PoseViNet: Distracted Driver Action Recognition Framework Using Multi-View Pose Estimation and Vision Transformer.
Neha SengarIndra KumariJihui LeeDongsoo HarPublished in: CoRR (2023)
Keyphrases
- multi view
- pose estimation
- action recognition
- computer vision
- human pose
- d objects
- body parts
- view invariant
- multiple cameras
- single view
- human body
- multiple views
- camera calibration
- human actions
- visual hull
- activity recognition
- depth map
- shape from silhouettes
- motion capture
- camera parameters
- human motion
- semi supervised
- human detection
- viewpoint
- object recognition
- vision system
- feature points
- bundle adjustment
- camera views
- pose parameters
- multiple viewpoints
- three dimensional
- dynamic scenes
- machine learning
- depth images
- view synthesis