PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition.
Shenglin HeXiaoyang QuJiguang WanGuokuan LiChangsheng XieJianzong WangPublished in: CoRR (2024)
Keyphrases
- action recognition
- point cloud
- real time
- point cloud data
- human actions
- structure from motion
- activity recognition
- computer vision
- action classification
- depth cameras
- laser scanner
- surface reconstruction
- recognition of human actions
- recognizing human actions
- point sets
- stereo camera
- recognizing actions
- three dimensional
- body parts
- high quality
- hough transform
- optical flow
- action recognition in videos