Real Time Human Motion Recognition Based on a Motion History Image and an Eigenspace

Takehito Ogata; Masudur M Rahman; Joo Kooi Tan; Seiji Ishikawa

doi:10.11499/sicep.2004.0_33_3

SICE Annual Conference 2004

DOI https://doi.org/10.11499/sicep.2004.0_33_3

Conference information

Host: The Society of Instrument and Control Engineers

Co-host: The IEEE Industrial Electronics Society, The IEEE Robotics and Automation Society, The IEEE Control Systems Society, The IEEE Systems, Man and Cybernetics Society, The Instrumentation, Systems, and Automation Society

Real Time Human Motion Recognition Based on a Motion History Image and an Eigenspace

*Takehito Ogata, Masudur M Rahman, Joo Kooi Tan, Seiji Ishikawa

Author information

Keywords: Human motion, recognition, real time

CONFERENCE PROCEEDINGS FREE ACCESS

Pages 33

Details

Abstract

In this paper, we propose an efficient motion recognition technique based on an eigenspace method. In the proposed system, we use a motion history image and a superposed motion image to create an eigenspace and it is employed for the real time motion recognition. Experimental results show satisfactory performance of the technique.

Corresponding author

Register with J-STAGE for free!