A Stereo-based Pedestrian Detection System for Smart Intersection

This paper introduces a stereo-based pedestrian detection system for smart intersection applications. Promising for real-time usage, a detector with sliding window approach is employed. In order to reduce scanning time, stereo cameras are utilized. Firstly, the system generates a disparity image from calibrated left and right images. Then, searching regions of interest (ROI) for pedestrians are obtained by clustering the disparity information. Finally, a raster scan is applied to all of the ROI and their scaled copies. For distance measurement, the authors developed a fast and accurate algorithm called Inverted Phase Filter (IPF), which can measure the disparity at sub-pixel level fast. Furthermore, for pedestrian classification, a novel feature – Staggered multi-scale LBP (Local Binary Pattern) histogram – is proposed. Evaluation results show that the proposed feature outperforms benchmarks like HOG and CoHOG on Panasonic night-time dataset and Daimler Chrysler dataset.

• Supplemental Notes:
  • Abstract reprinted with permission from Intelligent Transportation Society of America.
• Corporate Authors:

  ITS America

  1100 17th Street, NW, 12th Floor
  Washington, DC  United States  20036
• Authors:
  • Cao, Yunyun
  • Pranata, Sugiri
  • Yasugi, Makoto
  • Niu, Zhiheng
  • Nishimura, Hirofumi
• Conference:
  • 19th ITS World Congress
  • Location: Vienna , Austria
  • Date: 2012-10-22 to 2012-10-26
• Publication Date: 2012

Language

• English

Media Info

• Media Type: Digital/other
• Features: CD-ROM; Figures; Photos; References; Tables;
• Pagination: 8p
• Monograph Title: 19th ITS World Congress, Vienna, Austria, 22 to 26 October 2012

Subject/Index Terms

• TRT Terms: Automated highways; Histograms; Intersections; Pedestrian detectors; Real time information; Stereoscopic cameras
• Subject Areas: Highways; Operations and Traffic Management; Pedestrians and Bicyclists; I73: Traffic Control;

Filing Info

• Accession Number: 01499136
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 21 2013 9:14AM