Using Partial Edge Contour Matches for Efficient Object Category Localization
Conference paper
Abstract
We propose a method for object category localization by partially matching edge contours to a single shape prototype of the category. Previous work in this area either relies on piecewise contour approximations, requires meaningful supervised decompositions, or matches coarse shape-based descriptions at local interest points. Our method avoids error-prone pre-processing steps by using all obtained edges in a partial contour matching setting. The matched fragments are efficiently summarized and aggregated to form location hypotheses. The efficiency and accuracy of our edge fragment based voting step yields high quality hypotheses in low computation time. The experimental evaluation achieves excellent performance in the hypotheses voting stage and yields competitive results on challenging datasets like ETHZ and INRIA horses.
Keywords
Object Detection Interest Point Query Image Partial Match Reference Template
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Download
to read the full conference paper text
Supplementary material
References
- 1.Shotton, J., Blake, A., Cipolla, R.: Contour-based learning for object detection. In: ICCV (2005)Google Scholar
- 2.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)CrossRefGoogle Scholar
- 3.Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. PAMI (2008)Google Scholar
- 4.Ravishankar, S., Jain, A., Mittal, A.: Multi-stage contour based detection of deformable objects. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 483–496. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 5.Maji, S., Malik, J.: Object detection using a max-margin hough transform. In: CVPR (2009)Google Scholar
- 6.Ommer, B., Malik, J.: Multi-scale object detection by clustering lines. In: ICCV (2009)Google Scholar
- 7.Bai, X., Li, Q., Latecki, L., Liu, W., Tu, Z.: Shape band: A deformable object detection approach. In: CVPR (2009)Google Scholar
- 8.Zhu, Q., Wang, L., Wu, Y., Shi, J.: Contour context selection for object detection: A set-to-set contour matching approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 774–787. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 9.Lu, C., Latecki, L., Adluru, N., Ling, H., Yang, X.: Shape guided contour fragment grouping with particle filters. In: ICCV (2009)Google Scholar
- 10.Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: ICCV (2003)Google Scholar
- 11.Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI (2005)Google Scholar
- 12.Biederman, I.: Human image understanding: Recent research and a theory. In: Computer Vision, Graphics, and Image Processing, vol. 32 (1985)Google Scholar
- 13.Ferrari, V., Jurie, F., Schmid, C.: From images to shape models for object detection. In: IJCV (2009)Google Scholar
- 14.Berg, A., Berg, T., Malik, J.: Shape matching and object recognition using low distortion correspondences. In: CVPR (2005)Google Scholar
- 15.Ferrari, V., Tuytelaars, T., Gool, L.V.: Object detection by contour segment networks. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 14–28. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 16.Ferrari, V., Jurie, F., Schmid, C.: Accurate object detections with deformable shape models learnt from images. In: CVPR (2007)Google Scholar
- 17.Leordeanu, M., Hebert, M., Sukthankar, R.: Beyond local appearance: Category recognition from pairwise interactions of simple features. In: CVPR (2007)Google Scholar
- 18.Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI (2002)Google Scholar
- 19.Gu, C., Lim, J., Arbelaez, P., Malik, J.: Recognition from regions. In: CVPR (2009)Google Scholar
- 20.Turney, J., Mudge, T., Volz, R.: Recognizing Partially Occluded Parts. PAMI (1985)Google Scholar
- 21.Brendel, W., Todorovic, S.: Video object segmentation by tracking regions. In: ICCV (2009)Google Scholar
- 22.Chen, L., Feris, R., Turk, M.: Efficient partial shape matching using smith-waterman algorithm. In: NORDIA (2008)Google Scholar
- 23.Felzenszwalb, P., Schwartz, J.: Hierarchical matching of deformable shapes. In: CVPR (2007)Google Scholar
- 24.Kokkinos, I., Yuille, A.: Hop: Hierarchical object parsing. In: CVPR (2009)Google Scholar
- 25.Donoser, M., Riemenschneider, H., Bischof, H.: Efficient partial shape matching of outer contours. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5994, pp. 281–292. Springer, Heidelberg (2009)CrossRefGoogle Scholar
- 26.Donoser, M., Riemenschneider, H., Bischof, H.: Linked Edges as Stable Region Boundaries. In: CVPR (2010)Google Scholar
- 27.Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. PAMI (2004)Google Scholar
- 28.Xu, C., Liu, J., Tang, X.: 2D Shape Matching by Contour Flexibility. PAMI (2009)Google Scholar
- 29.Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: ICCV (2005)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2010