Deep-Learning Based Object Detection'. Together they form a unique fingerprint.

Cite this