0
TECHNICAL PAPERS

A Comprehensive Tool for Recovering 3D Models From 2D Photos With Wide Baselines

[+] Author and Article Information
Yuzhu Lu

 Iowa State University, Virtual Reality Applications Center, Human Computer Interaction Program, Department of Agricultural Biosystem Engineering, 1620 Howe Hall, Ames, IA 50011-2274yuzhu@iatate.edu

Shana Smith

 Iowa State University, Virtual Reality Applications Center, Human Computer Interaction Program, Department of Agricultural Biosystem Engineering, 1620 Howe Hall, Ames, IA 50011-2274sssmith@iastate.edu

J. Comput. Inf. Sci. Eng 6(4), 372-380 (Jul 18, 2006) (9 pages) doi:10.1115/1.2353855 History: Received September 15, 2005; Revised July 18, 2006

Recovering 3D objects from 2D photos is an important application in the areas of computer vision, computer intelligence, feature recognition, and virtual reality. This paper describes an innovative and systematic method that integrates automatic feature extraction, automatic feature matching, manual revision, feature recovery, and model reconstruction into an effective and integrated 3D object recovery tool. The proposed method is a convenient and inexpensive way to recover 3D scenes and models directly from 2D photos. New automatic key-point selection and hierarchical matching algorithms were developed for matching 2D photos with wide baselines. The method uses a universal camera intrinsic matrix estimation technique to eliminate the need for camera calibration experiments. A new automatic texture-mapping algorithm was also developed for finding the best textures in 2D photos. The paper includes some examples and results to show the capabilities of the new method.

FIGURES IN THIS ARTICLE
<>
Copyright © 2006 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Epipolar geometry

Grahic Jump Location
Figure 2

Process of feature segment extraction. (a) Original image. (b) Edge detection. (c) Segment extraction.

Grahic Jump Location
Figure 3

Process of background noise filtering. (a) Original image. (b) Segment extraction. (c) Features kept after noise filtering.

Grahic Jump Location
Figure 4

Hierarchical matching algorithm

Grahic Jump Location
Figure 5

First indices for P1 and P2—relative position. (a) Relative position of P1. (b) Relative position of P2.

Grahic Jump Location
Figure 6

Matching result comparison. (a) Proposed matching algorithm. (b) Classical cross correlation algorithm.

Grahic Jump Location
Figure 7

Camera focal length analysis for 21 research studies. (a) Histogram with normal curve. (b)Q-Q plot.

Grahic Jump Location
Figure 8

Several parameters were defined to evaluate the precision of recovered results

Grahic Jump Location
Figure 9

Reconstruction with texture mapping

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