Evolution of a Tracking System
This chapter describes the evolution of a feature-based tracking system developed by metaio. One of the reasons that started the development of the system was the first tracking contest at the International Symposium of Mixed and Augmented Reality (ISMAR) in 2008, which was designed to fairly evaluate different tracking systems. We present the toolchain we conceived to solve common problems like referencing to another coordinate system or creating a map of the environment from photos; we also describe the principles of our tracking method which, in contrast to the methods of all other contestants, was robust enough to use exactly the same parameters for all scenarios of the tracking contest held within the German research project AVILUS1 but at the same time was the most accurate. The ultimate goal of development is its integration into an end consumer product.
KeywordsTracking System Augmented Reality Extend Kalman Filter Global Coordinate System Bundle Adjustment
Our thank goes to Daniel Pustka and Gudrun Klinker who conceived and organized the ISMAR 2008 and 2009 tracking contests as well as Björn Schwerdfeger who together with Gudrun Klinker mainly organized the AVILUS Tracking contest. Futhermore, we are thankful to Harald Wuest, Mark Fiala, Peter Keitler and Sudeep Sundaram for disclosing their technology and for valuable discussions about their view on the tracking contests.
This work was partially supported by BMBF grant Avilus / 01 IM08001 P.
- 1.Aicon 3d systems gmbh. http://www.aicon.de, accessed 2010-12-01.
- 2.Faro europe gmbh & co. kg. http://www.faro.com, accessed 2010-12-01.
- 3.Instantvision, subproject of instantlabs. http://doc.instantreality.org, accessed 2010-12-01.
- 4.The rawseeds project. http://www.rawseeds.org, accessed 2010-12-01.
- 5.Ronald Azuma. A survey of augmented reality. Presence, 6(4):355–385, 1997.Google Scholar
- 7.Simon Baker, Daniel Scharstein, J. P. Lewis, Stefan Roth, Michael J. Black, and Richard Szeliski. A database and evaluation methodology for optical flow. In ICCV, 2007.Google Scholar
- 9.Gary Bradski. The OpenCV Library. Dr. Dobb’s Journal of Software Tools, 2000.Google Scholar
- 10.Robert Castle, Georg Klein, and David Murray. Video-rate localization in multiple maps for wearable augmented reality. In Proc 12th IEEE Int Symp on Wearable Computers, Pittsburgh PA, Sept 28 - Oct 1, 2008, pages 15–22, 2008.Google Scholar
- 14.Andrew P. Gee, Denis Chekhlov, Walterio Mayol, and Andrew Calway. Discovering planes and collapsing the state space in visual slam. In BMVC, 2007.Google Scholar
- 15.Richard I. Hartley and Andrew Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521540518, second edition, 2004.Google Scholar
- 16.Hirokazu Kato and Mark Billinghurst. Marker tracking and hmd calibration for a video-based augmented reality conferencing system. In Proceedings of the 2nd International Workshop on Augmented Reality (IWAR 99), San Francisco, USA, October 1999.Google Scholar
- 17.Georg Klein and David Murray. Parallel tracking and mapping for small AR workspaces. In ISMAR, 2007.Google Scholar
- 18.Marion Langer and Selim Benhimane. An interactive vision-based 3d reconstruction workflow for industrial ar applications. In ISMAR 2010, Workshop: Augmented Reality Super Models, 2010.Google Scholar
- 20.Sebastian Lieberknecht, Selim Benhimane, Peter Meier, and Nassir Navab. A dataset and evaluation methodology for template-based tracking algorithms. In ISMAR, 2009.Google Scholar
- 22.Bruce D. Lucas and Takeo Kanade. An iterative image registration technique with an application to stereo vision (ijcai). In Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI ’81), pages 674–679, April 1981.Google Scholar
- 23.Katharina Pentenrieder, Peter Meier, and Gudrun Klinker. Analysis of tracking accuracy for single-camera square-marker-based tracking. In Proc. Dritter Workshop Virtuelle und Erweiterte Realitt der GI-Fachgruppe VR/AR, 2006.Google Scholar
- 24.Daniel Pustka, Manuel Huber, Christian Waechter, Florian Echtler, Peter Keitler, Gudrun Klinker, Joseph Newman, and Dieter Schmalstieg. Ubitrack: Automatic Configuration of Pervasive Sensor Networks for Augmented Reality. to appear in IEEE Pervasive Computing, 2010.Google Scholar
- 25.Björn Schwerdtfeger. AVILUS tracking contest 2010 – Abschlussbericht. Technical report, TUM, 2010.Google Scholar
- 26.Jianbo Shi and Carlo Tomasi. Good features to track. In CVPR, 1994.Google Scholar