Urban road user classification framework using local feature descriptors and HMM

Surveillance and safety systems for pedestrians and bicyclists are becoming much more important because there continue to be a large number of traffic accidents that involve vulnerable road users. In this paper, the authors propose an urban road user classification framework using local feature descriptors and hidden Markov models (HMM). Their framework achieved pedestrians, bicyclists, motorcyclist classification in high accuracy. The framework consists of two classification methods: pedestrian-bicyclist classification and bicyclist-motorcyclist classification. First, they discriminate between pedestrians and bicyclist-like objects using histograms of oriented gradients (HOG)-based classifiers. They implemented a cascade classifier using generic HOG and their original local feature descriptor called co-occurrence semantic HOG. Bicyclist-like objects mainly consist of bicyclists and motorcyclists. They focused on the objects' leg motions and classify them using the hidden Markov models (HMM)-based motion models. They conducted experiments with real traffic scenes to evaluate the performance of their framework. The experiments for pedestrian-bicyclist classification and bicyclist-motorcyclist classification are conducted independently and both methods achieve nearly 90% on classification.

• Record URL:
  https://doi.org/10.1109/ITSC.2012.6338669
• Availability:
  • Find a library where document is available. Order URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6328848
• 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:
  • Takahashi, T
  • HyungKwan, Kim
  • Kamijo, S
• Conference:
  • 15th International IEEE Conference on Intelligent Transportation Systems (ITSC2012)
  • Location: Anchorage Alaska, United States
  • Date: 2012-9-16 to 2012-9-19
• Publication Date: 2012-9

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 67-72
• Monograph Title: 15th International IEEE Conference on Intelligent Transportation Systems (ITSC 2012)

Subject/Index Terms

• TRT Terms: Classification; Cyclists; Markov processes; Pedestrians; Traffic safety; Urban highways; Vulnerable road users
• Subject Areas: Highways; Pedestrians and Bicyclists; Planning and Forecasting; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01563654
• Record Type: Publication
• ISBN: 9781467330640
• Files: TRIS
• Created Date: May 19 2015 1:48PM