Looking at Pedestrians at Different Scales: A Multiresolution Approach and Evaluations

Typically, in a detector framework, the model size is fixed at the size of the smallest object to be detected, and larger objects are detected by scaling the input image. The information lost due to scaling could be vital for accurately detecting large objects, which is an essential task for vision-based driver-assistance systems. To this end, the authors evaluate a multiresolution detector framework by training models at different sizes and demonstrate its effectiveness on a state-of-the-art pedestrian detector. The authors' comprehensive evaluation demonstrates meaningful improvement in detector performance. On the KITTI dataset under moderate difficulty settings, the authors achieve a 6% increase in the detector's average precision over the baseline single-resolution result on the KITTI benchmark. Further insights into the detector's improvements are provided using a fine-grained analysis of the detector's performance at various threshold settings.

• Record URL:
  • https://doi.org/10.1109/TITS.2016.2561262
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2016, IEEE.
• Authors:
  • Rajaram, Rakesh Nattoji
  • Ohn-Bar, Eshed
  • Trivedi, Mohan Manubhai
• Publication Date: 2016-12

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 3565-3576
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 17
  • Issue Number: 12
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Driver support systems; Machine vision; Pedestrian detectors; Pedestrian safety; Pedestrians; Performance; Precision
• Uncontrolled Terms: Feature extraction
• Subject Areas: Data and Information Technology; Highways; Pedestrians and Bicyclists; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01619114
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 21 2016 11:29AM