Multi-view image registration for wide-baseline visual sensor networks. Caner, G., Tekalp, A. M., Sharma, G., & Heinzelman, W. In 2006 IEEE International Conference on Image Processing, ICIP 2006, Proceedings, of IEEE International Conference on Image Processing (ICIP), pages 369-372, 2006. IEEE. IEEE International Conference on Image Processing (ICIP 2006), Atlanta, GA, OCT 08-11, 2006
doi  abstract   bibtex   
We present a new dense multi-view registration technique for wide-baseline video/images that integrates a parametric optical flow-based approach with a sparse set of feature correspondences, based on a locally planar approximation of a nonplanar scene. The proposed method can deal with illuminance variations between the views, which is critically important for wide-baseline applications. It differs from existing work on wide-baseline image registration in that it requires only image information and provides dense matching without computing any camera calibration matrices or performing any prior scene segmentation. These characteristics render the method suitable for practical deployment in visual sensor networks, towards which the current work is directed. We demonstrate the performance of the proposed method on simulated multi-view images of a virtual 3D world composed of piece-wise smooth textured surfaces, as well as real wide-baseline images of nonplanar textured surfaces.
@inproceedings{ ISI:000245768500093,
Author = {Caner, Gulcin and Tekalp, A. Murat and Sharma, Gaurav and Heinzelman,
   Wendi},
Book-Group-Author = {{IEEE}},
Title = {{Multi-view image registration for wide-baseline visual sensor networks}},
Booktitle = {{2006 IEEE International Conference on Image Processing, ICIP 2006,
   Proceedings}},
Series = {{IEEE International Conference on Image Processing (ICIP)}},
Year = {{2006}},
Pages = {{369-372}},
Note = {{IEEE International Conference on Image Processing (ICIP 2006), Atlanta,
   GA, OCT 08-11, 2006}},
Organization = {{IEEE}},
Abstract = {{We present a new dense multi-view registration technique for
   wide-baseline video/images that integrates a parametric optical
   flow-based approach with a sparse set of feature correspondences, based
   on a locally planar approximation of a nonplanar scene. The proposed
   method can deal with illuminance variations between the views, which is
   critically important for wide-baseline applications. It differs from
   existing work on wide-baseline image registration in that it requires
   only image information and provides dense matching without computing any
   camera calibration matrices or performing any prior scene segmentation.
   These characteristics render the method suitable for practical
   deployment in visual sensor networks, towards which the current work is
   directed. We demonstrate the performance of the proposed method on
   simulated multi-view images of a virtual 3D world composed of piece-wise
   smooth textured surfaces, as well as real wide-baseline images of
   nonplanar textured surfaces.}},
DOI = {{10.1109/ICIP.2006.313170}},
ISSN = {{1522-4880}},
ISBN = {{978-1-4244-0481-0}},
ResearcherID-Numbers = {{Sharma, Gaurav/A-1154-2007}},
ORCID-Numbers = {{Sharma, Gaurav/0000-0001-9735-9519}},
Unique-ID = {{ISI:000245768500093}},
}

Downloads: 0