Geometric Segmentation of Perspective Images Based on Symmetry Groups
Abstract
Symmetry is an effective geometric cue to facilitate conventional segmentation techniques on images of man-made environment. Based on three fundamental principles that summarize the relations between symmetry and perspective imaging, namely, structure from symmetry, symmetry hypothesis testing, and global symmetry testing, we develop a prototype system which is able to automatically segment symmetric objects in space from single 2-D perspective images. The result of such a segmentation is a hierarchy of geometric primitives, called symmetry cells and complexes, whose 3-D structure and pose are fully recovered. Such a geometrically meaningful segmentation may greatly facilitate applications such as feature matching and robot navigation.
Cite
Text
Yang et al. "Geometric Segmentation of Perspective Images Based on Symmetry Groups." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238634Markdown
[Yang et al. "Geometric Segmentation of Perspective Images Based on Symmetry Groups." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/yang2003iccv-geometric/) doi:10.1109/ICCV.2003.1238634BibTeX
@inproceedings{yang2003iccv-geometric,
title = {{Geometric Segmentation of Perspective Images Based on Symmetry Groups}},
author = {Yang, Allen Y. and Rao, Shankar R. and Huang, Kun and Hong, Wei and Ma, Yi},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2003},
pages = {1251-1258},
doi = {10.1109/ICCV.2003.1238634},
url = {https://mlanthology.org/iccv/2003/yang2003iccv-geometric/}
}