Fast Cyclist Detection by Cascaded Detector and Geometric Constraint

In this paper the authors present a vision-based detection system for cyclists. The authors build cascaded detectors with different classifiers and shared features to detect cyclists from multiple viewpoints. To improve the performance, the authors reveal the dependence between the size and the position of an object in the image by a regression method. The authors also explore the applications of this geometric constraint with different camera setups. Based on experiments the authors demonstrate that their detector is suitable for real time applications.

Language

  • English

Media Info

  • Media Type: Web
  • Features: References;
  • Pagination: pp 1286-1291
  • Monograph Title: 18th International IEEE Conference on Intelligent Transportation Systems (ITSC 2015)

Subject/Index Terms

Filing Info

  • Accession Number: 01602718
  • Record Type: Publication
  • ISBN: 9781467365956
  • Files: TRIS
  • Created Date: May 2 2016 3:25PM