Evaluation of various classification techniques for land use, land cover with special reference to urban mapping

Remotely sensed data is a valuable and efficient tool to update land cover/ land use maps. This is in-fact one of the most common uses of multi-spectral satellite images. Land use and land cover are essential components in understanding the human interactions with the environment. While land cover refer's to that which covers the earth's surface, land use gives a description as to how the land cover has been modified. The ASTER sensor, an optical remote sensor onboard NASA's Earth observing satellite Terra comprises of 14 spectral bands. These bands range from visible to thermal infrared region. These multi-spectral bands enable the sensor to provide data for a detailed land use classification of heterogeneously covered areas. This study evaluates the potential of ASTER data for land use, land cover classification of an upcoming urban area and also to identify the best classification technique. Assessment of accuracy of each method was performed using ground truth field investigation. © 2012 Cafet-Innova Technical Society.