Title :
OpenGV: A unified and generalized approach to real-time calibrated geometric vision
Author :
Kneip, Laurent ; Furgale, Paul
Author_Institution :
CECS, Australian Nat. Univ., Canberra, ACT, Australia
fDate :
May 31 2014-June 7 2014
Abstract :
OpenGV is a new C++ library for calibrated realtime 3D geometric vision. It unifies both central and non-central absolute and relative camera pose computation algorithms within a single library. Each problem type comes with minimal and non-minimal closed-form solvers, as well as non-linear iterative optimization and robust sample consensus methods. OpenGV therefore contains an unprecedented level of completeness with regard to calibrated geometric vision algorithms, and it is the first library with a dedicated focus on a unified real-time usage of non-central multi-camera systems, which are increasingly popular in robotics and in the automotive industry. This paper introduces OpenGV´s flexible interface and abstraction for multi-camera systems, and outlines the performance of all contained algorithms. It is our hope that the introduction of this open-source platform will motivate people to use it and potentially also include more algorithms, which would further contribute to the general accessibility of geometric vision algorithms, and build a common playground for the fair comparison of different solutions.
Keywords :
C++ language; computer vision; iterative methods; pose estimation; public domain software; software libraries; C++ library; OpenGV; geometric vision algorithms; minimal closed-form solvers; multicamera system abstraction; noncentral multicamera systems; nonlinear iterative optimization; nonminimal closed-form solvers; open-source platform; real-time calibrated geometric vision; relative camera pose computation algorithms; robust sample consensus methods; Cameras; Computational modeling; Libraries; Real-time systems; Robots; Three-dimensional displays; Vectors;
Conference_Titel :
Robotics and Automation (ICRA), 2014 IEEE International Conference on
Conference_Location :
Hong Kong
DOI :
10.1109/ICRA.2014.6906582