2012 | OriginalPaper | Chapter
Introduction
Authors : Javier Civera, Andrew J. Davison, José María Martínez Montiel
Published in: Structure from Motion using the Extended Kalman Filter
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
The fully automated 3D estimation of a scene and the 6 degrees of freedom camera motion using as the only input the images taken by the camera has been a long term aim in the computer vision community. The intense research in the latest decades has produced spectacular advances; the topic is already mature and most of its aspects are already well known. 3D vision has inmediate applications in many different fields, like robotics or augmented reality, and technological transfer is starting to be a reality. This book describes one of the first systems for sparse point-based 3D reconstruction and egomotion estimation from an image sequence; able to work in real-time at video rate in room-sized scenarios. This chapter introduces the main topics that will be detailed in the rest of the book, covering aspects like the point feature model, efficient and robust correspondences search, model selection for degenerate configurations and internal self-calibration.