Abstract :
Recently we proposed a wavelet-based dynamic range compression algorithm to improve the visual quality of digital images captured in the high dynamic range scenes with nonuniform lighting conditions. The fast image enhancement algorithm which provides dynamic range compression preserving the local contrast and tonal rendition is a very good candidate in aerial imagery applications such as image interpretation for defense and security tasks.
This algorithm can further be applied to video streaming for aviation safety. In this project the latest version of the proposed algorithm which is able to enhance aerial images so that the enhanced images are better then direct human observation, is presented. The results obtained by applying the algorithm to numerous aerial images show strong robustness and high image quality.
Aerial images captured from aircrafts, spacecrafts, or satellites usually suffer from lack of clarity, since the atmosphere enclosing Earth has effects upon the images such as turbidity caused by haze, fog, clouds or heavy rain. The visibility of such aerial images may decrease drastically and Sometimes the conditions at which the images are taken may only lead to near zero visibility even for the human eyes. Even though human observers may not see much than smoke, there may exist useful information in those images taken under such poor conditions. Captured images are usually not the same as what we see in a real world scene, and are generally a poor rendition of it.
High dynamic range of the real life scenes and the limited dynamic range of imaging devices results in images with locally poor contrast. Human Visual System (HVS) deals with the high dynamic range scenes by compressing the dynamic range and adapting locally to each part of the scene. There are some exceptions such as turbid (e.g. fog, heavy rain or snow) imaging conditions under which acquired images and the direct observation possess a close parity .The extreme narrow dynamic range of such scenes leads to extreme low contrast in the acquired images.