Shape Based Detection and Top-Down Delineation Using Image Segments
- 229 Downloads
We introduce a segmentation-based detection and top-down figure-ground delineation algorithm. Unlike common methods which use appearance for detection, our method relies primarily on the shape of objects as is reflected by their bottom-up segmentation.
Our algorithm receives as input an image, along with its bottom-up hierarchical segmentation. The shape of each segment is then described both by its significant boundary sections and by regional, dense orientation information derived from the segment’s shape using the Poisson equation. Our method then examines multiple, overlapping segmentation hypotheses, using their shape and color, in an attempt to find a “coherent whole,” i.e., a collection of segments that consistently vote for an object at a single location in the image. Once an object is detected, we propose a novel pixel-level top-down figure-ground segmentation by “competitive coverage” process to accurately delineate the boundaries of the object. In this process, given a particular detection hypothesis, we let the voting segments compete for interpreting (covering) each of the semantic parts of an object. Incorporating competition in the process allows us to resolve ambiguities that arise when two different regions are matched to the same object part and to discard nearby false regions that participated in the voting process.
We provide quantitative and qualitative experimental results on challenging datasets. These experiments demonstrate that our method can accurately detect and segment objects with complex shapes, obtaining results comparable to those of existing state of the art methods. Moreover, our method allows us to simultaneously detect multiple instances of class objects in images and to cope with challenging types of occlusions such as occlusions by a bar of varying size or by another object of the same class, that are difficult to handle with other existing class-specific top-down segmentation methods.
KeywordsShape-based object detection Class-based top-down segmentation
Unable to display preview. Download preview PDF.
- Agarwal, S., & Roth, D. (2002). Learning a sparse representation for object detection. European Conference on Computer Vision, 2, 113–130. Google Scholar
- Borenstein, E. (2006). Shape guided object segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2006. Google Scholar
- Borenstein, E. (2009). http://www.msri.org/people/members/eranb.
- Borenstein, E., Sharon, E., & Ullman, S. (2004). Combining top-down and bottom-up segmentation. In Workshop on perceptual organization in computer vision, IEEE conference on computer vision and pattern recognition, Washington, 2004. Google Scholar
- Burl, M. C., Weber, M., & Perona, P. (1998). A probabilistic approach to object recognition using local photometry and global geometry. In Lecture notes in computer science (Vol. 1407). Google Scholar
- Cao, L., & Fei-Fei, L. (2007). Spatially coherent latent topic model for concurrent object segmentation and classification. In International conference on computer vision, 2007. Google Scholar
- Ferrari, V., Jurie, F., & Schmid, C. (2007). Accurate object detection with deformable shape models learnt from images. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2007. Google Scholar
- Gorelick, L., Galun, M., Sharon, E., Brandt, A., & Basri, R. (2006). Shape representation and classification using the Poisson equation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(12), 2006. Google Scholar
- Kumar, M. P., Torr, P., & Zisserman, A. (2004). Extending pictorial structures for object recognition. In British machine vision conference, 2004. Google Scholar
- Kumar, M. P., Torr, P., & Zisserman, A. (2005). Obj cut. In IEEE conference on computer vision and pattern recognition (1) (pp. 18–25), 2005. Google Scholar
- Levin, A., & Weiss, Y. (2006). Learning to combine bottom-up and top-down segmentation. In European conference on computer vision, 2006. Google Scholar
- Mori, G., Ren, X., Efros, A., & Malik, J. (2004). Recovering human body configurations: Combining segmentation and recognition. In IEEE conference on computer vision and pattern recognition, 2004. Google Scholar
- Opelt, A., Pinz, A., & Zisserman, A. (2006). A boundary-fragment-model for object detection. In European conference on computer vision, May 2006. Google Scholar
- Pantofaru, C., Dorko, G., Schmid, C., & Hebert, M. (2008). Combining regions and patches for object class localization (pp. 23–30), June 2006. Google Scholar
- Ren, X., Berg, A., & Malik, J. (2005a). Recovering human body configurations using pairwise constraints between parts. In International conference on computer vision (Vol. 1, pp. 824–831). Google Scholar
- Ren, X., Fowlkes, C., & Malik, J. (2005b). Cue integration for figure ground labeling. In Advances in neural information processing systems (Vol. 18), 2005. Google Scholar
- Russell, B. C., Efros, A. A., Sivic, J., Freeman, W. T., & Zisserman, A. (2006). Using multiple segmentations to discover objects and their extent in image collections. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2006. Google Scholar
- Shotton, J., Blake, A., & Cipolla, R. (2005). Contour-based learning for object detection. In International conference on computer vision, (Vol. 1, pp. 503–510), October 2005. Google Scholar
- Todorovic, S., & Ahuja, N. (2007). Learning the taxonomy and models of categories present in arbitrary images. In International conference on computer vision, 2007. Google Scholar
- Ullman, S., Sali, E., & Vidal-Naquet, M. (2001). A fragment-based approach to object representation and classification. In International workshop on visual form 4, 2001. Google Scholar
- Vidal-Naquet, M., & Ullman, S. (2003). Object recognition with informative features and linear classification. In International conference on computer vision (p. 281), 2003. Google Scholar
- Wang, L., Shi, J., Song, G., & Shen, I.-F. (2007). Object detection combining recognition and segmentation. In Asian conference on computer vision, 2007. Google Scholar
- Weber, M., Welling, M., & Perona, P. (2000). Towards automatic discovery of object categories. IEEE Conference on Computer Vision and Pattern Recognition, 2, 101–108. Google Scholar
- Winn, J., & Jojic, N. (2005). Locus: Learning object classes with unsupervised segmentation. In International conference on computer vision, Beijing, 2005. Google Scholar