A Decoupled Algorithm for Vision Parameter Estimation with Application to the Trifocal Tensor
Tony Scoleri, Wojciech Chojnacki, Michael J. Brooks · 2007
We consider the problem of estimating parameters of a model described by a system of equations which underlies a wide class of computer vision applications. One method to solve such a problem is the fundamental numerical scheme (FNS) previously proposed by some of the authors. In this paper, a more stable version of FNS is developed, with better convergence properties than the original version. The improvement in performance is achieved by reducing the original estimation problem to a couple of problems of lower dimension. By way of example, the new algorithm has been applied to the problem of estimating the trifocal tensor relating three views of a scene. Experiments carried out with both synthetic and real images reveal the new estimator to be more stable compared to the original FNS method, and commensurate in accuracy with the Gold Standard maximum likelihood estimator.