Approach to reach high range resolution by using neural networks

For automatic target recognition, especially on high resolution radars, range profiles are very important, because they can be used to describe the accurate geometric shape and structural features of targets, and can be obtained in a few periods of pulse, and then, the real-time data processing realized easily. However, the traditional algorithms can not give us satisfactory resolution. In this paper, neural networks are used to reach high range resolution, and recognize these range profiles.