Position Identification Using Image Processing for UAV Flights in Martian Atmosphere

This paper presents a method for the position identification of an unmanned aerial vehicle (UAV) in Martian atmosphere future. It uses image processing craters captured via onboard camera UAV and database images. The is composed two processes: individual crater detection using cascade object detector recognition Taguchi (RT)-method. In detection, objects with shapes that resemble are detected regardless their positions, positions multiple identified criterion variable D * , which normalized Mahalanobis distance. calculated from several feature variables expressing area ratios relative RT-method.