In Defense of the Eight-Point Algorithm
IEEE Transactions on Pattern Analysis and Machine Intelligence
Determining the Epipolar Geometry and its Uncertainty: A Review
International Journal of Computer Vision
Statistical Optimization for Geometric Computation: Theory and Practice
Statistical Optimization for Geometric Computation: Theory and Practice
Bundle Adjustment - A Modern Synthesis
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Compact Fundamental Matrix Computation
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Proceedings of the International Conference on Advances in Computing, Communication and Control
Highest accuracy fundamental matrix computation
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
| Hi-index | 0.00 |
Given a set of point correspondences in an uncalibrated image pair, we can estimate the fundamental matrix, which can be used in calculating several geometric properties of the images. Among the several existing estimation methods, nonlinear methods can yield accurate results if an approximation to the true solution is given, whereas linear methods are inaccurate but no prior knowledge about the solution is required. Usually a linear method is employed to initialize a nonlinear method, but this sometimes results in failure when the linear approximation is far from the true solution. We herein describe an alternative, or complementary, method for the initialization. The proposed method minimizes the algebraic error, making sure that the results have the rank-2 property, which is neglected in the conventional linear method. Although an approximation is still required in order to obtain a feasible algorithm, the method still outperforms the conventional linear 8-point method, and is even comparable to Sampson error minimization.