30 January 2012 2D-3D feature association via projective transform invariants for model-based 3D pose estimation
Author Affiliations +
The three dimensional (3D) tracking of rigid objects is required in many applications, such as 3D television (3DTV) and augmented reality. Accurate and robust pose estimates enable improved structure reconstructions for 3DTV and reduce jitter in augmented reality scenarios. On the other hand, reliable 2D-3D feature association is one of the most crucial requirements for obtaining high quality 3D pose estimates. In this paper, a 2D-3D registration method, which is based on projective transform invariants, is proposed. Due to the fact that projective transform invariants are highly dependent on 2D and 3D coordinates, the proposed method relies on pose consistencies in order to increase robustness of 2D-3D association. The reliability of the approach is shown by comparisons with RANSAC, perspective factorization and SoftPOSIT based methods on real and artificial data.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
O. Serdar Gedik, O. Serdar Gedik, A. Aydin Alatan, A. Aydin Alatan, "2D-3D feature association via projective transform invariants for model-based 3D pose estimation", Proc. SPIE 8290, Three-Dimensional Image Processing (3DIP) and Applications II, 82900R (30 January 2012); doi: 10.1117/12.910463; https://doi.org/10.1117/12.910463


Robot motion tracking system with multiple views
Proceedings of SPIE (October 04 2001)
3D-model-based head tracking
Proceedings of SPIE (January 09 1997)
Model-based image coding
Proceedings of SPIE (September 15 1994)
Tracking a rigid object in 3D from a single camera
Proceedings of SPIE (August 17 1997)
Video coding of model based at very low bit rates
Proceedings of SPIE (June 22 2003)

Back to Top