Airport Detection Base on Support Vector Machine from A Single Image

Abstract

Airport is one of the key transportation targets. Airport detection is very important in military and civil fields. A novel method to detect airports from a single image is proposed in this paper. It combines texture features with shape features, and uses support vector machine as a classification function. Canny edge detector is firstly used, then short lines and curves are removed, and long straight lines are detected by Hough transform, at last the airport runways are discriminated by support vector machine. The experimental results demonstrate the efficacy of the proposed automatic airport-detection method