3D skeleton-based action recognition by representing motion capture sequences as 2D-RGB images.
Sohaib LarabaMohammed BrahimiJoëlle TilmanneThierry DutoitPublished in: Comput. Animat. Virtual Worlds (2017)
Keyphrases
- action recognition
- human motion capture data
- motion capture
- motion capture data
- static images
- human motion
- computer graphics
- human actions
- activity recognition
- computer vision
- human body
- motion history images
- bag of words
- input image
- human detection
- action classification
- image classification
- image features
- body parts
- recognizing human actions
- image retrieval
- object recognition
- three dimensional
- human computer interaction
- virtual environment
- human activities
- visual data
- video sequences
- image processing