Construction and exploitation of a 3D model from 2D image features
Name
Ni-2010-Construction and exploitation .pdf
Size
6 MB
Format
Adobe PDF
Checksum (MD5)
923c408195cef3bcbbbdfa2c88dd9a93
Author(s)
Bliss, Nadya T.
Sun, Zachary
Ni, Karl S.
Snavely, Noah
Date Issued
January 2010
Journal
Proceedings of SPIE--the International Society for Optical Engineering
Publisher
SPIE
Citation
Ni, Karl et al. “Construction and exploitation of a 3D model from 2D image features.” Computational Imaging VIII. Ed. Charles A. Bouman, Ilya Pollak, & Patrick J. Wolfe. San Jose, California, USA: SPIE, 2010. 75330J-10. ©201 SPIE.
Version
Final published version
Abstract
This paper proposes a trainable computer vision approach for visual object registration relative to a collection of training images obtained a priori. The algorithm first identifies whether or not the image belongs to the scene location, and should it belong, it will identify objects of interest within the image and geo-register them. To accomplish this task, the processing chain relies on 3-D structure derived from motion to represent feature locations in a proposed model. Using current state-of- the-art algorithms, detected objects are extracted and their two-dimensional sizes in pixel quantities are converted into relative 3-D real-world coordinates using scene information, homography, and camera geometry. Locations can then be given with distance alignment information. The tasks can be accomplished in an efficient manner. Finally, algorithmic evaluation is presented with receiver operating characteristics, computational analysis, and registration errors in physical distances.
MIT Department
Lincoln Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1117/12.849919
