Abstract: A radar plots classification method based on back propagation (BP) neural network is proposed to solve the problem of a lot of clutter after target detection in complex electromagnetic environment of radar detection. This method can further distinguish target points and clutter points after target detection, and improve the quality of target tracking. In this paper, BP neural network is trained and compared with K nearest neighbor method and support vector machine, it is found that the classification accuracy of this method is up to 87. 3% , which is 19. 6% and 7. 6% higher than latter two methods. The experimental results show that the radar plots classification method based on BP neural network is effective.