Construction and exploitation of a 3D model from 2D image features

Karl Ni, Zachary Sun, Nadya Bliss, Noah Snavely

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations


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.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Computational Imaging VIII
StatePublished - 2010
Externally publishedYes
EventComputational Imaging VIII - San Jose, CA, United States
Duration: Jan 18 2010Jan 19 2010

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X


OtherComputational Imaging VIII
Country/TerritoryUnited States
CitySan Jose, CA


  • Bundle adjustment
  • Object detection
  • Registration
  • Structure from motion

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Construction and exploitation of a 3D model from 2D image features'. Together they form a unique fingerprint.

Cite this