0
Research Papers

Poisson Mesh Reconstruction for Accurate Object Tracking With Low-Fidelity Point Clouds

[+] Author and Article Information
Timothy Garrett

Virtual Reality Applications Center,
Iowa State University,
Ames, IA 50011
e-mail: garrettt@iastate.edu

Saverio Debernardis

Department of Mechanics,
Mathematics and Management,
Politecnico di Bari,
Bari 70126, Italy
e-mail: saverio.debernardis@poliba.it

James Oliver

Fellow ASME
Professor
Virtual Reality Applications Center,
Iowa State University,
Ames, IA 50011
e-mail: oliver@iastate.edu

Rafael Radkowski

Mem. ASME
Assistant Professor
Virtual Reality Applications Center,
Iowa State University,
Ames, IA 50011
e-mail: rafael@iastate.edu

Contributed by the Design Engineering Division of ASME for publication in the JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING. Manuscript received October 6, 2015; final manuscript received July 25, 2016; published online November 7, 2016. Editor: Bahram Ravani.

J. Comput. Inf. Sci. Eng 17(1), 011003 (Nov 07, 2016) (9 pages) Paper No: JCISE-15-1319; doi: 10.1115/1.4034324 History: Received October 06, 2015; Revised July 25, 2016

Tracking refers to a set of techniques that allows one to calculate the position and orientation of an object with respect to a global reference coordinate system in real time. A common method for tracking with point clouds is the iterative closest point (ICP) algorithm, which relies on the continuous matching of sequential sampled point clouds with a reference point cloud. Modern commodity range cameras provide point cloud data that can be used for that purpose. However, this point cloud data is generally considered as low-fidelity and insufficient for accurate object tracking. Mesh reconstruction algorithms can improve the fidelity of the point cloud by reconstructing the overall shape of the object. This paper explores the potential for point cloud fidelity improvement via the Poisson mesh reconstruction (PMR) algorithm and compares the accuracy with a common ICP-based tracking technique and a local mesh reconstruction operator. The results of an offline simulation are promising.

FIGURES IN THIS ARTICLE
<>
Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Iterations to minimize the distance between a reference object P and an environment point cloud X

Grahic Jump Location
Fig. 2

The matching process

Grahic Jump Location
Fig. 3

Fidelity of the reproduced mesh in comparison to the regular point cloud

Grahic Jump Location
Fig. 4

The main desktop of the simulation tool which has been used for testing

Grahic Jump Location
Fig. 5

Test objects for the analysis: (a) a gear switch, (b) an axial piston motor, (c) valves, (d) the Stanford bunny model, (e) dragon model, and (f) Happy Buddha

Grahic Jump Location
Fig. 6

Matching results for the objects in Figs. 5(a)5(c)

Grahic Jump Location
Fig. 7

Matching results for the objects in Figs. 5(d)5(f)

Grahic Jump Location
Fig. 8

(a) The reference model for the gear switch and (b) the reference model for the piston motor

Grahic Jump Location
Fig. 9

Mean squared error for ICP with and without mesh generation

Grahic Jump Location
Fig. 10

Number of Iterations for ICP with and without mesh generation

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In