PROJECT TITLE :
A New Geostatistical Solution to Remote Sensing Image Downscaling
The availability of the panchromatic (PAN) band in remote sensing images gives birth to so-known as image fusion techniques for increasing the spatial resolution of images to that of the PAN band. The spatial resolution of such spatially sharpened images, such as for the MODIS and Landsat sensors, however, could not be sufficient to produce the desired detailed land-cover/land-use info. This paper proposes an space-to-purpose regression kriging (ATPRK)-based geostatistical answer to increase the spatial resolution of remote sensing pictures beyond that of any input images, as well as the PAN band. The new approach could be a 2-stage approach, together with covariate downscaling and ATPRK-based image fusion. The new approach treats the PAN band as the covariate and takes blessings of its textural data. It explicitly accounts for the scale of support, spatial correlation, and the point unfold perform of the sensor and has the characteristic of perfect coherence with the initial coarse information. Moreover, the new downscaling approach can be extended readily by incorporating different ancillary info. The proposed approach was examined using both Landsat and MODIS images. The results show that it can turn out a lot of correct sharpened images than four benchmark approaches.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here