Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures
Name
1603.04868.pdf
Description
Submitted version
Size
3.62 MB
Format
Adobe PDF
Checksum (MD5)
c1505b19220a934457f56a589c87e450
Author(s)
Straub, Julian
Campbell, Trevor
How, Jonathan P.
Fisher, John W.
Date Issued
July 2017
Publisher
IEEE
Citation
Straub, Julian, Campbell, Trevor, How, Jonathan P. and Fisher, John W. 2017. "Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures."
Version
Original manuscript
Abstract
© 2017 IEEE. Point cloud alignment is a common problem in computer vision and robotics, with applications ranging from 3D object recognition to reconstruction. We propose a novel approach to the alignment problem that utilizes Bayesian non-parametrics to describe the point cloud and surface normal densities, and branch and bound (BB) optimization to recover the relative transformation. BB uses a novel, refinable, near-uniform tessellation of rotation space using 4D tetrahedra, leading to more efficient optimization compared to the common axis-angle tessellation. We provide objective function bounds for pruning given the proposed tessellation, and prove that BB converges to the optimum of the cost function along with providing its computational complexity. Finally, we empirically demonstrate the efficiency of the proposed approach as well as its robustness to real-world conditions such as missing data and partial overlap.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Aerospace Controls Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/cvpr.2017.258
