Active Camera Calibration for a Head-Eye Platform Using the Variable State-Dimension Filter
IEEE Transactions on Pattern Analysis and Machine Intelligence
MLESAC: a new robust estimator with application to estimating image geometry
Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Multiple view geometry in computer vision
Multiple view geometry in computer vision
Theory of Reconstruction from Image Motion
Theory of Reconstruction from Image Motion
Using Singular Displacements for Uncalibrated Monocular Visual Systems
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
Metric calibration of a stereo rig
VSR '95 Proceedings of the IEEE Workshop on Representation of Visual Scenes
Self-Alignment of an Active Head from Observations of Rotation Matrices
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Violating Rotating Camera Geometry: The Effect of Radial Distortion on Self-Calibration
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Self-Calibration and Euclidean Reconstruction Using Motions of a Stereo Rig
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Linear auto-calibration for ground plane motion
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Metrics for 3D Rotations: Comparison and Analysis
Journal of Mathematical Imaging and Vision
Moving object segmentation using motor signals
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Real-time visuomotor update of an active binocular head
Autonomous Robots
Hi-index | 0.00 |
In this paper we show how to carry out an automatic alignment of a pan-tilt camera platform with its natural coordinate frame, using only images obtained from the cameras during controlled motion of the unit. An active camera in aligned orientation represents the zero position for each axis, and allows axis odometry to be referred to a fixed reference frame; such referral is otherwise only possible using mechanical means, such as end-stops, which cannot take account of the unknown relationship between the camera coordinate frame and its mounting. The algorithms presented involve the calculation of two-view transformations (homographies or epipolar geometry) between pairs of images related by controlled rotation about individual head axes. From these relationships, which can be calculated linearly or optimised iteratively, an invariant line to the motion can be extracted which represents an aligned viewing direction. We present methods for general and degenerate motion (translating or non-translating), and general and degenerate scenes (non-planar and planar, but otherwise unknown), which do not require knowledge of the camera calibration, and are resistant to lens distortion non-linearity.Detailed experimentation in simulation, and in real scenes, demonstrate the speed, accuracy, and robustness of the methods, with the advantages of applicability to a wide range circumstances and no need to involve calibration objects or complex motions. Accuracy of within half a degree can be achieved with a single motion, and we also show how to improve on this by incorporating images from further motions, using a natural extension of the basic algorithm.