سال انتشار: ۱۳۹۱
محل انتشار: کنفرانس بین المللی مدل سازی غیر خطی و بهینه سازی
تعداد صفحات: ۱۲
Mehdi Darbandi – Department of Electrical Engineering and Computer Science at Iran University of Science and Technology (IUST);
Mohammad Abedi –
Constructing new professional and intelligence aircraft or spacecraft with integrated navigation and control systems that can complete flight tasks iscomplicate and in most of the cases it involves with integrating information from multiple sensors and other measurement devices to estimate the state(condition, direction) and velocity of the vehicle. This article explains a way, in which an aircraft can fly from a starting point to a predetermined targetprecisely using vision only method. Using visiononly to control an aircraft represents a unique challenge, partially because the high rate of imagesrequired in order to maintain tracking and to keep the aircraft on target in a moving air mass. Second, absolute distance and angle measurements to thetarget are not readily available when the aircraft does not have independent measurements of its own position. The method presented here uses anintegral image representation of the video input for the analysis. The integral image, which is obtained by integrating the pixel intensities across the image, is reduced to a probable target location by performing a cascade of feature matching functions.The cascade is designed to eliminate the majority ofthe potential targets in a first pruning using computationally inexpensive process. Then, themore exact and computationally expensiveprocesses are used on the few remaining candidates; thereby, dramatically decreasing the processingrequired per image. The navigation algorithmspresented in this paper use a Kalman filter to estimate attitude and glide slope required based onmeasurements of the target in the image. Theeffectiveness of the algorithms is demonstrated through simulation of a small glider instrumentedwith only a simulated camera.