Abstract
We present a novel framework for unsupervised training of an object detection system. The basic idea is to (1) exploit a huge amount of unlabeled video data by being very conservative in selecting training examples; and (2) to start with a very simple object detection system and using generative and discriminative classifiers in an iterative co-training fashion to arrive at increasingly better object detectors. We demonstrate the framework on a surveillance task where we learn a person detector. We start with a simple moving object classifier and proceed with robust PCA (on shape and appearance) as a generative classifier which in turn generates a training set for a discriminative AdaBoost classifier. The results obtained by AdaBoost are again filtered by PCA which produces an even better training set. We demonstrate that by using this approach we avoid hand labeling training data and still achieve a state of the art detection rate.
This work has been supported by the Austrian Joint Research Project Cognitive Vision under projects S9103-N04 and S9104-N04, by the Federal Ministry for Education, Science and Culture of Austria under the CONEX program, by the SI-A project, by the Federal Ministry of Transport, Innovation and Technology under P-Nr. I2-2-26p Vitus2, by the Research program Computer Vision P2-0214 (RS), by EU FP6-004250-IP project CoSy and by EU FP6-511051-2 project MOBVIS.
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.
Similar content being viewed by others
References
Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. PAMI 26(11), 1475–1490 (2004)
Breu, H., Gil, J., Kirkpatrick, D., Werman, M.: Linear time euclidean distance transform algorithms. IEEE Trans. PAMI 17(5), 529–533 (1995)
De la Torre, F., Black, M.J.: A framework for robust subspace learning. IJCV 54(1), 117–142 (2003)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. CVPR 2003, pp. 264–271 (2003)
Freund, Y., Shapire, R.: A decision-theoretic generalization of online learning and an application to boosting. J. of Computer and System Sciences 55, 119–139 (1997)
Leonardis, A., Bischof, H.: Robust recognition using eigenimages. Computer Vision and Image Understanding 78, 99–118 (2000)
Levi, K., Weiss, Y.: Learning Object Detection from a Small Number of Examples: The Importance of Good Features. In: Proc. CVPR 2004 (2004)
Levin, A., Viola, P., Freund, Y.: Unsupervised improvement of visual detectors using co-training. In: Proc. ICCV, pp. 626–633 (2003)
Littlestone, N.: Learning quickly when irrelevant attributes abound. Machine Learning 2, 285–318 (1987)
McFarlane, N.J.B., Schofield, C.P.: Segmentation and tracking of piglets. Machine Vision and Applications 8(3), 187–193 (1995)
Nair, V., Clark, J.J.: An unsupervised, online learning framework for moving object detection. In: Proc. CVPR 2004, pp. 317–324 (2004)
Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 71–84. Springer, Heidelberg (2004)
Park, J.-H., Choi, Y.-K.: On-line learning for active pattern recognition. IEEE Signal Processing Letters 3(11), 301–303 (1996)
Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Trans. PAMI 20(1), 23–38 (1998)
Skočaj, D., Bischof, H., Leonardis, A.: A robust PCA algorithm for building representations from panoramic images. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 761–775. Springer, Heidelberg (2002)
Skočaj, D., Leonardis, A.: Weighted and robust incremental method for subspace learning. In: Proc. ICCV 2003, vol. II, pp. 1494–1501 (2003)
Sung, K., Poggio, T.: Example-based learning for view-based face detection. IEEE Trans. PAMI 20, 39–51 (1998)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. CVPR 2001, pp. 511–518 (2001)
Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: Proc. ICCV 2003, vol. 2, pp. 734–741 (2003)
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
Roth, P., Grabner, H., Skočaj, D., Bischof, H., Leonardis, A. (2005). Conservative Visual Learning for Object Detection with Minimal Hand Labeling Effort. 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_37
Download citation
DOI: https://doi.org/10.1007/11550518_37
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)