High Accuracy Fundamental Matrix Computation and Its Performance Evaluation
نویسندگان
چکیده
We compare the convergence performance of different numerical schemes for computing the fundamental matrix from point correspondences over two images. First, we state the problem and the associated KCR lower bound. Then, we describe the algorithms of three well-known methods: FNS, HEIV, and renormalization, to which we add Gauss-Newton iterations. For initial values, we test random choice, least squares, and Taubin’s method. Experiments using simulated and real images reveal different characteristics of each method. Overall, FNS exhibits the best convergence performance.
منابع مشابه
High Accuracy Computation of Rank-constrained Fundamental Matrix by Efficient Search
High Accuracy Computation of Rank-constrained Fundamental Matrix by Efficient Search Yasuyuki SUGAYA† and Kenichi KANATANI†† † Department of Information and Computer Sciences, Toyohashi University of Technology, Toyohashi, Aichi, 441–8580 Japan †† Department of Computer Science, Okayama University, Okayama, 700–8530 Japan E-mail: †[email protected], ††[email protected] Abs...
متن کاملHigh Accuracy Computation of Rank-Constrained Fundamental Matrix
A new method is presented for computing the fundamental matrix from point correspondences: its singular value decomposition (SVD) is optimized by the Levenberg-Marquard (LM) method. The search is initialized by optimal correction of unconstrained ML. There is no need for tentative 3-D reconstruction. The accuracy achieves the theoretical bound (the KCR lower bound).
متن کاملHighest Accuracy Fundamental Matrix Computation
We compare algorithms for fundamental matrix computation, which we classify into “a posteriori correction”, “internal access”, and “external access”. Doing experimental comparison, we show that the 7-parameter Levenberg-Marquardt (LM) search and the extended FNS (EFNS) exhibit the best performance and that additional bundle adjustment does not increase the accuracy to any noticeable degree.
متن کاملFundamental Matrix Computation: Theory and Practice
We classify and review existing algorithms for computing the fundamental matrix from point correspondences and propose new effective schemes: 7-parameter Levenberg-Marquardt (LM) search, EFNS, and EFNS-based bundle adjustment. Doing experimental comparison, we show that EFNS and the 7-parameter LM search exhibit the best performance and that additional bundle adjustment does not increase the ac...
متن کاملOptimal Fundamental Matrix Computation : Algorithm and Reliability Analysis
This paper presents an optimal linear algorithm for computing the fundamental matrix from corresponding points over two images under an assumed model, which admits independent Gaussian noise that is not necessarily isotropic or homogeneous. We derive a theoretical bound and demonstrate by experiments that our algorithm delivers results in the vicinity of the bound. Simulated and real-image exam...
متن کامل