DATA FUSION APPROACH TO IMPROVE FOREST COVER CLASSIFICATION USING SAR IMAGERY

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" DATA FUSION APPROACH TO IMPROVE FOREST COVER CLASSIFICATION USING SAR IMAGERY "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149901
Doc. No	:	ET21693
Main Entry	:	Cheng Zhu
Title Proper	:	DATA FUSION APPROACH TO IMPROVE FOREST COVER CLASSIFICATION USING SAR IMAGERY
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	interferometry coherence, backscatter, and texture information from JERS-1synthetic aperture radar (SAR) data were investigated for discriminating generalforest types (i.e., hardwood, mixed, and softwood) in the northeastern United States.The JERS-1 SAR data was then fused with Landsat 7 Enhanced Thematic MapperPlus (ETM+) imagery to improve forest cover classification using artificial neuralnetworks (ANNs) approaches. The study used two ANN classifiers, multi-layerperceptron network (MLP) and learning vector quantizer (LVQ), to apply the datafusion both in pixel level and decision level. Conventional statistical classifiermaximum likelihood (ML) classifier and ANN classifiers were also applied to theindividual imagery for comparison.Statistical analysis showed that the combination of interferometry coherence,backscatter, and texture information of JERS-1 SAR data (called Enhanced JERS-l(EJERS-1) imagery)..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL44875.pdf
Title and statement of responsibility and	:	DATA FUSION APPROACH TO IMPROVE FOREST COVER CLASSIFICATION USING SAR IMAGERY [Thesis]