期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 37, 期 5, 页码 1328-1342出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2021.3056043
关键词
Pose estimation; Tracking; Uncertainty; Solid modeling; Training; Task analysis; Target tracking; Computer vision; state estimation; 6-D object pose tracking
类别
The PoseRBPF method proposed in this article efficiently estimates the pose of an object by decoupling 3-D rotation and 3-D translation in the Rao-Blackwellized particle filtering framework. By discretizing the rotation space in a fine-grained manner, training an autoencoder network, and constructing a codebook of feature embeddings, it can track objects with arbitrary symmetries.
Tracking 6-D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this article, we formulate the 6-D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3-D rotation and the 3-D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF, to efficiently estimate the 3-D translation of an object along with the full distribution over the 3-D rotation. This is achieved by discretizing the rotation space in a fine-grained manner and training an autoencoder network to construct a codebook of feature embeddings for the discretized rotations. As a result, PoseRBPF can track objects with arbitrary symmetries while still maintaining adequate posterior distributions. Our approach achieves state-of-the-art results on two 6-D pose estimation benchmarks. We open-source our implementation at https://github.com/NVlabs/PoseRBPF.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据