One-dimensional deep convolution network underwater multi-target recognition method

Abstract

The invention provides a one-dimensional deep convolution network underwater multi-target recognition method. A 6dB / frequency doubling one-order digital filter is adopted to enhance a high-frequency part to enable a signal spectrum to be flattened; a window function is selected to intercept signals, and signals with the duration of 170 ms are acquired as the best input frame length for a convolutional neural network; the one-dimensional deep convolution network is adopted to carry out feature extraction on sound signals; a training sample set is used for learning the convolution network to obtain network structure parameters with the best features; and an extreme learning machine is selected to carry out classification and recognition on output features of the convolution network. the deep convolution network in the deep learning is used for carrying out feature extraction on the sound signals, the traditional manual feature extraction is replaced, the automatically-extracted sound features contain richer recognition information, the extreme learning machine is used for carrying out classification and recognition on features automatically extracted by the convolution network, features different from those obtained in the traditional manual analysis mode can be effectively found out, and the underwater sound signal recognition rate is improved.

Description

technical field [0001] The invention relates to a pattern recognition method, in particular to a feature extraction and multi-object classification recognition method of underwater sound signals. Background technique [0002] Acoustic signals are the main form of energy that can be transmitted over long distances underwater, and sonar is also the most effective means of underwater detection. The classification and identification of underwater acoustic signals is the focus of underwater acoustic signal research, and the development of underwater acoustic identification has experienced the development of automatic identification of underwater targets from the most traditional sonar personnel. The research on underwater sound signals first started in developed western countries. Although our country started late in the field of underwater sound recognition, some breakthroughs have been made through the efforts of scientific researchers. Mainly through the time-frequency conve...

AI Technical Summary

Problems solved by technology

[0003] At present, the research in the field of underwater multi-target recognition is based on traditional methods, and the use of deep learning is mainly concentrated in the field of speech recognition. There is no relevant literature on the use of deep convolutional networks for target recognition of acoustic signals.

Images