Symmetrical Judgement Area Reduction and Ecohog Feature Descriptor for Pedestrian Detection

In this study, a method to detect pedestrians using an in-vehicle camera is presented. The authors improved the technology in detecting pedestrians with highly accurate images using a monocular camera. The authors were able to predict pedestrian activities by monitoring them, and they developed an algorithm to recognize pedestrians and their movements more accurately. For the feature descriptor, the authors found that an Extended Co-occurrence Histogram of Oriented Gradients (ECoHOG) was the best in decreasing both the undetectable and the excessive detectable ratio. Thus, the use of the new method by images captured on the real road was validated.

• Record URL:
  https://doi.org/10.1504/IJVS.2012.048548
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/14793105
• Authors:
  • Kataoka, Hirokatsu
  • Aoki, Yoshimitsu
  • Matsui, Yasuhiro
• Publication Date: 2012

Language

• English

Media Info

• Media Type: Print
• Features: Figures; Photos; References; Tables;
• Pagination: pp 48-60
• Serial:
  • International Journal of Vehicle Safety
  • Volume: 6
  • Issue Number: 1
  • Publisher: Inderscience Enterprises Limited
  • ISSN: 1479-3105
  • EISSN: 1479-3113
  • Serial URL: http://www.inderscience.com/jhome.php?jcode=ijvs

Subject/Index Terms

• TRT Terms: Algorithms; Highway safety; Histograms; Pedestrian detectors; Pedestrian safety; Technological innovations; Video cameras
• Subject Areas: Highways; Pedestrians and Bicyclists; Safety and Human Factors; Vehicles and Equipment; I73: Traffic Control; I91: Vehicle Design and Safety;

Filing Info

• Accession Number: 01499371
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 21 2013 9:20AM