A neural network-based detection thresholding scheme for active sonar signal tracking

Intensity thresholding is an effective technique to cut off the low energy noises and cut down the computational load in an underwater target tracking system. A neural network based adaptive intensity thresholding scheme with a constant false alarm rate (CFAR) for an active sonar signal tracking situation in a realistic sea environment is proposed in this paper. The proposed system has the following advantages: (1) It performs well in a nonhomogenous sea environment; the false alarm rate is kept constant while the threshold changes with different sea environments; (2) It can adaptively estimate the threshold for different range cells because the noise under estimation is strictly local so that the received intensities of noise and targets are not affected by the distance they travel; and (3) The computational requirements are moderate.