Information Technology Reference
In-Depth Information
Chapter 1
Catadioptric Stereo with Planar Mirrors:
Multiple-view Geometry and
Camera Localization
Gian Luca Mariottini, Stefano Scheggi, Fabio Morbidi, and Domenico Prattichizzo
Abstract. Planar catadioptric stereo (PCS) vision sensors consist of a pinhole cam-
era and two or more planar mirrors. PCS systems have recently received an increas-
ing attention in computer vision and have a promising applicability in robotics,
since the use of mirrors allows to obtain a stereo view without the need of exact
multi-camera synchronization and stereo calibration. The chapter presents a rigor-
ous analytical treatment of the imaging geometry of PCS sensors and introduce new
multiple-view properties that are instrumental in addressing the camera localization
problem. Original results on mirror calibration are also provided. Extensive simu-
lation and real-data experiments conducted with an eye-in-hand robot illustrate the
theory and show the effectiveness of the proposed designs.
1.1
Introduction
In this section we present the motivation for this work, review the related literature,
list the original contributions and briefly illustrate the organization of the chapter.
1.1.1
Motivation and Related Works
Stereoscopic vision has been playing a key role in many fields, such as, e.g. ,3D
imaging for entertainment and mapping, medicine, industrial robotics, augmented
reality [13, 11]. Standard stereo sensors are composed of two coupled pinhole cam-
eras and are generally expensive and difficult to calibrate. In addition, the limited
field of view considerably limits their application range. To alleviate this problem,
Search WWH ::




Custom Search