NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Truncated Gaussians as tolerance setsThis work focuses on the use of truncated Gaussian distributions as models for bounded data measurements that are constrained to appear between fixed limits. The authors prove that the truncated Gaussian can be viewed as a maximum entropy distribution for truncated bounded data, when mean and covariance are given. The characteristic function for the truncated Gaussian is presented; from this, algorithms are derived for calculation of mean, variance, summation, application of Bayes rule and filtering with truncated Gaussians. As an example of the power of their methods, a derivation of the disparity constraint (used in computer vision) from their models is described. The authors' approach complements results in Statistics, but their proposal is not only to use the truncated Gaussian as a model for selected data; they propose to model measurements as fundamentally in terms of truncated Gaussians.
Document ID
19950020996
Acquisition Source
Legacy CDMS
Document Type
Contractor Report (CR)
Authors
Cozman, Fabio
(Carnegie-Mellon Univ. Pittsburgh, PA, United States)
Krotkov, Eric
(Carnegie-Mellon Univ. Pittsburgh, PA, United States)
Date Acquired
August 16, 2013
Publication Date
September 28, 1994
Subject Category
Statistics And Probability
Report/Patent Number
AD-A289357
NAS 1.26:197732
NASA-CR-197732
CMU-RI-TR-94-35
Accession Number
95N27417
Funding Number(s)
CONTRACT_GRANT: NAGW-1175
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Available Downloads

There are no available downloads for this record.
No Preview Available