Single-Image 3D Pose Estimation for Texture-Less Object via Symmetric Prior

Xiaoyuan REN  Libing JIANG  Xiaoan TANG  Junda ZHANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.7   pp.1972-1975
Publication Date: 2018/07/01
Publicized: 2018/04/10
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8014
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
3D,  pose estimation,  priori-knowledge,  texture-less object,  

Full Text: PDF(429KB)>>
Buy this Article

Extracting 3D information from a single image is an interesting but ill-posed problem. Especially for those artificial objects with less texture such as smooth metal devices, the decrease of object detail makes the problem more challenging. Aiming at the texture-less object with symmetric structure, this paper proposes a novel method for 3D pose estimation from a single image by introducing implicit structural symmetry and context constraint as priori-knowledge. Firstly, by parameterized representation, the texture-less object is decomposed into a series of sub-objects with regular geometric primitives. Accordingly, the problem of 3D pose estimation is converted to a parameter estimation problem, which is implemented by primitive fitting algorithm. Then, the context prior among sub-objects is introduced for parameter refinement via the augmentedLagrange optimization. The effectiveness of the proposed method is verified by the experiments based on simulated and measured data.