CHI '93 Proceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in Computing Systems
Real-time inverse kinematics techniques for anthropomorphic limbs
Graphical Models and Image Processing
Synthesis of Hand-Arm Gestures
Proceedings of Gesture Workshop on Progress in Gestural Interaction
Virtual Human Animation Based on Movement Observation and Cognitive Behavior Models
CA '99 Proceedings of the Computer Animation
3-D model-based tracking of humans in action: a multi-view approach
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Style-based inverse kinematics
ACM SIGGRAPH 2004 Papers
ACM SIGGRAPH 2005 Papers
Inverse kinematics for reduced deformable models
ACM SIGGRAPH 2006 Papers
A System to Make Signs Using Collaborative Approach
ICCHP '08 Proceedings of the 11th international conference on Computers Helping People with Special Needs
Full-body performance animation with Sequential Inverse Kinematics
Graphical Models
Toward automatic sign language recognition from web3D based scenes
ICCHP'10 Proceedings of the 12th international conference on Computers helping people with special needs
| Hi-index | 0.00 |
Starting from the study of different methods of animations we introduce a new animation approach that ensures real-time generation of the virtual character postures. The main goal of this paper is the description of an inverse kinematics approach for animating avatar that allows the automatic moving of the different articulations of a signing avatar body in order to obtain a realistic animation of the virtual character. And so enable deaf person to visualize signs. Our approach is based on a thorough study of sign language and gestures classification. We identified the main constraints that need to be used for the automatic generation postures in sign language. To further facilitate editing, a graphical interface had been developed. The challenge of this project is to find the tradeoff between computational time and realistic representation that must be closer to real-time generation signs.