Synergetic reconstruction from 2D pose and 3D motion for wide-space multi-person video motion capture in the wild.
Takuya OhashiYosuke IkegamiYoshihiko NakamuraPublished in: Image Vis. Comput. (2020)
Keyphrases
- motion capture
- monocular video sequences
- human figure
- video sequences
- pose tracking
- human motion
- video frames
- space time
- articulated human motion
- human body
- motion capture data
- three dimensional
- multi view
- human computer interaction
- human motion capture data
- body pose
- non rigid structure from motion
- video data
- computer animation
- image sequences
- computer graphics
- human motion capture
- face tracking
- pose estimation
- low dimensional
- joint angles
- human pose
- human actions
- image processing
- visual data
- d objects
- multimedia
- markerless
- body parts
- high resolution
- optical flow
- position and orientation
- humanoid robot
- motion parameters
- machine learning
- motion model
- moving objects