Abstract
We present a novel way of performing pose estimation of known objects in 2D images. We follow a probabilistic approach for modeling objects and representing the observations. These object models are suited to various types of observable visual features, and are demonstrated here with edge segments. Even imperfect models, learned from single stereo views of objects, can be used to infer the maximum-likelihood pose of the object in a novel scene, using a Metropolis-Hastings MCMC algorithm, given a single, calibrated 2D view of the scene. The probabilistic approach does not require explicit model-to-scene correspondences, allowing the system to handle objects without individually-identifiable features. We demonstrate the suitability of these object models to pose estimation in 2D images through qualitative and quantitative evaluations, as we show that the pose of textureless objects can be recovered in scenes with clutter and occlusion.
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
Collet, A., Berenson, D., Srinivasa, S., Ferguson, D.: Object recognition and full pose registration from a single image for robotic manipulation. In: ICRA (2009)
Collet, A., Srinivasa, S.S.: Efficient multi-view object recognition and full pose estimation. In: ICRA, pp. 2050–2055 (2010)
Detry, R.: A probabilistic framework for 3D visual object representation: Experimental data (2009), http://intelsig.org/publications/Detry-2009-PAMI/
Detry, R., Piater, J.: Continuous surface-point distributions for 3D object pose estimation and recognition. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 572–585. Springer, Heidelberg (2011)
Detry, R., Pugeault, N., Piater, J.: A probabilistic framework for 3D visual object representation. IEEE Trans. PAMI 31(10), 1790–1803 (2009)
Ekvall, S., Hoffmann, F., Kragic, D.: Object recognition and pose estimation for robotic manipulation using color cooccurrence histograms. In: IROS (2003)
Gordon, I., Lowe, D.G.: What and where: 3D object recognition with accurate pose. In: Toward Category-Level Object Recognition, pp. 67–82 (2006)
Hsiao, E., Collet, A., Hebert, M.: Making specific features less discriminative to improve point-based 3D object recognition. In: CVPR, pp. 2653–2660 (2010)
Klein, G., Drummond, T.: Robust visual tracking for non-instrumented augmented reality. In: ISMAR, Tokyo, pp. 113–122 (October 2003)
Kraft, D., Krüger, N.: Object sequences (2009), http://www.mip.sdu.dk/covig/sequences.html
Kragic, D., Miller, A.T., Allen, P.K.: Real-time tracking meets online grasp planning. In: ICRA, pp. 2460–2465 (2001)
Krüger, N., Wörgötter, F.: Multi-modal primitives as functional models of hyper-columns and their use for contextual integration. In: De Gregorio, M., Di Maio, V., Frucci, M., Musio, C. (eds.) BVAI 2005. LNCS, vol. 3704, pp. 157–166. Springer, Heidelberg (2005)
Mittrapiyanuruk, P., DeSouza, G.N., Kak, A.C.: Calculating the 3D pose of rigid objects using active appearance models. In: ICRA, pp. 5147–5152 (2004)
Pless, R.: Using many cameras as one. In: CVPR (2), pp. 587–593 (2003)
Pope, A.R., Lowe, D.G.: Probabilistic models of appearance for 3D object recognition (2000)
Pugeault, N.: Early Cognitive Vision: Feedback Mechanisms for the Disambiguation of Early Visual Representation. VDM Verlag Dr. Müller (2008)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vision 66(3), 231–259 (2006)
Sudderth, E.B.: Graphical models for visual object recognition and tracking. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA, USA (2006)
Vacchetti, L., Lepetit, V., Fua, P.: Stable real-time 3D tracking using online and offline information. IEEE Trans. PAMI 26(10), 1385–1391 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Teney, D., Piater, J. (2011). Probabilistic Object Models for Pose Estimation in 2D Images. In: Mester, R., Felsberg, M. (eds) Pattern Recognition. DAGM 2011. Lecture Notes in Computer Science, vol 6835. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23123-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-23123-0_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23122-3
Online ISBN: 978-3-642-23123-0
eBook Packages: Computer ScienceComputer Science (R0)