Novel Human Action Recognition in RGB-D Videos Based on Powerful View Invariant Features Technique.
Sebastien MambouOndrej KrejcarKamil KucaAli SelamatPublished in: ACIIDS (Extended Posters) (2018)
Keyphrases
- action recognition
- invariant features
- spatio temporal interest points
- human activities
- human actions
- static images
- human object interactions
- motion history images
- action classification
- recognition of human actions
- motion capture data
- video dataset
- activity recognition
- bag of words
- recognizing human actions
- recognizing actions
- view invariant
- depth cameras
- action detection
- computer vision
- action recognition in videos
- space time interest points
- image matching
- keypoints
- human pose
- body parts
- texture images
- shape features
- spatio temporal
- object segmentation
- d objects
- depth data
- multiple views
- video data
- image classification