Unbiased estimation and statistical analysis of 3-D rigid motion from two views
- 1 January 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 15 (1), 37-50
- https://doi.org/10.1109/34.184773
Abstract
The problem of estimating 3D rigid motion from point correspondences over two views is formulated as nonlinear least-squares (LS) optimization, and the statistical behaviors of the errors in the solution are analyzed by introducing a realistic model of noise described in terms of the covariance matrices of N-vectors. It is shown that the LS solution based on the epipolar constraint is statistically biased. The geometry of this bias is described in both quantitative and qualitative terms. Finally, an unbiased estimation scheme is presented, and random number simulations are conducted to observe its effectiveness.Keywords
This publication has 35 references indexed in Scilit:
- A multi-frame approach to visual motion perceptionInternational Journal of Computer Vision, 1991
- Least-squares estimation of transformation parameters between two point patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Structure from motion-a critical analysis of methodsIEEE Transactions on Systems, Man, and Cybernetics, 1991
- 3-D motion estimation using a sequence of noisy stereo images: models, estimation, and uniqueness resultsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Polynomial methods for structure from motionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Some properties of the E matrix in two-view motion estimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- A simplification to linear two-view motion algorithmsComputer Vision, Graphics, and Image Processing, 1989
- Motion and structure from two perspective views: algorithms, error analysis, and error estimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- Two-view motion analysis: a unified algorithmJournal of the Optical Society of America A, 1986
- Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved SurfacesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984