Despite the wide application of bilinear problems to problems both in computer vision and in other fields, their behaviour under the effects of noise is still poorly understood. In this paper, we show analytically that marginal distributions on the solution components of a bilinear problem can be bimodal, even with Gaussian measurement error. We demonstrate and compare three different methods of estimating the covariance of a solution. We show that the Hessian at the mode substantially underestimates covariance. Many problems in computer vision can be posed as bilinear problems: i.e. one must find a solution to a set of equations of the form.
Noise in bilinear problems
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 622-627 vol.2
2001-01-01
595145 byte
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2001
|Solutions to Bilinear H~ Output Feedback Control Problems
British Library Online Contents | 1996
|Heteroscedastic Regression in Computer Vision: Problems with Bilinear Constraint
British Library Online Contents | 2000
|British Library Conference Proceedings | 1998
|IEEE | 1998
|