DocumentCode
2044464
Title
Epipolar Spaces for Active Binocular Vision Systems
Author
Monaco, James ; Bovik, Alan C. ; Cormack, Lawrence K.
Author_Institution
Univ. of Texas at Austin, Austin
Volume
6
fYear
2007
fDate
Sept. 16 2007-Oct. 19 2007
Abstract
Depth recovery for active binocular vision systems is simplified if the camera geometry is known and corresponding points can be restricted to epipolar lines. Unfortunately, computation of epipolar lines requires calibration which can be complex and inaccurate. While it is possible to register images without geometric information, such unconstrained algorithms are usually time consuming and prone to error. In this paper we propose a compromise. Even without the instantaneous knowledge of the system geometry, we can restrict the region of correspondence by imposing limits on the possible range of configurations, and as a result, confine our search for matching points to epipolar spaces. For each point in one image, we define the corresponding epipolar space in the other image as the union of all associated epipolar lines over all possible system geometries. Epipolar spaces eliminate the need for calibration at the cost of an increased search region.
Keywords
cameras; image matching; image registration; active binocular vision systems; calibration; camera geometry; epipolar lines; epipolar spaces; system geometry; Calibration; Cameras; Computational geometry; Costs; Data mining; Geometrical optics; Image registration; Machine vision; Registers; Stereo vision; Active vision; Image registration; Stereo vision;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing, 2007. ICIP 2007. IEEE International Conference on
Conference_Location
San Antonio, TX
ISSN
1522-4880
Print_ISBN
978-1-4244-1437-6
Electronic_ISBN
1522-4880
Type
conf
DOI
10.1109/ICIP.2007.4379643
Filename
4379643
Link To Document