This research focuses on the application of Machine Vision (MV) techniques and algorithms to the problems of Autonomous Aerial Refueling (AAR) and Runway Detection. In particular, real laboratory based hardware was used in a simulated environment to emulate real-life conditions for AAR. It was shown that the K-Means Clustering Algorithm solution to the Marker Detection problem could be executed at a frame rate of 30 Hz and it averaged a tracking error of less than one pixel while utilizing only 0.16% of the image. It was also shown that the solution to the Runway Detection problem could be executed at a frame rate of 20 Hz which is acceptable for use in an UAV performing reconnaissance work. Data from these tests suggest that both software schemes are suitable for applications in moving vehicles and that the accuracy of the measurements produced by the schemes make them suitable for UAV applications. iii ACKNOWLEDGEMENTS First, I would like to thank Dr. Marcello Napolitano for his knowledge, guidance, and support throughout my life as a graduate student. You will certainly not be forgotten. I would also like to thank my colleagues Dr. Brad Seanor, Dr. Yu Gu, Dr. Giampiero Campa, Srikanth Gururajan, and Peter Cooke for the knowledge and guidance they gave me in completing this research. All seriousness aside, I would like to thank the group for all of the camaraderie, good times, and bad times we had in completing the Autonomous Formation Flight project. That is and will always be a memorable time in my life.