Translator Disclaimer
27 January 2010 Construction and exploitation of a 3D model from 2D image features
Author Affiliations +
Proceedings Volume 7533, Computational Imaging VIII; 75330J (2010)
Event: IS&T/SPIE Electronic Imaging, 2010, San Jose, California, United States
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.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Karl Ni, Zachary Sun, Nadya Bliss, and Noah Snavely "Construction and exploitation of a 3D model from 2D image features", Proc. SPIE 7533, Computational Imaging VIII, 75330J (27 January 2010);


Illumination invariant 3D change detection
Proceedings of SPIE (March 07 2014)
3D reconstruction based on light field images
Proceedings of SPIE (April 10 2018)
Study of RGB D point cloud registration method guided by...
Proceedings of SPIE (November 15 2018)
Error estimation of 3D reconstruction from image sequences
Proceedings of SPIE (October 09 2009)

Back to Top