3D rigid pose tracking based on new distance function of line segments

Langming Zhou; Lihua Xiao; Jiedong Wang; Han Yu

doi:10.1117/12.2540195

14 August 2019 3D rigid pose tracking based on new distance function of line segments

Langming Zhou, Lihua Xiao, Jiedong Wang, Han Yu

Proceedings Volume 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019); 111794L (2019) https://doi.org/10.1117/12.2540195
Event: Eleventh International Conference on Digital Image Processing (ICDIP 2019), 2019, Guangzhou, China

Abstract

To track and estimate the pose of known rigid objects efficiently in complex environment, we propose a method based on 3D particle filter (PF) with M-estimation optimization. A similarity observation model is put forward according to a new distance function of line segments firstly; secondly, the correspondences between 3D-2D line segments are obtained based on the tracking results of PF. Then, the pose is optimized using M-estimation to minimize the objective function defined according to our new distance metric which integrating the midpoint distance. Finally, the optimized particles are fused into the PF framework according to the importance sampling theory. Experiments indicate that the proposed method can effectively track and accurately estimate the pose of freely moving objects in unconstrained environment. Comparisons on synthetic images demonstrate that our method greatly outperforms the state-of-art method in accuracy and efficiency.

Citation Download Citation

Langming Zhou, Lihua Xiao, Jiedong Wang, and Han Yu "3D rigid pose tracking based on new distance function of line segments", Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 111794L (14 August 2019); https://doi.org/10.1117/12.2540195

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available