Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Three-Frame Algorithm for Estimating Two-Component Image Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Parallax Geometry of Pairs of Points for 3D Scene Analysis
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
A Unified Approach to Moving Object Detection in 2D and 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-Frame Estimation of Planar Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-Frame Correspondence Estimation Using Subspace Constraints
International Journal of Computer Vision
Factorization with Uncertainty
International Journal of Computer Vision
International Journal of Computer Vision
Spatio-Temporal Alignment of Sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Direct Recovery of Planar-Parallax from Multiple Frames
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust recovery of multiple light source based on local light source constant constraint
Pattern Recognition Letters
Egomotion Estimation Using Quadruples of Collinear Image Points
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Direct Recovery of Planar-Parallax from Multiple Frames
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Reconstruction of a Scene with Multiple Linearly Moving Objects
International Journal of Computer Vision
Fixation as a Mechanism for Stabilization of Short Image Sequences
International Journal of Computer Vision
Over-Parameterized Variational Optical Flow
International Journal of Computer Vision
Camera Motion Estimation Through Planar Deformation Determination
Journal of Mathematical Imaging and Vision
Block Wiener-based image registration for moving target indication
Image and Vision Computing
A system for rotational velocity computation from image sequences
Image and Vision Computing
c-Velocity: A Flow-Cumulating Uncalibrated Approach for 3D Plane Detection
International Journal of Computer Vision
Robust moving object detection on moving platforms
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Error sources and their impact on c-velocity methods
Pattern Recognition and Image Analysis
Machine Vision and Applications
Hi-index | 0.14 |
A method for computing the 3D camera motion (the ego-motion) in a static scene is described, where initially a detected 2D motion between two frames is used to align corresponding image regions. We prove that such a 2D registration removes all effects of camera rotation, even for those image regions that remain misaligned. The resulting residual parallax displacement field between the two region-aligned images is an epipolar field centered at the FOE (Focus-of-Expansion). The 3D camera translation is recovered from the epipolar field. The 3D camera rotation is recovered from the computed 3D translation and the detected 2D motion. The decomposition of image motion into a 2D parametric motion and residual epipolar parallax displacements avoids many of the inherent ambiguities and instabilities associated with decomposing the image motion into its rotational and translational components, and hence makes the computation of ego-motion or 3D structure estimation more robust.