A Low-Slow-Small Target Detection Method for Offshore Radar Based on GPU

Abstract

In recent years, the detection of low-slow-small targets by offshore radar has become a key issue to be solved urgently. This paper analyzes the echo characteristics of the sea clutter and the target, by extracting the features of the target and sea clutter, the feature detector is used to realize the classification of the target and the clutter, and then extract the target information. In addition, the method in this paper is implemented by GPU to increase the computing speed. The method in this paper is verified by the measured data of a Ku-band offshore radar. It has a higher detection capability than traditional CFAR, and the GPU processing speed meets engineering requirements, realizing the real-time detection of the target by the radar.