Measurement of pedestrians in urban environment using subtraction stereo

  • Authors:

  • Kenji Terabayashi;Yuki Hashimoto;Yuma Hoshikawa;Kazunori Umeda

  • Affiliations:

  • Faculty of Science and Engineering, Chuo University and CREST, JST;School of Science and Engineering, Chuo University and CREST, JST;School of Science and Engineering, Chuo University and CREST, JST;Faculty of Science and Engineering, Chuo University and CREST, JST

  • Venue:
  • INSS'09 Proceedings of the 6th international conference on Networked sensing systems
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper discusses a method to detect and measure pedestrians in urban environment using "subtraction stereo." Subtraction stereo is a stereo vision method that calculates distance only for moving regions to make the stereo matching robust and fast. Pedestrians are detected based on their three dimensional features, which are position, height, width, and so on, obtained from a range image by standard labeling. The number of pedestrians in groups is estimated from their area on a range image. In urban environments, the effectiveness of this method is verified by experiments using a stereo camera which is commercially available and implemented with subtraction stereo.