View-Invariant 3D Action Recognition Using Spatiotemporal Self-Similarities from Depth Camera.
Areum LeeHeung-Il SukSeong-Whan LeePublished in: ICPR (2014)
Keyphrases
- view invariant
- depth cameras
- action recognition
- cross view action recognition
- human actions
- gesture recognition
- multi view
- single view
- depth map
- spatio temporal
- activity recognition
- space time
- depth information
- depth images
- viewpoint
- human motion
- three dimensional
- moving objects
- computer vision
- human activities
- multiple viewpoints
- video sequences
- highly accurate
- d scene
- human body
- model fitting
- hidden markov models
- depth data