Neural Networks in Speckle Reduction of Sar Data for Landuse Mapping : Microwave Remote Sensing, Satellites, Artificial Neural Networks & Speckle Reduction: Concepts and Applications

Over the recent years, remote sensing has been extensive in the field of sciences drawing from many areas for support and development. It depends greatly on the support of governments and private industries worldwide. Satellite and digital imagery play an important role in remote sensing; providing information about the land use activities.The remotely sensed data is now available in various wavelength ranges from a large number of satellites orbiting the earth. The main characteristics of remotely sensed data are spatial, spectral, radiometric and temporal resolutions. Spectral and radiometric resolutions have also been improved. This has resulted in tremendous amount of data to be handled and processed. The main objective of the studies is to develop methods for reducing speckle in SAR data mainly by ANN, also by utilizing spectral and spatial attributes and statistical approach. A critical review is carried out pertaining to various aspects of SAR data analysis, such as, speckle reduction in SAR images, speckle reduction using first order statistics, classification methods, their application for SAR data analysis and advantages in speckle reduction of SAR data.