A Classification and Recognition Method for Underwater Static Targets

Abstract

The invention relates to a method for classifying and identifying underwater static targets. The method comprises: step 1) receiving an echo pulse signal of the target by a transducer array of an active sonar; step 2) determining an observation area, performing band-pass filtering and multi-stage amplification, Obtain time domain x(t); perform FFT processing to obtain frequency domain X(f); perform high-resolution beamforming on X(f) to obtain frequency domain beam Y(θ, f); Step 3) obtain the output of matched filtering Z(θ, f); Step 4) Perform IFFT processing on Z(θ, f) to obtain the high-resolution azimuth spectrum z(θ, t) at each time point, and use it as a training sample; Step 5) Perform amplitude filtering to obtain the training set to be checked; Step 6) adopt K-means clustering method to classify; Step 7) sort by the order of mean value from small to large; only the K-th label with the largest mean value is processed, step 8) Calculate the mean of the standard deviation of the azimuth spectrum of the target to be classified in the K-th label E{std θ (z(t n ))}, further classify the K-th label obtained in step 7) to distinguish the lighthouse and the target.

Description

technical field [0001] The invention belongs to the technical field of classification and recognition of underwater targets, and in particular relates to a method for classification and recognition of static underwater targets. Background technique [0002] Underwater target classification and recognition is to extract target features from signals received by underwater sensors and perform classification and recognition. This is the core of the sonar system and a prerequisite for ocean exploration, monitoring and underwater acoustic countermeasures. However, due to the complex underwater environment, how to accurately identify targets has always been a difficult problem. [0003] In the shallow sea environment, the underwater acoustic channel has complex time-space-frequency characteristics. Due to the strong submarine reverberation and strong correlation with the transmitted signal, the performance of the sonar is severely restricted by the reverberation. Reverberation can...

AI Technical Summary

Problems solved by technology

[0007] The object of the present invention is that, in order to solve the above-mentioned defects in the existing classification and recognition methods, the present invention proposes a classification and recognition method for underwater static targets, which solves the problem that the existing sonar platform has a low detection probability for underwater static targets and is difficult to detect. The problem of distinguishing from strong interference signals such as lighthouses; according to the energy difference of reverberation, lighthouses, and floating targets and the difference in azimuth spectrum in the vertical direction, automatic classification of the three types of signals such as reverberation, lighthouses, and floating targets can be realized

Images