Abstract
Estimating a camera pose given a set of 3D-object and 2D-image feature points is a well understood problem when correspondences are given. However, when such correspondences cannot be established a priori, one must simultaneously compute them along with the pose. Most current approaches to solving this problem are too computationally intensive to be practical. An interesting exception is the SoftPosit algorithm, that looks for the solution as the minimum of a suitable objective function. It is arguably one of the best algorithms but its iterative nature means it can fail in the presence of clutter, occlusions, or repetitive patterns. In this paper, we propose an approach that overcomes this limitation by taking advantage of the fact that, in practice, some prior on the camera pose is often available. We model it as a Gaussian Mixture Model that we progressively refine by hypothesizing new correspondences. This rapidly reduces the number of potential matches for each 3D point and lets us explore the pose space more thoroughly than SoftPosit at a similar computational cost. We will demonstrate the superior performance of our approach on both synthetic and real data.
This work was supported by the Swiss National Science Foundation and by funds of the European Commission under the IST-project 034307 DYVINE.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
David, P., DeMenthon, D., Duraiswami, R., Samet, H.: Softposit: Simultaneous pose and correspondence determination. IJCV 59, 259–284 (2004)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981)
Grimson, W.E.L., Meyer-Arendt, J.R.: Object recognition by computer: the role of geometric constraints, vol. 31. MIT Press, Cambridge (1992)
Grimson, W.E.L.: The combinatorics of heuristic search termination for object recognition in cluttered environments. IEEE PAMI 13, 920–935 (1991)
Breuel, T.: Fast recognition using adaptive subdivisions of transformation space. In: Proc. IEEE CVPR, pp. 445–451 (1992)
Cass, T.A.: Polynomial-time object recognition in the presence of clutter, occlusion, and uncertainty. In: Proc. ECCV, pp. 834–842 (1992)
Olson, C.F.: Efficient pose clustering using a randomized algorithm. IJCV 23, 131–147 (1997)
Stockman, G.: Object recognition and localization via pose clustering. Comput. Vision Graph. Image Process 40, 361–387 (1987)
Ayache, N., Faugeras, O.D.: Hyper: a new approach for the recognition and positioning to two-dimensional objects. IEEE PAMI 8, 44–54 (1986)
Grimson, W.E.L., Lozano-Pérez, T.: Localizing overlapping parts by searching the interpretation tree. IEEE PAMI 9, 469–482 (1987)
Lamdan, Y., Wolfson, H.J.: Geometric hashing: A general and efficient model-based recognition scheme. In: Proc. IEEE ICCV, pp. 238–249 (1988)
Burns, J.B., Weiss, R.S., Riseman, E.M.: View variation of point-set and line-segment features. IEEE PAMI 15, 51–68 (1993)
Beis, J.S., Lowe, D.G.: Indexing without invariants in 3D object recognition. IEEE PAMI 21, 1000–1015 (1999)
Jurie, F.: Solution of the simultaneous pose and correspondence problem using gaussian error model. CVIU 73, 357–373 (1999)
Wunsch, P., Hirzinger, G.: Registration of cad-models to images by iterative inverse perspective matching. In: Proc. ICPR., vol. 78 (1996)
Beveridge, J.R., Riseman, E.M.: Optimal geometric model matching under full 3D perspective. CVIU 61, 351–364 (1995)
Arya, S., Mount, D., Netanyahu, N., Silverman, R., Wu, A.: An optimal algorithm for approximate NN searching fixed dimensions. J. ACM 45, 891–923 (1998)
David, P., DeMenthon, D.: Object recognition in high clutter images using line features. In: Proc. IEEE ICCV, pp. 1581–1588 (2005)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 15, 91–110 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moreno-Noguer, F., Lepetit, V., Fua, P. (2008). Pose Priors for Simultaneously Solving Alignment and Correspondence. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88688-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-88688-4_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88685-3
Online ISBN: 978-3-540-88688-4
eBook Packages: Computer ScienceComputer Science (R0)