Tracking and Motion Cues for Rear-View Pedestrian Detection

This paper describes a new system for detecting pedestrians using the rear-view camera only. The system is based on "Accelerated Feature Synthesis" (AFS) part-based object detection which enables the detection of pedestrians across a wide range of appearance changes: upright and non-upright pedestrians, partially occluded pedestrians and children. In this paper the authors enhance the AFS by introducing an integrated system taking into account temporal cues for reducing the system error rates. The authors introduce two new algorithmic components: Non-maximal suppression (NMS) tracking which uses visual tracking and detection history to enhance detection, and local-motion features which help identifying independently moving objects. In addition the authors use a collected application-specific training data and make its test part available as a new benchmark. Compared to the previously published results, this integrated system reduces the false alarm rate (at 90% detection rate) by a factor of 24 and shows a promising capability of detecting pedestrians and children in arbitrary poses.

• Record URL:
  • https://doi.org/10.1109/ITSC.2015.114
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9781467365956
• Supplemental Notes:
  • Abstract reprinted with permission of IEEE.
• Corporate Authors:

  Institute of Electrical and Electronics Engineers (IEEE)

  3 Park Avenue, 17th Floor
  New York, NY  United States  10016-5997
• Authors:
  • Levi, Dan
  • Silberstein, Shai
• Conference:
  • 18th International IEEE Conference on Intelligent Transportation Systems (ITSC)
  • Location: Canary Islands , Spain
  • Date: 2015-9-15 to 2015-9-18
• Publication Date: 2015

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 664-671
• Monograph Title: 18th International IEEE Conference on Intelligent Transportation Systems (ITSC 2015)

Subject/Index Terms

• TRT Terms: Detection and identification systems; Errors; Image processing; Motion perception; Pedestrians; Tracking systems
• Subject Areas: Data and Information Technology; Pedestrians and Bicyclists;

Filing Info

• Accession Number: 01601060
• Record Type: Publication
• ISBN: 9781467365956
• Files: TRIS
• Created Date: May 31 2016 9:21AM