Research of FOD Recognition Based on Gabor Wavelets and SVM Classification

Foreign Object Debris (FOD) on civilian and military runways threatens lives, disrupts service and causes billions of dollars in aircraft engine damage annually. Currently, most of the FOD monitoring is still done by man, which is inefficient and unreliable. This paper proposed a novel framework for Foreign Object Debris (FOD) detection on the runway surface based on Gabor wavelets and Support Vector Machine (SVM). The proposed system is carried by a vehicle. The framework has three steps. In the first step, the FOD is detected from the runway. In the second step, Gabor wavelets are used to extract features. In the third step, when the Gabor features were obtained, classifications were done by Support Vector Machine (SVM). Experiment results showed that the proposed framework is effective and accurately.