nips nips2008 nips2008-95 nips2008-95-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Praveen Srinivasan, Liming Wang, Jianbo Shi
Abstract: Contours have been established in the biological and computer vision literature as a compact yet descriptive representation of object shape. While individual contours provide structure, they lack the large spatial support of region segments (which lack internal structure). We present a method for further grouping of contours in an image using their relationship to the contours of a second, related image. Stereo, motion, and similarity all provide cues that can aid this task; contours that have similar transformations relating them to their matching contours in the second image likely belong to a single group. To find matches for contours, we rely only on shape, which applies directly to all three modalities without modification, in contrast to the specialized approaches developed for each independently. Visually salient contours are extracted in each image, along with a set of candidate transformations for aligning subsets of them. For each transformation, groups of contours with matching shape across the two images are identified to provide a context for evaluating matches of individual contour points across the images. The resulting contexts of contours are used to perform a final grouping on contours in the original image while simultaneously finding matches in the related image, again by shape matching. We demonstrate grouping results on image pairs consisting of stereo, motion, and similar images. Our method also produces qualitatively better results against a baseline method that does not use the inferred contexts. 1
[1] S. Belongie, J. Malik, and J. Puzicha. Shape matching and object recognition using shape contexts. IEEE PAMI, 2002.
[2] S. Birchfield and C. Tomasi. Depth discontinuities by pixel-to-pixel stereo. In ICCV, 1998.
[3] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. PAMI, 2001.
[4] L. Fei-Fei, R. Fergus, and P. Perona. One-shot learning of object categories. PAMI, 2006.
[5] V. Ferrari, L. Fevrier, F. Jurie, and C. Schmid. Groups of adjacent contour segments for object detection. PAMI, 2008.
[6] M. Gelautz and D. Markovic. Recognition of object contours from stereo images: an edge combination approach. 3D PVT, 2004.
[7] W.E.L. Grimson. Why stereo vision is not always about 3d reconstruction. In MIT AI Memo, Technical Report AIM-1435, 1993.
[8] V. Hedau, H. Arora, and N. Ahuja. Matching images under unstable segmentation. In CVPR 2008.
[9] C. Liu, W. T. Freeman, and E.H. Adelson. Analysis of contour motions. In NIPS, 2006.
[10] D. Lowe. Distinctive image features from scale-invariant keypoints. In IJCV, 2003.
[11] D.G. Lowe and T.O. Binford. The recovery of three-dimensional structure from image curves. PAMI, 1985.
[12] D. Sherman and S. Peleg. Stereo by incremental matching of contours. PAMI, 1990.
[13] J.Y.A. Wang and E.H. Adelson. Layered representation for motion analysis. In CVPR, 1993.
[14] J. Wills, S. Agarwal, and S. Belongie. A feature-based approach for dense segmentation and estimation of large disparity motion. IJCV, 2006.
[15] Q. Zhu, G. Song, and J. Shi. Untangling cycles for contour grouping. In ICCV 2007.
[16] Qihui Zhu, Liming Wang, Yang Wu, and Jianbo Shi. Contour context selection for object detection: A set-to-set contour matching approach. In ECCV, 2008. 8