Turkish Sign Language recognition using spatio-temporal features on Kinect RGB video sequences and depth maps.
Abbas MemisSongul AlbayrakPublished in: SIU (2013)
Keyphrases
- sign language
- depth data
- depth map
- video sequences
- gesture recognition
- image sequences
- depth information
- depth cameras
- multi view
- d scene
- three dimensional
- hand gestures
- high quality
- sign recognition
- depth estimation
- stereo matching
- depth images
- motion estimation
- hidden markov models
- frame rate
- dynamic scenes
- object tracking
- camera motion
- visual tracking
- video frames
- view synthesis
- high resolution
- input image
- video data
- human computer interaction
- range data
- video camera
- color information
- dense depth maps
- color space
- space time
- pose estimation
- input data
- color images
- human motion
- stereo camera
- low resolution
- super resolution
- time of flight
- motion model
- multiple views
- facial expressions
- optical flow
- user interface