ConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and Pseudocoloring.
Pichao WangWanqing LiZhimin GaoChang TangJing ZhangPhilip OgunbonaPublished in: ACM Multimedia (2015)
Keyphrases
- action recognition
- depth cameras
- depth map
- depth sensors
- depth data
- depth information
- human actions
- time of flight
- virtual view
- multi view
- computer vision
- body parts
- real scenes
- high quality
- stereo camera
- view synthesis
- depth images
- d scene
- stereo matching
- gesture recognition
- image sequences
- three dimensional
- image processing