Abstract
In this paper, we show that a better performance can be achieved by training a keypoint detector to only find those points that are suitable to the needs of the given task. We demonstrate our approach in an urban environment, where the keypoint detector should focus on stable man-made structures and ignore objects that undergo natural changes such as vegetation and clouds. We use WaldBoost learning with task specific training samples in order to train a keypoint detector with this capability. We show that our aproach generalizes to a broad class of problems where the task is known beforehand.
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
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int’l Journal of Computer Vision 60(2), 91–110 (2004)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)
Šochman, J., Matas, J.: Waldboost - learning for time constrained sequential detection. In: Schmid, C., Soatto, S., Tomasi, C. (eds.) Proc. Int’l Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 150–157. IEEE Computer Society Press, Los Alamitos (2005)
Šochman, J., Matas, J.: Learning a fast emulator of a binary decision process. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) Proc. Asian Conf. on Computer Vision. LNSC, vol. II, pp. 236–245. Springer, Heidelberg (2007)
Yarbus, A.L.: Eye movements and vision. Plenum, New York (1967) (Originally published in Russian, 1962)
Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. Found. Trends. Comput. Graph. Vis. 3(3), 177–280 (2008)
Rosten, E., Drummond, T.W.: Machine learning for high-speed corner detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 430–443. Springer, Heidelberg (2006)
Förstner, W., Gülch, E.: A fast operator for detection and precise location of distinct points, corners and centers of circular features. In: Proceedings of the ISPRS Intercommission Workshop on Fast Processing of Photogrammetric Data, pp. 281–305 (1987)
Ouellet, J.-N., Hébert, P.: ASN: Image Keypoint Detection from Adaptive Shape Neighborhood. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 454–467. Springer, Heidelberg (2008)
Agrawal, M., Konolige, K., Blas, M.R.: Censure: Center surround extremas for realtime feature detection and matching. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 102–115. Springer, Heidelberg (2008)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. British Machine Vision Conf., pp. 384–393 (2002)
Vergauwen, M., Van Gool, L.: Web-based 3d reconstruction service. Mach. Vision Appl. 17(6), 411–426 (2006)
Snavely, N., Seitz, S., Szeliski, R.: Photo tourism: exploring photo collections in 3D. In: SIGGRAPH 2006, pp. 835–846. ACM Press, New York (2006)
Rosten, E., Porter, R., Drummond, T.: Faster and better: A machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 99(1), 5555
Kienzle, W., Wichmann, F.A., Schlkopf, B., Franz, M.O.: Learning an interest operator from human eye movements. In: 2006 Conference on Computer Vision and Pattern Recognition Workshop, p. 24. IEEE Computer Society, Los Alamitos (2006)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 55(1), 119–139 (1997)
Schapire, R.E., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Machine Learning, 80–91 (1999)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. Int’l Journal of Computer Vision 65(1-2), 43–72 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Strecha, C., Lindner, A., Ali, K., Fua, P. (2009). Training for Task Specific Keypoint Detection. In: Denzler, J., Notni, G., Süße, H. (eds) Pattern Recognition. DAGM 2009. Lecture Notes in Computer Science, vol 5748. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03798-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-03798-6_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03797-9
Online ISBN: 978-3-642-03798-6
eBook Packages: Computer ScienceComputer Science (R0)