Chinese Journal of Intelligent Science and Technology ›› 2022, Vol. 4 ›› Issue (2): 246-254.doi: 10.11959/j.issn.2096-6652.202227

• Special Topic: Autonomous Agent Learning for Dexterous and Accurate Manipulations • Previous Articles    

Category-level object pose estimation from depth point cloud

Renwu LI1,2, Lingxiao ZHANG1,2, Lin GAO1,2, Chunpeng LI1,2, Hao JIANG1,2   

  1. 1 Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
    2 University of Chinese Academy of Sciences, Beijing 100049, China
  • Online:2022-06-01 Published:2022-06-01
  • Supported by:
    The National Key Research and Development Program of China(2018AAA0103002);Science and Technology Service Network Initiative, CAS(KFJ-STS-QYZD-129)

Abstract:

Aiming at the problem of category-level object pose estimation, a method was proposed to accurately estimate the pose of the target object by only taking the point cloud scanned by the depth camera as the input, with knowing the category of input point cloud only.The method did not reply on a huge amount of labeled dataset, but used virtual data produced by simulation instead, which achieved better accuracy on real-world dataset.This method first filtered the background noise of the input point cloud.Then standardized the point cloud through the well-designed center prediction module.After that, the normalized object coordinate space would be estimated through a shape template deformation module.Finally, the pose would be obtained from least squares.Experiments on real-world dataset demonstrates that the method achieve higher accuracy and better generalization ability.

Key words: pose estimation, point cloud processing, deep learning, pattern recognition

CLC Number: 

No Suggested Reading articles found!