Modeling for gesture set design toward realizing effective human-vehicle interface

Cheoljong Yang, Jongsung Yoon, Jounghoon Beh, Hanseok Ko

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

3 Citations (Scopus)

Abstract

Intuitive driver-to-vehicle interface is highly desirable as we experience rapid increase of vehicle device complexity in modern day automobile. This paper addresses the gesture mode of interface and proposes an effective gesture language set capable of providing automotive control via hand gesture as natural but safe human-vehicle interface. Gesture language set is designed based on practical motions of single hand gesture. Proposed language set is optimized for in-vehicle imaging environment. Feature mapping for recognition is achieved using hidden Markov model which effectively captures the hand motion descriptors. Representative experimental results indicate that the recognition performance of proposed language set is over 99%, which makes it promising for real vehicle application.

Original languageEnglish
Title of host publicationComputers,Networks, Systems, and Industrial Engineering 2011
EditorsRoger Lee, Yung-Cheol Byun, Kiumi Akingbehin
Pages171-180
Number of pages10
DOIs
Publication statusPublished - 2011

Publication series

NameStudies in Computational Intelligence
Volume365
ISSN (Print)1860-949X

Keywords

  • HMM
  • driver-vehicle interface
  • gesture recognition
  • language set

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Modeling for gesture set design toward realizing effective human-vehicle interface'. Together they form a unique fingerprint.

Cite this