Effect of Spectral/Spatial Transformation on Remote Sensing Image for NDVI-Based Drought Detection Analysis

Remote sensing image have been known to be an important part for environmental analysis. Drought early warning system is one of the few example of remote sensing image applications. One of the oldest tool in remote sensing studies, NDVI is often used for drought detection. Although very essential, remote sensing image requires large storage requirement. A large image data may cause network congestion which certainly affects the aptitude of the drought detection system. An image compression may be used as an approach to this issue. However, this would lead to another issue, image quality. This article emphasize on the effect of image compression through transformation towards remote sensing image. Analysis is conducted through NDVI pixel threshold as well as other complimentary error metric method. Hybrid methods of transformation are presented here for the image transformation process. The experiments performed on test images shows that hybrid transformation is capable of reducing image data and preserving sufficient quality.