Automatic Extraction of Planetary Image Features and Multi-Sensor Image Registration

Many automatic feature extraction methods have been proposed and utilized for Earth remote sensing images, but these methods are not always applicable to Lunar data that often present low contrast and uneven illumination characteristics. The boundary of Lunar features is not always well defined, and it is therefore somewhat difficult to segment and characterize Lunar images. With the large quantity of new Lunar data that will be collected in the next few years, it is important to implement an automated method to extract these features, and to perform tasks such as image registration. This technology can be generalized for commercial applications with similar restraints such as medical imaging, where low contrast and uneven illumination image characteristics often pose issues.