Definition and recovery of kinematic features for recognition of American sign language movements
Image and Vision Computing
Segmentation and Tracking for Vision Based Human Robot Interaction
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 03
Robotic navigation in crowded environments: key challenges for autonomous navigation systems
PerMIS '08 Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems
Multi-layered hand and face tracking for real-time gesture recognition
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Hi-index | 0.00 |
This paper, aiming at real-time gesture-controlled interaction, describes visual modeling, analysis, and recognition of continuous dynamic hand gestures. By hierarchically integrating multiple cues, a spatio-temporal appearance model and novel approaches are proposed for modeling and analysis of dynamic gestures respectively. At low level, fusion of flesh chrominance analysis and coarse image motion detection is employed to detect and segment hand gestures; at high level, parameters of the spatio-temporal appearance model are recovered by combining robust parameterized image motion estimation and hand shape analysis. The approach, therefore, fulfills real-time processing as well as high recognition rates. Without resorting to any special marks, twelve kinds of hand gestures can be recognized with average accuracy over 89%. A prototype system, gesture-controlled panoramic map browser, is designed and implemented to demonstrate the usability of gesture-controlled interaction.