Omnidirectional Vision Systems, 2013
Calibration, Feature Extraction and 3D Information
SpringerBriefs in Computer Science Series

This work focuses on central catadioptric systems, from the early step of calibration to high-level tasks such as 3D information retrieval. The book opens with a thorough introduction to the sphere camera model, along with an analysis of the relation between this model and actual central catadioptric systems. Then, a new approach to calibrate any single-viewpoint catadioptric camera is described.  This is followed by an analysis of existing methods for calibrating central omnivision systems, and a detailed examination of hybrid two-view relations that combine images acquired with uncalibrated central catadioptric systems and conventional cameras. In the remaining chapters, the book discusses a new method to compute the scale space of any omnidirectional image acquired with a central catadioptric system, and a technique for computing the orientation of a hand-held omnidirectional catadioptric camera.

Modeling Omnidirectional Vision Systems

Calibration of Omnidirectional Cameras Using a DLT-Like Approach

Comparison of Calibration Methods for Omnidirectional Cameras

Two-View Relations Between Omnidirectional and Conventional Cameras

Generic Scale Space for a Camera Invariant Feature Extractor

Orientation of a Hand-Held Catadioptric System in Man-Made Environments

Conclusions

Presents the first linear method to calibrate all central projection systems and fisheye cameras

Introduces a generic approach to obtain the scale space of any central projection system, by combining the Riemannian geometry with the sphere camera model

Explores the role of hybrid two-view relations to construct robust matching approaches

Examines the problem of extracting conics from catadioptric images that represent the projections of straight lines

Includes supplementary material: sn.pub/extras