Using vanishing points for camera calibration
International Journal of Computer Vision
Invariant Descriptors for 3D Object Recognition and Pose
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Geometric invariance in computer vision
Geometric invariance in computer vision
Projective pose estimation of linear and quadratic primitives in monocular computer vision
CVGIP: Image Understanding
3D interpretation of conics and orthogonality
CVGIP: Image Understanding
Direct Least Square Fitting of Ellipses
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Spatial Localization Of Modelled Objects Of Revolution In Monocular Perspective Vision
ECCV '90 Proceedings of the First European Conference on Computer Vision
Metric Rectification for Perspective Images of Planes
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
In defence of the 8-point algorithm
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Planar Metric Rectification by Algebraically Estimating The Image of the Absolute Conic
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection of Concentric Circles for Camera Calibration
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Hi-index | 0.00 |
Conics have been used extensively to help perform camera calibration. In this paper, we present a lesser-known result that conics can also be applied to achieve fast and reliable calibration-free scene analysis. We show that the images of the circular points can be identified by solving the intersection of two imaged coplanar circles under projective transformation and thus metric planar rectification can be achieved. The advantage of this approach is that it eliminates the troublesome camera calibration or vanishing line identification step that underlies many previous approaches and makes the computation more direct and efficient. Computation of the vanishing line becomes a by-product of our method which produces a closed form solution by solving the intersection of two ellipses in the perspective view. Different root configurations are inspected to identify the image of the circular points reliably so that 2D Euclidean measurement can be directly made in the perspective view. Compared with other conic based approaches, our algorithm successfully avoids the calibration process and hence is conceptually intuitive and computationally efficient. The experimental results validate the effectiveness and accuracy of the method.