Aircraft recognition based on feature points and invariant moments

Abstract

As the development of remote sensing satellite technology, the target recognition technology based on remote sensing image has become possible. The technology of remote sensing image can be widely used in military, science and technology, civil and other fields. At present, many scholars at home and abroad have done some research and made some progress. But in the actual research, remote sensing images have a variety of factors, such as background noise, occlusion, weather changes, the aircraft target recognition is very difficult, so how to improve the existing aircraft recognition accuracy and anti-jamming capability is the research focus. This paper presents an aircraft identification algorithm based on Harris-laplace corner, Zernike moments and Color invariant moments. The experimental results show that the proposed algorithm is able to identify a variety of aircraft targets, and its recognition accuracy is better than the reference.