Spatio-Temporal Pyramid Model based on depth maps for action recognition.
Haining XuEnqing ChenChengwu LiangLin QiLing GuanPublished in: MMSP (2015)
Keyphrases
- action recognition
- depth map
- human actions
- spatio temporal
- depth cameras
- view invariant
- input image
- image sequences
- action recognition in videos
- multi view
- depth information
- d scene
- recognition of human actions
- stereo matching
- three dimensional
- bag of words
- computer vision
- high quality
- activity recognition
- spatial and temporal
- depth data
- human detection
- body parts
- super resolution
- depth estimation
- stereo pair
- high resolution
- multiscale
- stereo camera
- view synthesis
- moving objects
- space time
- single view
- low resolution
- image processing
- time of flight
- stereo vision
- feature points
- multiple views
- optical flow