Selected Readings in Vision and Graphics
edited by Luc Van Gool, Gábor Székely, Markus Gross, Bernt Schiele

Volume 56

Herbert Bay


From Wide-baseline Point and Line Correspondences to 3D.

2009. XVI, 186 pages. EUR 64,00. ISBN-10: 3-86628-292-3

ISBN-13: 978-3-86628-292-6



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

Reihe " Selected Readings in Vision and Graphics " im Hartung-Gorre Verlag

Direkt bestellen bei / to order directly from:

Hartung-Gorre Verlag / D-78465 Konstanz / Germany

Telefon: +49 (0) 7533 97227 Telefax: +49 (0) 7533 97228