Robust Three-View Triangulation Done Fast
2014 (English)In: Proceedings: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014, IEEE , 2014, 152-157 p.Conference paper (Refereed)
Estimating the position of a 3-dimensional world point given its 2-dimensional projections in a set of images is a key component in numerous computer vision systems. There are several methods dealing with this problem, ranging from sub-optimal, linear least square triangulation in two views, to finding the world point that minimized the L2-reprojection error in three views. This leads to the statistically optimal estimate under the assumption of Gaussian noise. In this paper we present a solution to the optimal triangulation in three views. The standard approach for solving the three-view triangulation problem is to find a closed-form solution. In contrast to this, we propose a new method based on an iterative scheme. The method is rigorously tested on both synthetic and real image data with corresponding ground truth, on a midrange desktop PC and a Raspberry Pi, a low-end mobile platform. We are able to improve the precision achieved by the closed-form solvers and reach a speed-up of two orders of magnitude compared to the current state-of-the-art solver. In numbers, this amounts to around 300K triangulations per second on the PC and 30K triangulations per second on Raspberry Pi.
Place, publisher, year, edition, pages
IEEE , 2014. 152-157 p.
, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, ISSN 2160-7508
Nonlinear optimization; Structure from motion; Three-view Triangulation; Cameras; Computer vision; Conferences; Noise; Polynomials; Robustness; Three-dimensional displays
Electrical Engineering, Electronic Engineering, Information Engineering Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:liu:diva-111512DOI: 10.1109/CVPRW.2014.28ISI: 000349552300023ISBN: 978-1-4799-4309-8OAI: oai:DiVA.org:liu-111512DiVA: diva2:756974
IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 23-28, Columbus, OH, USA