Abstract
In this paper a visual module is proposed as a part of a visuo-motor system, implemented on an anthropomorphic robotic platform. This platform is composed by a robotic arm with a human-like hand, and a robotic stereo head to provide visual information. The platform is able to reproduce a human hand-posture in the robotic human-like hand. The vision algorithm provides information about positioning, orientation and posture to the robotic hand. This is done in non-structured environments, in which illumination and workspace distribution can arbitrarily change. The recognition module is inspired in the Elastic Graph Matching algorithm. The main improvement of the proposed application is the ability to cope with affine transformations of the image, that is, with rotated, translated and scaled hand-postures, without the extensive use of comparisons.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
M. Lades, J.C. Vorbrüggen, J. Buhmann, J. Lance, C. Malsburg, R.P. Würtz, and W. Konen, Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42, 1993, 300–311.
J. Triesch, Vision-based robotic gesture recognition, (Doctoral Thesis, Bochum University, 1999).
M. Pinzolas, R. Chumilla, JL. Coronado, Affine-Invariant Graph Matching, 3rd IASTED International Conference on Visualization, Imaging and Image Processing, 2003, Benalmádena, España. Vol:1, pp: 1002–1008.
J. F. Canny, A computational approach to edge detecttion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.
PETS2002 datasets, The University of Reading, UK. Website: http://pets2002.visualsurveillance.org
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
García, D., Pinzolas, M., Coronado, J.L., Martínez, P. (2006). An Application of the AIGM Algorithm to Hand-Posture Recognition in Manipulation. In: Tokhi, M.O., Virk, G.S., Hossain, M.A. (eds) Climbing and Walking Robots. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-26415-9_118
Download citation
DOI: https://doi.org/10.1007/3-540-26415-9_118
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26413-2
Online ISBN: 978-3-540-26415-6
eBook Packages: EngineeringEngineering (R0)