6D Pose Estimation with Combined Deep Learning and 3D Vision Techniques for a Fast and Accurate Object Grasping.
Tuan-Tang LeTrung-Son LeYu-Ru ChenJoel VidalChyi-Yeu LinPublished in: CoRR (2021)
Keyphrases
- deep learning
- vision system
- human hand
- unsupervised learning
- unsupervised feature learning
- machine learning
- articulated objects
- computer vision
- d objects
- moving objects
- object model
- multiple objects
- weakly supervised
- pattern recognition
- video sequences
- deep architectures
- viewpoint
- pose estimation
- target object
- mental models
- data mining