Efficient MSPSO Sampling for Object Detection and 6D Pose Estimation in 3D Scenes

Efficient MSPSO Sampling for Object Detection and 6D Pose Estimation in 3D Scenes

Xing, Xuejun (University of Chinese Academy of Sciences)
Guo, Jianwei (University of Chinese Academy of Sciences; Chinese Academy of Sciences)
Nan, L. (TU Delft Urban Data Science)
Gu, Qingyi (Chinese Academy of Sciences)
Zhang, Xiaopeng (Chinese Academy of Sciences)
Yan, Dong Ming (Chinese Academy of Sciences)

2022

The point pair feature (PPF) is widely used in industrial applications for estimating 6D poses of known objects from unrecognized point clouds. The key to the success of PPF matching is to establish correct 3D correspondences between the object and the scene, i.e., finding as many valid similar point pairs as possible. Thus, a set of reference points in the scene should be sampled and paired with other points in the scene to create point pair features. However, efficient sampling of scene point pairs has been overlooked in existing frameworks. The novelty of our approach is a new sampling algorithm for selecting scene reference points based on the multi-subpopulation particle swarm optimization (MSPSO) guided by a probability map. We also introduce an effective pose clustering and hypotheses verification method to obtain the optimal pose. Moreover, we optimize the progressive sampling for multi-frame point clouds to improve processing efficiency. The experimental results show that our method outperforms previous methods by 6.6%, 3.9% in terms of accuracy on the public DTU and LineMOD datasets, respectively. We further validate our approach by applying it in a real robot grasping task.

3D point cloud
6D pose estimation
Clustering algorithms
Deep learning
Image segmentation
Multi-subpopulation particle swarm optimization
Point pair features
Pose estimation
Robot kinematics
Robustness
Three-dimensional displays

http://resolver.tudelft.nl/uuid:bd7c5adc-ed48-48af-a867-5d1dce769acf

https://doi.org/10.1109/TIE.2021.3121721

2022-04-27

0278-0046

IEEE Transactions on Industrial Electronics, 69 (10), 10281-10291

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2022 Xuejun Xing, Jianwei Guo, L. Nan, Qingyi Gu, Xiaopeng Zhang, Dong Ming Yan