Gesture Recognition for Humanoids using Proto-symbol Space

In this paper, we propose the system of gesture recognition for humanoids using proto-symbol space proposed by Inamura et al., by which we can tell similarity between gestures. Our goal is to develop the robust and real-time gesture recognition on real-world by humanoids. We succeeded to get 3D trajectory of human's hands using face detection and depth data obtained from stereo cameras. Our system does not need any special devices and skin color information. We can tell gestures changing with time, and also distinguish unknown gestures as unknown. By using proto-symbol space, we can generate humanoid's motion from human's gesture. Proposed system leads to imitation and teaching on humanoids.

[1]  Xia Liu,et al.  Hand gesture recognition using depth data , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[2]  Yoshihiko Nakamura,et al.  Embodied Symbol Emergence Based on Mimesis Theory , 2004, Int. J. Robotics Res..

[3]  Nobuyuki Otsu,et al.  Gesture recognition using auto-regressive coefficients of higher-order local auto-correlation features , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[4]  Luc Van Gool,et al.  Real-time pointing gesture recognition for an immersive environment , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[5]  Masayuki Inaba,et al.  Behavior Induction by Geometric Relation between Symbols of Multi-sensory Pattern , 2006, IAS.

[6]  Agnès Just,et al.  Recognition of isolated complex mono- and bi-manual 3D hand gestures , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[7]  Victor Ng-Thow-Hing,et al.  Estimating pose from depth image streams , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[8]  Paulo Menezes,et al.  A single camera motion capture system dedicated to gestures imitation , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[9]  Sébastien Marcel,et al.  Hand gesture recognition using input-output hidden Markov models , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[10]  Anup Basu,et al.  Visual gesture recognition for ground air traffic control using the Radon transform , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Gordon Cheng,et al.  Real-time stereo facial feature tracking: mimicking human mouth movement on a humanoid robot head , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[12]  Vladimir Pavlovic,et al.  Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Lars Bretzner,et al.  Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[14]  Katsu Yamane,et al.  Optical motion capture system with pan-tilt camera tracking and real time data processing , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).