Prediction of driving behaviors in intersections based on a supervised dimension reduction considering locality

Takatomi Kubo, Ryunosuke Hamada, Zujie Zhang, Kazushi Ikeda, Takashi Bando, Kentarou Hitomi, Masumi Egawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Prediction of driving behavior has been regarded as one of the important issue to realize the next generation of advanced driver assistance systems. However, prediction of driving behaviors is also difficult issue, because the distribution of each driving behavior seems to be not unimodal but multimodal due to its intrinsic complexity and lack of a well-established segmentation method. When we consider to predict driving behaviors with a supervised dimension reduction method and hidden Markov models (HMMs), the multimodal structure of observed distributions should be preserved since they can contain information regarding these behaviors. We therefore propose to combine HMMs with local Fisher discriminant analysis (LFDA) that can maximize the between-class separata-bility and preserve within-class multimodality. We evaluated the performance of the HMMs with LFDA in predicting actual driving behaviors, and compared its performance with those of with conventional Fisher discriminant analysis and with no dimension reduction. As a result, the LFDA based method showed the best prediction accuracy among the all methods.

Original languageEnglish
Title of host publication2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1487-1489
Number of pages3
ISBN (Electronic)9781479960781
DOIs
Publication statusPublished - 2014 Nov 14
Event2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014 - Qingdao, China
Duration: 2014 Oct 82014 Oct 11

Publication series

Name2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014

Other

Other2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014
CountryChina
CityQingdao
Period14/10/814/10/11

ASJC Scopus subject areas

  • Computer Science Applications
  • Automotive Engineering
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Prediction of driving behaviors in intersections based on a supervised dimension reduction considering locality'. Together they form a unique fingerprint.

Cite this