Open AccessSurface segmentation and environment change analysis using band ratio phenology index method – supervised aspect
Author(s) -
Sivabalan K.R.,
Ramaraj E.
Publication year - 2020
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.6526
Subject(s) - multispectral image , remote sensing , confusion matrix , computer science , vegetation (pathology) , cohen's kappa , phenology , earth observation , confusion , segmentation , environmental science , multispectral pattern recognition , index (typography) , field (mathematics) , normalized difference vegetation index , climate change , artificial intelligence , machine learning , geography , ecology , mathematics , satellite , medicine , psychology , pathology , aerospace engineering , world wide web , psychoanalysis , engineering , biology , pure mathematics
Remote sensing is an escalating field that helps to monitor the earth in different perspectives like vegetation assessment, coastal studies, global warming analysis etc. Presently many satellites are orbiting the earth for taking multispectral imagery, which is working behind the principle remote sensing applications. Though there are mechanisms for image classification still innovative method is required to detect and monitor the physical characteristics of the environment. Weather forecasting, ecology assessment and irrigation management are relying upon the seasonal changes. This research study concentrates on seasonal change analysis by supervised image classification called Band Ratio Phenology Index (BRPI) method. This BRPI has helped to learn seasonal impact on the environment for the last six years. Confusion Matrix, Overall Accuracy, and Kappa Coefficient are the quality measures used to legitimise the classification exactness.