An adaptive hidden Markov model-based gesture recognition approach using Kinect to simplify large-scale video data processing for humanoid robot imitation.
Ing-Jr DingChe-Wei ChangPublished in: Multim. Tools Appl. (2016)
Keyphrases
- gesture recognition
- humanoid robot
- data processing
- human robot interaction
- kinect sensor
- depth cameras
- imitation learning
- depth data
- motion planning
- biologically inspired
- human computer interaction
- sign language recognition
- hidden markov models
- multi modal
- motion capture
- hand gesture recognition
- hand gestures
- video sequences
- video data
- data management
- sign language
- human machine interface
- real time
- joint space
- video images
- hand motion
- depth information
- human motion
- point cloud
- depth map
- sign recognition
- sensory feedback
- dynamic scenes
- human actions
- high dimensional
- reinforcement learning
- image sequences