Aiming at the difficulty of target location and classification in low altitude surveillance and anti Unmanned Aerial Vehicle(UAV) system. This paper mainly studies the recognition algorithm of low-altitude UAV. First, the UAV image is preprocessed, and candidate partial images of different sizes and positions are generated through a sliding window, and the moment invariant features of the image are extracted. Then, the neural network is used to train the image, and the support vector machine classifier is used to classify the aircraft, and then the recognition and classification algorithm of the aircraft target in the low-altitude airspace are finished. Based on the theoretical algorithm research, this paper uses MATLAB software to simulate and analyze the aircraft recognition algorithm, and the accuracy is more than 90%. The results show that the research algorithm can be used for UAV recognition and low-altitude aircraft classification.
Low-altitude UAV Recognition and Classification Algorithm Based on Machine Learning Ershen Wang、Wansen Shu、Junjie Zhu、Song Xu、Pingping Qu、Tao Pang