TY - GEN
T1 - Construction and exploitation of a 3D model from 2D image features
AU - Ni, Karl
AU - Sun, Zachary
AU - Bliss, Nadya
AU - Snavely, Noah
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
KW - Bundle adjustment
KW - Object detection
KW - Registration
KW - Structure from motion
UR - http://www.scopus.com/inward/record.url?scp=77952045825&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77952045825&partnerID=8YFLogxK
U2 - 10.1117/12.849919
DO - 10.1117/12.849919
M3 - Conference contribution
AN - SCOPUS:77952045825
SN - 9780819479266
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Proceedings of SPIE-IS and T Electronic Imaging - Computational Imaging VIII
T2 - Computational Imaging VIII
Y2 - 18 January 2010 through 19 January 2010
ER -