A finite mixtures algorithm for finding classes in imagesThe authors describe an algorithm for estimating the proportions of classes in a SAR (synthetic aperture radar) image without any user interaction. The method assumes that the image is a mixture of a known number of different pixel types. A maximum likelihood estimate of the parameters of the resulting mixture distribution is then used to find the proportions for the various classes. The technique was successfully applied to aircraft SAR images of sea ice. Computer simulations were used to determine the relative errors of the technique. The technique performs well even with extremely noisy images.
Document ID
19920052600
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Samadani, Ramin (NASA Headquarters Washington, DC United States)
Vesecky, John F. (Stanford University CA, United States)
Date Acquired
August 15, 2013
Publication Date
January 1, 1991
Subject Category
Earth Resources And Remote Sensing
Meeting Information
Meeting: IGARSS ''91: Annual International Geoscience and Remote Sensing Symposium