Monocular 3D Reconstruction of Human Motion in Long Action Sequences.
Gareth LoyMartin ErikssonJosephine SullivanStefan CarlssonPublished in: ECCV (4) (2004)
Keyphrases
- human motion
- human actions
- action sequences
- image sequences
- view invariant
- human pose
- motion capture data
- motion capture
- articulated human motion
- human body
- spatio temporal
- video sequences
- motion recognition
- body parts
- three dimensional
- motion sequences
- computer vision
- action recognition
- body pose
- real time
- visual data
- pose estimation
- motion segmentation
- projective geometry
- plan recognition
- initial state
- optical flow
- machine learning