Robust human action recognition based on depth motion maps and improved convolutional neural network.
Linqin CaiXiaolin LiuFuli ChenMin XiangPublished in: J. Electronic Imaging (2018)
Keyphrases
- action recognition
- human movements
- static images
- human motion capture data
- motion capture data
- view invariant
- convolutional neural network
- motion history images
- recognizing human actions
- recognition of human actions
- human actions
- depth sensors
- motion features
- action recognition in videos
- computer vision
- bag of words
- human activities
- activity recognition
- action primitives
- human detection
- action classification
- motion capture
- body parts
- depth cameras
- mid level
- human motion
- robust tracking
- image sequences
- motion analysis
- human activity recognition
- motion recognition
- neural network
- human pose
- bag of features
- depth map
- recognizing actions
- face detection
- human body
- motion estimation