Title :
Euclidean Structure from Conic Feature Correspondences
Author_Institution :
Sch. of Control Sci. & Eng., Shandong Univ., Jinan, China
Abstract :
In this paper, a novel method of the 2D Euclidean structure recovery in one view from the projections of N parallel conics is proposed. Without considering the conic dual to the absolute points (CDAP), we transform conic features from the homogeneous coordinates to the lifted coordinates. In the lifted space, the conic features have the similar properties to the point or line features, which especially means that the Homography can also be deduced by conic features directly. Our work gives a generic framework of recovering the Euclidean structure from conic features. A series of experiments with simulated and real data are conducted. The experimental results show that the proposed theory has its validity in practical applications.
Keywords :
cameras; feature extraction; 2D Euclidean structure recovery; CDAP; N-parallel conic projections; conic dual-to-the-absolute points; conic feature correspondences; conic features; generic framework; homogeneous coordinates; homography; lifted coordinates; lifted space; line features; point features; Calibration; Cameras; Computer vision; Equations; Symmetric matrices; Transmission line matrix methods; Vectors; Euclidean structure; camera calibration; conic correspondence; homography;
Conference_Titel :
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location :
Stockholm
DOI :
10.1109/ICPR.2014.687