Indoor robot 3D scene reconstruction optimization using planar features

Zhongyuan Lv; Jia Zheng; Yang Liu

doi:10.1117/12.2244965

29 August 2016 Indoor robot 3D scene reconstruction optimization using planar features

Zhongyuan Lv, Jia Zheng, Yang Liu

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100335V (2016) https://doi.org/10.1117/12.2244965
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

At present, g²o (general graph optimization) is the main method of reducing the accumulated errors of point cloud registration, an important step of 3D scene reconstruction. However, the huge amount of point cloud data produced in the application process leads to the failure of meeting real -time request. Since cuboid is the most common indoor geometric structure of buildings , this paper presents an optimization method using planar features of point cloud. We rapidly extract the planes from point cloud and modify the transfer matrix of pair point c louds based on planar rotation. Results show that, by regulating down sampling threshold, the treatment time of each frame of point cloud data can be approximately shortened to 1.8486s in comparison of 3.08683s by g²o. Besides, the algorism ensures the matching effect and thus has strong robustness.

Citation Download Citation

Zhongyuan Lv, Jia Zheng, and Yang Liu "Indoor robot 3D scene reconstruction optimization using planar features", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100335V (29 August 2016); https://doi.org/10.1117/12.2244965

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