Readings in Vision and Graphics
edited by Luc Van Gool, Gábor Székely, Markus Gross, Bernt Schiele
From Wide-baseline Point and Line Correspondences to 3D.
2009. XVI, 186 pages. EUR 64,00. ISBN-10: 3-86628-292-3
This book discusses the problem of point and line segment
correspondences between two images taken under wide-baseline
conditions for the particular application of automatic 3D reconstruction.
First, we present the well-known SURF (Speeded Up Robust Features) algorithm and show its performance compared to other state-of-the-art detection/descriptor scheme on a benchmark dataset.
Second, we introduce a wide-baseline line segment matching algorithm. It shows how the position of a line segment with respect to the others is used to filter mismatches and to increase the number of correct matches in an iterative manner.
The third and last part of this book shows how the two methods for image correspondances are used for automatic camera calibration and 3D modelling from two wide-baseline images.
About the author:
Herbert Bay holds a PhD in Computer Vision Studies from the ETH Zurich, the
Swiss Federal Institute of Technology in Zürich and a Masters Degree in
Microengineering from the EPFL, the Swiss Federal Institute of Technology
in Lausanne. After graduating from the EPFL in 2002, with several
scientific publications to his name, he started his career at IBM
Switzerland in Zurich. In 2003, Herbert Bay undertook a PhD at the
Computer Vision Lab of the ETH Zurich. During the course of his research,
he published numerous scientific publications, developed the renown SURF
algorithm, and registered two patents. After completing his PhD in 2006, he
co-founded the startup company kooaba.
Keywords / Schlagwörter: Wide-baseline Point, Line Correspondences, 3D reconstruction
Direkt bestellen bei / to order directly from: Hartung.Gorre@t-online.de
Hartung-Gorre Verlag / D-78465 Konstanz / Germany
Telefon: +49 (0) 7533 97227 Telefax: +49 (0) 7533 97228