Beat-based gesture recognition for non-secure, far-range, or obscured perception scenarios

Graylin Trevor Jay, Patrick Beeson, and Odest Chadwicke Jenkins. Beat-based gesture recognition for non-secure, far-range, or obscured perception scenarios. In IJCAI Workshop on Space, Time and Ambient Intelligence (STAMI), Barcelona, Spain, July 2011.

Abstract

Gesture recognition is an important communication modality for a variety of human-robot applications, including mobile robotics and ambient intelligence domains. Most gesture recognition systems focus on estimating the position of the arm with respect to the torso of a tracked human. As an alternative, we present a novel approach to gesture recognition that focuses on reliable detection of time-dependent, cyclic “beats” given by a human user. While the expressiveness of “beat-based” gestures is limited, beat-based gesture recognition has several benefits, including reliable 2D gesture detection at far ranges, gesture detection anywhere in the image frame, detection when the human is mostly hidden or obscured, and secure detection via randomly rotated beat patterns that are known only by the user and the perception system. In addition to discussing this complimentary approach to gesture recognition, we also overview a preliminary implementation of beat-based gestures, and demonstrate some initial successes.

BibTeX

@InProceedings{Jay-stami-11,
  author =       {Graylin Trevor Jay and Patrick Beeson and Odest Chadwicke
                  Jenkins},
  title =        {Beat-based gesture recognition for non-secure, far-range, or
                  obscured perception scenarios},
  booktitle =    {IJCAI Workshop on Space, Time and Ambient Intelligence
                  (STAMI)},
  year =         2011,
  address =      {Barcelona, Spain},
  month =        {July},
  abstract =     {Gesture recognition is an important communication modality
                  for a variety of human-robot applications, including mobile
                  robotics and ambient intelligence domains.  Most gesture
                  recognition systems focus on estimating the position of the
                  arm with respect to the torso of a tracked human.  As an
                  alternative, we present a novel approach to gesture
                  recognition that focuses on reliable detection of
                  time-dependent, cyclic ``beats'' given by a human user.
                  While the expressiveness of ``beat-based'' gestures is
                  limited, beat-based gesture recognition has several
                  benefits, including reliable 2D gesture detection at far
                  ranges, gesture detection anywhere in the image frame,
                  detection when the human is mostly hidden or obscured, and
                  secure detection via randomly rotated beat patterns that are
                  known only by the user and the perception system.  In
                  addition to discussing this complimentary approach to
                  gesture recognition, we also overview a preliminary
                  implementation of beat-based gestures, and demonstrate some
                  initial successes.},
  bib2html_pubtype ={Workshop},
  bib2html_rescat ={Human-Robot Interaction},
}

Download:

[475.0KB pdf]