Aerial target recognition based on Zernike moments of information fusion

Based on OpenGL and Google library we established the target model library and the canny operator is used for edge detection. Combined with D-S evidence theory and Pseudo-Zernike moments, the air target recognition algorithm based on information fusion is proposed. Pseudo-Zernike moments are invariant to rotation, translation and scale invariance and easy to construct high order moment, compared with the Hu moment redundancy small, and not easy to affect by noise. The D-S theory of evidence solved the conflict absorption which make the result more reliable. The reliability and robustness of the method are verified by the simulation experiment of the target image in Gauss noise