Automated detection of lunar craters based on object-oriented approach

The object-oriented approach is a powerful method in making classification. With the segmentation of images to objects, many features can be calculated based on the objects so that the targets can be distinguished. However, this method has not been applied to lunar study. In this paper we attempt to apply this method to detecting lunar craters with promising results. Craters are the most obvious features on the moon and they are important for lunar geologic study. One of the important questions in lunar research is to estimate lunar surface ages by examination of crater density per unit area. Hence, proper detection of lunar craters is necessary. Manual crater identification is inefficient, and a more efficient and effective method is needed. This paper describes an object-oriented method to detect lunar craters using lunar reflectance images. In the method, many objects were first segmented from the image based on size, shape, color, and the weights to every layer. Then the feature of “contrast to neighbor objects” was selected to identify craters from the lunar image. In the next step, by merging the adjacent objects belonging to the same class, almost every crater can be taken as an independent object except several very big craters in the study area. To remove the crater rays diagnosed as craters, the feature of “length/width” was further used with suitable parameters to finish recognizing craters. Finally, the result was exported to ArcGIS for manual modification to those big craters and the number of craters was acquired.