Counting pedestrians passing through a line in crowded scenes by extracting optical flows

Yoshiaki Taniguchi, Miki Mizushima, Go Hasegawa, Hirotaka Nakano, Morito Matsuoka

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

In this paper, we propose a counting method of pedestrians passing through a specific line, called counting line, in crowded scenes. In our proposed method, the number of optical flows whose segment crosses the counting line is used for estimation of the number of pedestrians. To improve accuracy of estimation, we delete optical flows detected falsely or extracted from background image. Through experimental evaluations using actual video sequences, we show that the correlation coefficient between the number of optical flows and the number of pedestrians passing through the counting line is more than 0.856. We also show that the mean relative error of our proposed method is less than 0.068.

Original languageEnglish
Pages (from-to)303-316
Number of pages14
JournalInformation (Japan)
Volume19
Issue number1
Publication statusPublished - 2016 Jan
Externally publishedYes

Keywords

  • Counting line
  • Good feature
  • Optical flow
  • Pedestrian counting
  • Video sequence

ASJC Scopus subject areas

  • Information Systems

Fingerprint

Dive into the research topics of 'Counting pedestrians passing through a line in crowded scenes by extracting optical flows'. Together they form a unique fingerprint.

Cite this