Title :
Analysis of the least median of squares estimator for computer vision applications
Author :
Mintz, Doron ; Meer, Peter ; Rosenfeld, Azriel
Author_Institution :
LSI Logic Corp., Milpitas, CA, USA
Abstract :
The robust least-median-of-squares (LMedS) estimator, which can recover a model representing only half the data points, was recently introduced in computer vision. Image data, however, is usually also corrupted by a zero-mean random process (noise) accounting for the measurement uncertainties. It is shown that in the presence of significant noise, LMedS loses its high breakdown point property. A different, two-stage approach in which the uncertainty due to noise is reduced before applying the simplest LMedS procedure is proposed. The superior performance of the technique is proved by comparative graphs
Keywords :
computer vision; least squares approximations; random processes; uncertainty handling; LMedS; computer vision; image data; least median of squares estimator; measurement uncertainties; zero-mean random process; Application software; Automation; Computer vision; Covariance matrix; Educational institutions; Electric breakdown; Least squares approximation; Logic; Surface fitting; Yield estimation;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223126