Automatic Feature Extraction for Panchromatic Mars Global Surveyor Mars Orbiter Camera Imagery

摘要

The Mars Global Surveyor Mars Orbiter Camera (MOC) has produced tens of thousands of images, which contain a wealth of information about the surface of the planet Mars. Current manual analysis techniques are inadequate for the comprehensive analysis of such a large dataset, while development of handwritten feature extraction algorithms is laborious and expensive. This project investigates the application of an automatic feature extraction approach to analysis of the MOC narrow angle panchromatic dataset, using an evolutionary computation software package called Genie. Genie uses a genetic algorithm to assemble feature extraction tools from low-level image operators. Each generated tool is evaluated against training data provided by the user. The best tools in each generation are allowed to "reproduce" to produce the next generation, and the population of tools is permitted to evolve until it converges to a solution or reaches a level of performance specified by the user. Craters are one of the most scientifically interesting and most numerous features in the MOC data set, and present a wide range of shapes at many spatial scales. We now describe preliminary results on development of a crater finder algorithm using the Genie software.