Abstract
This paper proposes an approach for the unsupervised learning of object models from local image feature correspondences. The object models are learned from an unlabeled sequence of training images showing one object after the other. The obtained object models enable the recognition of these objects in cluttered scenes, under occlusion, in-plane rotation and scale change. Maximally stable extremal regions are used as local image features and two different types of descriptors characterising the appearance and shape of the regions allow a robust matching. Experiments with real objects show the recognition performance of the presented approach under various conditions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Baumberg, A.: Reliable feature matching across widely separated views. In: CVPR, pp. 774–781 (2000)
Belongie, S., Malik, J.: Matching with shape context. In: IEEE Workshop on Content-based Access of Image and Video Libraries, CBAIVL 2000 (2000)
Blthoff, H.H., Wallraven, C., Graf, A.B.A.: View-based dynamic object recognition based on human perception. In: ICPR, pp. 768–776. IEEE CS Press, Los Alamitos (2002)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 2003, vol. 2, pp. 264–271 (2003)
Ferrari, V., Tuytelaars, T., van Gool, L.: Wide-baseline muliple-view correspondences. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, June 2003, vol. I, pp. 718–728 (2003)
Ferrari, V., Tuytelaars, T., van Gool, L.: Integrating multiple model views for object recognition. In: IEEE Computer Vision and Pattern Recognition (CVPR), June 2004, vol. II, pp. 105–112 (2004)
Kadir, T.: Scale, Saliency and Scene Description. PhD thesis, University of Oxford (2002)
Kuhn, H.W.: The Hungarian method for the assignment problem. In: Naval Research Logistics Quarterly, vol. 2, pp. 83–97 (1955)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. Int. Conf. on Computer Vision ICCV, Corfu, pp. 1150–1157 (1999)
Lowe, D.G.: Local feature view clustering for 3d object recognition. In: Proc. Int. Conf. on Computer Vision and Pattern Recognition CVPR (2001)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. BMVC, pp. 384–393 (2002)
Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: European Conference on Computer Vision, Copenhagen, pp. 128–142. Springer, Heidelberg (2002)
Munkres, J.R.: Algorithms for the assignment and transportation problems. SIAM 5, 32–38 (1957)
Ramanan, D., Forsyth, D.A.: Using temporal coherence to build models of animals. In: International Conference on Computer Vision (ICCV), Nice (October 2003)
Schmid, C., Mohr, R.: Matching by local invariants. Rapport de Recherche N 2644, INRIA (1995)
Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leitner, R., Bischof, H. (2005). Recognition of 3D Objects by Learning from Correspondences in a Sequence of Unlabeled Training Images. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds) Pattern Recognition. DAGM 2005. Lecture Notes in Computer Science, vol 3663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550518_46
Download citation
DOI: https://doi.org/10.1007/11550518_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28703-2
Online ISBN: 978-3-540-31942-9
eBook Packages: Computer ScienceComputer Science (R0)