Abstract
This paper proposes a discriminative object class detection and recognition based on spatial configuration of local shape features. We show how simple, redundant edge based features overcome the problem of edge fragmentation while the efficient use of geometrically related feature pairs allows us to construct a robust object shape matcher, invariant to translation, scale and rotation. These prerequisites are used for weakly supervised learning of object models as well as object class detection. The object models employing pairwise combination of redundant shape features exhibit remarkably accurate localization of similar objects even in the presence of clutter and moderate view point changes which is further exploited for model building, object detection and recognition.
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
Ballard, D.H.: Generalizing the hough transform to detect arbitrary shapes. Pattern Recognition 2(13) (1981)
Berg, A.C., Berg, T.L., Malik, K.: Shape matching and object recognition using low distortion correspondences. In: CVPR, pp. 26–33 (2005)
Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical models. In: CVPR, pp. 10–17 (2005)
Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. T-PAMIÂ 30(1) (2008)
Laptev, I.: Improving object detection with boosted histograms. In: Image and Vision Computing (2008)
Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV 77(1-3), 259–289 (2008)
Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: ICCV, vol. 2, pp. 1482–1489 (2005)
Leordeanu, M., Hebert, M.: Beyond local appearance: Category recognition from pairwise interactions of simple features. In: CVPR, pp. 1–8 (2007)
Opelt, A., Pinz, A., Zisserman, A.: A boundary-fragment-model for object detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 575–588. Springer, Heidelberg (2006)
Fergus, P.P.R., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: CVPR, pp. 380–387 (2005)
Shotton, J., Blake, A., Cipolla, R.: Multiscale categorical object recognition using contour fragments. T-PAMI 30(7), 1270–1281 (2008)
Win, J., Jojic, N.: Locus: learning object classes with unsupervised segmentation. In: ICCV, pp. 756–763 (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
Szumilas, L., Wildenauer, H. (2009). Spatial Configuration of Local Shape Features for Discriminative Object Detection. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2009. Lecture Notes in Computer Science, vol 5875. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10331-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-10331-5_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10330-8
Online ISBN: 978-3-642-10331-5
eBook Packages: Computer ScienceComputer Science (R0)