Remote sensing provides us with a continuous and constant source of information about the Earth, and geographic information systems (GIS) are a methodology for handling all of this geographic data.
Concept 1: Digital image classification uses the spectral information represented by the digital numbers in one or more spectral bands, and attempts to classify each individual pixel based on this spectral information. This type of classification is termed spectral pattern recognition.
Three levels of remote sensing image classification: (a) pixel-level remote sensing image classification focuses on labeling each pixel with a class; (b) object-level remote sensing image classification aims at recognizing objects in remote sensing images; (c) scene-level remote sensing image classification seeks to classify each given remote sensing image patch into a semantic class.
The land use/land cover classification scheme consists of Level‐I: 8 classes, Level‐II: 31 classes, and Level‐III: 54 classes (NRSC, 2012).
This post focuses on pixel-level remote sensing image classification.
For More Visit: www.agsrt.com