Title :
Comparison and improvement of Dempster-Shafer models
Author :
Abdellatif, B. ; Boudraa, A.O. ; Osswald, C. ; Boucher, JM
Author_Institution :
Nat. Authority for Remote Sensing & Space Sci., Cairo, Egypt
Abstract :
In this paper, a performance comparison of different classification algorithms based on the evidence theory of Dempster-Shafer will be presented. The comparison is illustrated on Landsat Multispectral Scanner (Landsat MSS) data whose ground truth is provided. A modification of the Denoeux´s model [1] is proposed showing better and more stable classification results of the Landsat MSS data.
Keywords :
inference mechanisms; pattern classification; sensor fusion; Dempster-Shafer models; classification algorithms; evidence theory; landsat MSS data; landsat multispectral scanner; multisensor data fusion; Accuracy; Bayesian methods; Earth; Probabilistic logic; Remote sensing; Satellites; Training;
Conference_Titel :
Intelligent Signal Processing (WISP), 2011 IEEE 7th International Symposium on
Conference_Location :
Floriana
Print_ISBN :
978-1-4577-1403-0
DOI :
10.1109/WISP.2011.6051696
