Euclidean structure from uncalibrated images
BMVC 94 Proceedings of the conference on British machine vision (vol. 2)
A Flexible New Technique for Camera Calibration
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple view geometry in computer vision
Multiple view geometry in computer vision
Euclidean 3D Reconstruction from Image Sequences with Variable Focal Lenghts
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Autocalibration from Planar Scenes
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Another Way of Looking at Plane-Based Calibration: The Centre Circle Constraint
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Camera Calibration with One-Dimensional Objects
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Camera calibration and light source orientation from solar shadows
Computer Vision and Image Understanding
A Variational Approach to Problems in Calibration of Multiple Cameras
IEEE Transactions on Pattern Analysis and Machine Intelligence
Plane-based camera self-calibration by metric rectification of images
Image and Vision Computing
A multiview approach to tracking people in crowded scenes using a planar homography constraint
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Towards a guaranteed solution to plane-based self-calibration
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Plane-Based calibration and auto-calibration of a fish-eye camera
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
| Hi-index | 0.00 |
We consider the problem of camera selfcalibration, from images of a planar object with unknown Euclidean structure. The general case of possibly varying focal length is addressed. This problem is non-linear in general. One of our contributions is a non-linear approach, that makes abstraction of the (possibly varying) focal length, resulting in a computationally efficient algorithm. In addition, it does not require a good initial estimate of the focal length, unlike previous approaches. As for the initialization of other parameters, we propose a practical approach, that simply requires to take one image in roughly fronto-parallel position. Closed-form solutions for various configurations of unknown intrinsic parameters are provided. Our methods are evaluated and compared to previous approaches, using simulated and real images. Besides our practical contributions, we also provide a detailed geometrical interpretation of the principles underlying our approach.