Acquiring Robust Representations for Recognition from Image Sequences
- 933 Downloads
We present an object recognition system which is capable of on-line learning of representations of scenes and objects from natural image sequences. Local appearance features are used in a tracking framework to find ‘key-frames’ of the input sequence during learning. In addition, the same basic framework is used for both learning and recognition. The system creates sparse representations and shows good recognition performance in a variety of viewing conditions for a database of natural image sequences.
Keywordsobject recognition model acquisition appearance-based learning
Unable to display preview. Download preview PDF.
- 2.D. Jugessur, G. Dudek, “Local Appearance for Robust Object Recognition”, In Proc. CVPR’00, 834–839, 2000.Google Scholar
- 3.J. Koenderink, A. van Doorn, “The internal representation of solid shape with respect to vision”, Biological Cybernetics, 32, 1979.Google Scholar
- 4.D. Lowe, “toward a Computational Model for Object Recognition in IT Cortex”, In Proc. BMCV’00, 20–31, 2000.Google Scholar
- 5.A. Massad, B. Mertsching, and S. Schmalz, “Combining multiple views and temporal associations for 3-D object recognition”, In Proc. ECCV’98, 699–715, 1998.Google Scholar
- 7.M. Pilu, “A direct method for stereo correspondence based on singular value decomposition”, In Proc. CVPR’97, 261–266, 1997.Google Scholar
- 8.C. Schmid, R. Mohr, “Local Greyvalue Invariants for Image Retrieval”, IEEE TPAMI, 19(5):530–535, 1997.Google Scholar
- 10.C. Tomasi, T. Kanade, “Detection and tracking of point features”, Carnegie-Mellon Tech Report CMU-CS-91-132, 1991.Google Scholar
- 11.T. Tuytelaars, L. van Gool, “Content-based image retrieval based on local affinely invariant regions”, In Proc. Visual’ 99, 493–500, 1999.Google Scholar