Abstract
In this paper we propose a new local learning algorithm for appearance-based object pose estimation, called Locally Linearly Embedded Regression (LLER). LLER uses a constrained version of Locally Linear Embedding (LLE) to simultaneously embed into an intermediate low-dimensional space the training images, the query image and a grid of pose parameters. A linear map is learned between the points in the local neighborhood of the query representation in this low-dimensional intermediate space and their corresponding pose parameters, which is used to directly recover the pose of the query image. The proposed method has been evaluated in a pose estimation task on a database of 16 different objects, consistently outperforming several representative global and local appearance-based pose estimation methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Grimson, E.: Object Recognition by Computer: The Role of Geometric Constraints. MIT Press (1990)
Lamdan, Y., Wolfson, H.J.: Geometric Hashing: A General and Efficient Model-Based Recognition Scheme. In: Proc. Int. Conf. on Computer Vision, Tampa, FL (1988)
Olson, C.F.: Efficient Pose Clustering Using a Randomized Algorithm. Int. Journal of Computer Vision 23(2), 131–147 (1997)
Lepetit, V., Fua, P.: Monocular Model-Based 3D Tracking of Rigid Objects: A Survey. Foundations and Trends in Computer Graphics and Vision 1(1), 1–89 (2005)
Murase, H., Nayar, S.K.: Visual Learning and Recognition of 3-D Objects from Appearance. Int. Journal of Computer Vision 14(1), 5–24 (1995)
Okatani, T., Deguchi, K.: Yet another appearance-based method for pose estimation based on a linear model. In: IAPR Workshop on Machine Vision Applications, pp. 258–261 (2000)
Melzer, T., Reiter, M., Bischof, H.: Appearance models based on kernel canonical correlation analysis. Pattern Recognition, Special Issue on Kernel and Subspace Methods for Computer Vision, 1961–1971 (2003)
Ando, S., Kusachi, Y., Suzuki, A., Arakawa, K.: Appearance based pose estimation of 3D object using support vector regression. In: International Conference on Image Processing, vol. 1, pp. 341–344 (2005)
Roweis, S.T., Saul, L.K.: Nonlinear Dimensionality Reduction by Locally Linear Embeding. Science 290, 2323–2326 (2000)
Ham, J.H., Lee, D.D., Saul, L.K.: Learning High Dimensional Correspondences from Low dimensional Manifolds. In: The 20th International Conference on Machine Learning (2003)
Raytchev, B., Terakado, K., Tamaki, T., Kaneda, K.: Pose Estimation by Local Procrustes Regression. In: Proc. 18th IEEE International Conference on Image Processing, ICIP 2011, pp. 3666–3669 (2011)
Torgeson, W.: Multidimensional Scaling: I. Theory and method. Psychometrika 17, 401–419 (1952)
Cox, T., Cox, M.: Multidimensional Scaling, 2nd edn. Chapman & Hall/CRC (2000)
Mardia, K., Kent, J., Bibby, J.: Multivariate Analysis. Academic Press (1979)
Ben-Israel, A., Greville, T.N.E.: Generalized Inverses: Theory and Applications. Wiley, New York (1974)
Jolliffe, I.: Principal Component Analysis. Springer (1986)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Belkin, M., Niyogi, P.: Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. In: Adv. NIPS 15, Vancouver, Canada (2001)
Yan, S., Xu, D., Zhang, B., Zhang, H., Yang, Q.: Graph Embedding and Extensions: A General Framework for Dimensionality Rediction. IEEE Trans. PAMI 29(1), 40–51 (2007)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2006)
Viksten, F., Forssen, P., Johansson, B., Moe, A.: Comparison of Local Image Descriptors for Full 6 Degree-of-Freedom Pose Estimation. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1139–1146 (2009)
Object Pose Estimation Database, http://www.cvl.isy.liu.se/research/objrec/posedb/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Raytchev, B., Terakado, K., Tamaki, T., Kaneda, K. (2013). Object Pose Estimation by Locally Linearly Embedded Regression. In: Lee, M., Hirose, A., Hou, ZG., Kil, R.M. (eds) Neural Information Processing. ICONIP 2013. Lecture Notes in Computer Science, vol 8228. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42051-1_57
Download citation
DOI: https://doi.org/10.1007/978-3-642-42051-1_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42050-4
Online ISBN: 978-3-642-42051-1
eBook Packages: Computer ScienceComputer Science (R0)