Abstract
Methods based on local, viewpoint invariant features have proven capable of recognizing objects in spite of viewpoint changes, occlusion and clutter. However, these approaches fail when these factors are too strong, due to the limited repeatability and discriminative power of the features. As additional shortcomings, the objects need to be rigid and only their approximate location is found. We present an object recognition approach which overcomes these limitations. An initial set of feature correspondences is first generated. The method anchors on it and then gradually explores the surrounding area, trying to construct more and more matching features, increasingly farther from the initial ones. The resulting process covers the object with matches, and simultaneously separates the correct matches from the wrong ones. Hence, recognition and segmentation are achieved at the same time. Only very few correct initial matches suffice for reliable recognition. Experimental results on still images and television news broadcasts demonstrate the stronger power of the presented method in dealing with extensive clutter, dominant occlusion, large scale and viewpoint changes. Moreover non-rigid deformations are explicitly taken into account, and the approximative contours of the object are produced. The approach can extend any viewpoint invariant feature extractor.
This research was supported by EC project VIBES, the Fund for Scientific Research Flanders, and the IST Network of Excellence PASCAL.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Baumberg, A.: Reliable feature matching across widely separated views. In: Proceedings of the International Conference on Computer Vision, pp. 774–781 (2000)
Bebis, G., Georgiopoulos, M., Lobo, N.V.: Learning geometric hashing functions for model-based object recognition. In: Proceedings of the International Conference on Computer Vision, pp. 543–548 (1995)
Chum, O., Matas, J., Obdrzalek, S.: Epipolar geometry from three correspondences. In: Proceedings of Computer Vision Winter Workshop (2003)
Cyr, C., Kimia, B.: 3d object recognition using similarity-based aspect graph. In: Proceedings of the International Conference on Computer Vision (2001)
Ferrari, V.: Affine Invariant Regions ++. Ph.D Thesis, Selected Readings in Vision and Graphics, Springer Verlag, Zuerich, CH (2004)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Wide-baseline multiple-view correspondences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2003)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Integrating multiple model views for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2004)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous object recognition and segmentation by image exploration. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 40–54. Springer, Heidelberg (2004)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous object recognition and segmentation from single or multiple model views. International Journal of Computer Vision (to appear, 2006)
Leibe, B., Schiele, B.: Scale-invariant object categorization using a scale-adaptive mean-shift search. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 145–153. Springer, Heidelberg (2004)
Lhuillier, M., Quan, L.: Match propagation for image-based modeling and rendering. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(12) (2002)
Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (to appear, 2004)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the British Machine Vision Conference (2002)
Mikolajczyk, K., Schmid, C.: Indexing based on scale-invariant interest points. In: Proceedings of the International Conference on Computer Vision (2001)
Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Proceedings of the European Conference on Computer Vision (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol.II, pp. 257–263 (2003)
Murase, H., Nayar, S.: Visual learning and recognition of 3d objects from appearance. International Journal of Computer Vision 14(1) (1995)
Obrdzalek, S., Matas, J.: Object recognition using local affine frames on distinguished regions. In: Proceedings of the British Machine Vision Conference, pp. 414–431 (2002)
Osian, M., Van Gool, L.: Video shot characterization. In: Proceedings of the TRECVID Workshop (2003)
Pritchett, P., Zisserman, A.: Wide baseline stereo matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (1998)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using affine-invariant image descriptors and multi-view spatial constraints. International Journal of Computer Vision (to appear, 2005)
Schaffalitzky, F., Zisserman, A.: Automated scene matching in movies. In: Proceedings of the Workshop on Content-based Image and Video Retrieval (2002)
Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets. In: Proceedings of the European Conference on Computer Vision (2002)
Schmid, C.: Combining greyvalue invariants with local constraints for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 872–877 (1996)
Selinger, A., Nelson, R.C.: A perceptual grouping hierarchy for appearance-based 3d object recognition. Computer Vision and Image Understanding 76(1), 83–92 (1999)
Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Proceedings of the International Conference on Computer Vision (2003)
Swain, M.J., Ballard, B.H.: Color indexing. International Journal of Computer Vision 7(1), 11–32 (1991)
Tell, D., Carlsson, S.: Combining appearance and topology for wide baseline matching. In: Proceedings of the European Conference on Computer Vision, pp. 68–81 (2002)
Torr, P.H.S., Murray, D.W.: The development and comparison of robust methods for estimating the fundamental matrix. International Journal of Computer Vision 24(3), 271–300 (1997)
Tuytelaars, T., Van Gool, L.: Wide baseline stereo based on local, affinely invariant regions. In: Proceedings of the British Machine Vision Conference (2000)
Tuytelaars, T., Van Gool, L., Dhaene, L., Koch, R.: Matching affinely invariant regions for visual servoing. In: Proceedings of the IEEE Conference on Robotics and Automation, pp. 1601–1606 (1999)
Yu, S.X., Gross, R., Shi, J.: Concurrent object recognition and segmentation by graph partitioning. In: Neural Information Processing Systems (2002)
Zhang, Z., Deriche, R., Faugeras, O., Luong, Q.: A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Artificial Intelligence 78, 87–119 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ferrari, V., Tuytelaars, T., Van Gool, L. (2006). Simultaneous Object Recognition and Segmentation by Image Exploration. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds) Toward Category-Level Object Recognition. Lecture Notes in Computer Science, vol 4170. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11957959_8
Download citation
DOI: https://doi.org/10.1007/11957959_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68794-8
Online ISBN: 978-3-540-68795-5
eBook Packages: Computer ScienceComputer Science (R0)