论文信息 - Human Sign Recognition for Robot Manipulation

Human Sign Recognition for Robot Manipulation

This paper addresses the problem of recognizing signs generated by a person to guide a robot. The proposed method is based on video color analysis of a moving person making signs. The analysis consists of segmentation of the middle body, arm and forearm location and recognition of the arm and forearm positions. The proposed method was experimentally tested on videos with different target colors and illumination conditions. Quantitative evaluations indicate 97.76% of correct detection of the signs in 1807 frames.

Mario Ignacio Chacon Murguia | Rafael Sandoval-Rodriguez | Javier Vega-Pineda | Leonardo Saldivar-Piñon

[1] Oliver Schreer,et al. Real-time 3d arm pose estimation from monocular video for enhanced HCI , 2008, VNBA '08.

[2] J. V. Draper. Teleoperator hand controllers: A contextual human factors assessment , 1994 .

[3] Seong-Whan Lee,et al. Gesture Spotting and Recognition for Human–Robot Interaction , 2007, IEEE Transactions on Robotics.

[4] Roger Clarke,et al. Asimov's Laws of Robotics: Implications for Information Technology - Part 2 , 1993, Computer.

[5] Patrick Horain,et al. 3D model based gesture acquisition using a single camera , 2002, Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings..

[6] Robert A. Meyers,et al. Encyclopedia of Complexity and Systems Science , 2009 .

[7] Mahmoud Tarokh,et al. Vision Based Person Tracking and Following in Unstructured Environments , 2008 .

[8] Takashi Morie,et al. Face and arm-posture recognition for secure human-machine interaction , 2008, 2008 IEEE International Conference on Systems, Man and Cybernetics.

[9] Jean J. Saade,et al. Fuzzy Inference-Based Person-Following Robot , 2008 .

[10] Hsuan-Sheng Chen,et al. Human action recognition using star skeleton , 2006, VSSN '06.

[11] Matheen Siddiqui,et al. Robust real-time upper body limb detection and tracking , 2006, VSSN '06.