Region-based remote-sensing image compression in the wavelet domain

This paper argues that texture regions in remotely sensed images of the Earth are often of no interest to projects for example, concerned with agricultural applications. These regions require a large number of bits to be encoded. It is proposed that they can be identified using a generic algorithm that identifies the boundaries of textured regions irrespective of their class, and removed from the encoding process. The rest of the regions which may be of interest to the specific application, may be encoded using 1D wavelet transform applied to the string of pixels created by raster scanning the region. This approach can help remove the bottleneck of image down-loading from micro-satellites in low Earth orbits, because these satellites can obtain hundreds of images in an orbit but they can only download a few of them during each pass over the tracking station. The proposed approach can be fully implemented for on-board image preprocessing before the down-loading, for cases that urban and forest regions (textured regions) in the images are of no interest.