Pose Priors for Simultaneously Solving Alignment and Correspondence
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.
KeywordsObject Recognition Gaussian Mixture Model Gaussian Component Repetitive Pattern Uncertainty Region
Unable to display preview. Download preview PDF.
- 3.Grimson, W.E.L., Meyer-Arendt, J.R.: Object recognition by computer: the role of geometric constraints, vol. 31. MIT Press, Cambridge (1992)Google Scholar
- 5.Breuel, T.: Fast recognition using adaptive subdivisions of transformation space. In: Proc. IEEE CVPR, pp. 445–451 (1992)Google Scholar
- 6.Cass, T.A.: Polynomial-time object recognition in the presence of clutter, occlusion, and uncertainty. In: Proc. ECCV, pp. 834–842 (1992)Google Scholar
- 11.Lamdan, Y., Wolfson, H.J.: Geometric hashing: A general and efficient model-based recognition scheme. In: Proc. IEEE ICCV, pp. 238–249 (1988)Google Scholar
- 15.Wunsch, P., Hirzinger, G.: Registration of cad-models to images by iterative inverse perspective matching. In: Proc. ICPR., vol. 78 (1996)Google Scholar
- 16.Beveridge, J.R., Riseman, E.M.: Optimal geometric model matching under full 3D perspective. CVIU 61, 351–364 (1995)Google Scholar
- 18.David, P., DeMenthon, D.: Object recognition in high clutter images using line features. In: Proc. IEEE ICCV, pp. 1581–1588 (2005)Google Scholar