Application For Shadow Removal From Geo Eye-1 RGB Composition

Shadow is a phenomenon that can’t be avoided and the effects are evident in high resolution images. Humans easily identify shadows, but it is harder to automatically recognize them with detection algorithm because there are a lot of factors that can influence the quality of the result. In this paper the problem of shadow detection and removal is treated for multispectral data of the GeoEye-1 satellite (geometric resolution: 2 m; bands: Blue, Green, Red, Near Infrared). The considered scene includes urban area where shadows originated by buildings and trees are present. An index, named RATIO, is computed using Near Infrared and Blue bands to highlight the affected areas in the images. To restore the luminance of shadow zones the radiometric enhancement technique named Gamma Correction is used