Abstract
Online learning for object detection is an important requirement for many computer vision applications. In this paper, we present an iterative optimization algorithm that learns separable linear classifiers from a sample of positive and negative example images. We demonstrate that separability not only leads to rapid runtime behavior but enables very fast training. Experimental results underline that the approach even allows for real time online learning for tracking of articulated objects in real world environments.
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
Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. In: Proc. CVPR, vol. I, pp. 511–518 (2001)
Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. on Pattern Analysis and Machine Intelligence 26, 1475–1490 (2004)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. CVPR, vol. II, pp. 264–272 (2003)
Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Proc. ECCV Workshop on Statistical Learning in Computer Vision, Prague (2004)
Bauckhage, C., Hanheide, M., Wrede, S., Sagerer, G.: A Cognitive Vision System for Action Recognition in Office Environments. In: Proc. CVPR. Vol. II, pp. 827–833 (2004)
Nair, V., Clark, J.: An Unsupervised Online Learning Framework for Moving Object Detection. In: Proc. CVPR, vol. II, pp. 317–324 (2004)
Ross, D., Lim, J., Yang, M.-H.: Adaptive probabilistic visual tracking with incremental subspace update. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 470–482. Springer, Heidelberg (2004)
Heidemann, G., Bekel, H., Bax, I., Ritter, H.: Interactive online learning. Pattern Recognition and Image Analysis 15, 55–58 (2005)
Venkatachalam, V., Aravena, J.: Optimal Parallel 2-D FIR Digital Filter with Separable Terms. IEEE Trans. on Signal Processing 45, 1393–1369 (1997)
Cover, T.: Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications to Pattern Recognition. IEEE Trans. on Electronic Computers 14, 326–334 (1965)
Black, M., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objects using a view-based reprenstation. Int. J. of Computer Vision 26, 63–84 (1998)
Gorges, N., Hanheide, M., Christmas, W.J., Bauckhage, C., Sagerer, G., Kittler, J.: Mosaics from arbitrary stereo video sequences. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 342–349. Springer, Heidelberg (2004)
Koenderink, N.J.J.P., van Doorn, A.J.: Image Processing Done Right. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 158–172. Springer, Heidelberg (2002)
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
Bauckhage, C., Tsotsos, J.K. (2005). Separable Linear Classifiers for Online Learning in Appearance Based Object Detection. In: Gagalowicz, A., Philips, W. (eds) Computer Analysis of Images and Patterns. CAIP 2005. Lecture Notes in Computer Science, vol 3691. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11556121_43
Download citation
DOI: https://doi.org/10.1007/11556121_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28969-2
Online ISBN: 978-3-540-32011-1
eBook Packages: Computer ScienceComputer Science (R0)