On Symmetry and Multiple-View Geometry: Structure, Pose, and Calibration from a Single Image
International Journal of Computer Vision
Pattern Recognition
Detecting symmetry and symmetric constellations of features
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
Symmetry is an effective geometric cue to facilitate conventionalsegmentation techniques on images of man-madeenvironment. Based on three fundamental principles thatsummarize the relations between symmetry and perspectiveimaging, namely, structure from symmetry, symmetry hypothesistesting, and global symmetry testing, we developa prototype system which is able to automatically segmentsymmetric objects in space from single 2-D perspective images.The result of such a segmentation is a hierarchy ofgeometric primitives, called symmetry cells and complexes,whose 3-D structure and pose are fully recovered. Such ageometrically meaningful segmentation may greatly facilitateapplications such as feature matching and robot navigation.