The adaptive constant false alarm rate for sonar target detection based on back propagation neural network access

Abstract With oceanic reverberation and a large amount of data being the main sources interference for underwater acoustic target detection, it is difficult to obtain more robust detection performance by relying on traditional constant false alarm rate (CFAR) method. An adaptive sonar CFAR method based back propagation (BP) neural network proposed. The combines artificial intelligence algorithm algorithm, uses classification ability select which can effectively improve adaptation environment control ability. This BP train echo signal complete clutter background establish recognition set. According output result each classification, best detector selected from four CA/SO/GO/OS‐CFAR detectors detect target. simulation results show proposed in uniform environment, multi‐target edge environment. that adaptability strong different backgrounds, further improves alarms under non‐uniform background.