Two-dimensional matched filtering feature extraction and classification detection of active sonar echo

ZHAO Meng; WANG Wenbo; REN Qunyan; XIAO Xu; MA Li; YU Yun

doi:10.12395/0371-0025.2023030

Volume 49 Issue 4

Jul. 2024

Turn off MathJax

Article Contents

Abstract

References

ACTA ACUSTICA > 2024 > 49(4): 731-742. > DOI: 10.12395/0371-0025.2023030 CSTR: 32049.14.11-2065.2023030

ZHAO Meng, WANG Wenbo, REN Qunyan, XIAO Xu, MA Li, YU Yun. Two-dimensional matched filtering feature extraction and classification detection of active sonar echo[J]. ACTA ACUSTICA, 2024, 49(4): 731-742. DOI: 10.12395/0371-0025.2023030

Citation:

PDF (2011 KB)

Two-dimensional matched filtering feature extraction and classification detection of active sonar echo

ZHAO Meng^{1, 2, 3,},
WANG Wenbo^{1, 2, 3},
REN Qunyan^{1, 2, 3, ,},
XIAO Xu^{1, 2, 3},
MA Li^{1, 2, 3},
YU Yun⁴

1.
Institute of Acoustics, Chinese Academy of Sciences　Beijing　100190
2.
Key Laboratory of Underwater Acoustic Environment, Chinese Academy of Sciences　Beijing　100190
3.
University of Chinese Academy of Sciences　Beijing　100049
4.
People’s Liberation Army of China, Naval Research Academy　Beijing　100161

More Information

PACS:
Received Date: February 27, 2023
Revised Date: September 19, 2023

Graphical Abstract

Abstract

Abstract

To reduce the clutter false alarm in active sonar echo detection, and enhance the echo detection rate while maintaining a low false alarm rate, a classification detection method based on the two-dimensional matching filter (2D-MF) is proposed. This method divides the matched signal into multiple sub-signals with appropriate pulse widths, and the sub-signals are used to respectively perform the matched filtering and extract the 2D-MF features from the active sonar received data. The extracted 2D-MF features utilize the time-frequency information and matching gain simultaneously. The convolutional neural network is then employed as the echo detector, effectively distinguishing between echo signals and clutter signals. Simulation and experimental results demonstrate that this method significantly improves the echo detection rate while maintaining a low false alarm rate in shallow-water channels. Specifically, it achieves an echo detection rate of 91.30% with a false alarm rate of 1‰ for the at-sea measured data, representing an approximate 4% improvement compared to existing methods.
- Echo detection,
- Clutter signal,
- Low false alarm,
- Two-dimensional matched filtering,
- Convolutional neural network

FullText(HTML)

References (22)

References

[1]	黄海宁, 李宇. 水声目标探测技术研究现状与展望. 中国科学院院刊, 2019; 34(3): 264−271 DOI: 10.16418/j.issn.1000-3045.2019.03.003
[2]	李启虎. 声呐信号处理引论. 北京: 科学出版社, 2012: 108−111
[3]	朱埜. 主动声呐检测信息原理. 北京: 海洋出版社, 2014: 98−100
[4]	Farina A, Studer F A. A review of CFAR detection techniques in radar systems. Microw. Mag., 1986; 29: 115 DOI: 10.1109/JLT.1986.1074902
[5]	Conte E, De Maio A, Galdi C. CFAR detection of multidimensional signals: An invariant approach. IEEE Trans. Signal Process., 2003; 51(1): 142−151 DOI: 10.1109/TSP.2002.806554
[6]	Gorman R P, Sejnowski T J. Analysis of hidden units in a layered network trained to classify sonar targets. Neural Netw., 1988; 1(1): 75−89 DOI: 10.1016/0893-6080(88)90023-8
[7]	Shin F B, Kil D H, Wayland R F. Active impulsive echo discrimination in shallow water by mapping target physics-derived features to classifiers. IEEE J. Oceanic Eng., 1997; 22(1): 66−80 DOI: 10.1109/48.557541
[8]	Young V W, Hines P C. Perception-based automatic classification of impulsive-source active sonar echoes. J. Acoust. Soc. Am., 2007; 122(3): 1502−1517 DOI: 10.1121/1.2767001
[9]	Bu M, Benenb S, Krausc D, et al. Feature selection and classification for false alarm reduction on active diver detection sonar data. 4th International Conference on Underwater Acoustics, Papadakis, Greece, 2017
[10]	Yang H, Byun S H, Lee K, et al. Underwater acoustic research trends with machine learning: Active SONAR applications. J. Ocean Eng. Technol., 2020; 34(4): 277−284 DOI: 10.26748/KSOE.2020.018
[11]	Testolin A, Kipnis D, Diamant R. Detecting submerged objects using active acoustics and deep neural networks: A test case for pelagic fish. IEEE Trans. Mobile Comput., 2020; 21(8): 2776−2788 DOI: 10.1109/TMC.2020.3044397
[12]	Choo Y, Lee K, Hong W Y, et al. Active underwater target detection using a shallow neural network with spectrogram-based temporal variation features. IEEE J. Oceanic Eng., 2024; 49(1): 279−293 DOI: 10.1109/JOE.2022.3164513
[13]	Berg H, Hjelmervik K T. Classification of anti-submarine warfare sonar targets using a deep neural network. OCEANS 2018 MTS, IEEE, Charleston, USA, 2018: 1−5
[14]	Bu M, Benenb S, Krausc D, et al. False alarm reduction for active sonars using deep learning architectures. Undersea Defence Technology (UDT) 2019, Stockholm, Sweden, 2019
[15]	伍飞云, 童峰. 双扩展水声信道的时延多普勒域稀疏估计. 声学学报, 2018; 43(4): 546−555 DOI: 10.15949/j.cnki.0371-0025.2018.04.014
[16]	刘伯胜, 雷家煜. 水声学原理. 科学出版社, 2019: 84−95
[17]	李启虎. 声呐信号处理引论. 北京: 科学出版社, 2012: 114−115
[18]	Baggenstoss P M. On detecting linear frequency-modulated waveforms in frequency- and time-dispersive channels: Alternatives to segmented replica correlation. IEEE J. Oceanic Eng., 1994; 19(4): 591−598 DOI: 10.1109/48.338395
[19]	Friedlander B, Zeira A. Detection of broadband signals in frequency and time dispersive channels. IEEE Trans. Signal Process., 1996; 44(7): 1613−1622 DOI: 10.1109/78.510610
[20]	Porter M B. The BELLHOP manual and user’s guide: Preliminary draft. Ocean Acoustics Library, Heat, Light, and Sound Research, Inc. , La Jolla, CA, USA, 2011
[21]	Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn Res., 2014; 15(1): 1929−1958 DOI: 10.5555/2627435.2670313
[22]	Kingma D P, Ba J. Adam: A method for stochastic optimization. International Conference on Learning Representations, 2014

Cited By

Cited by

Periodical cited type(0)

Other cited types(2)

Get Citation

PDF

XML

Article Metrics

Article views (128) PDF downloads (59) Cited by(2)

Two-dimensional matched filtering feature extraction and classification detection of active sonar echo

Abstract

References

Cited by

Periodical cited type(0)

Other cited types(2)

Catalog

Article Metrics

Related

Two-dimensional matched filtering feature extraction and classification detection of active sonar echo

Abstract

References

Cited by

Periodical cited type(0)

Other cited types(2)

Catalog

Article Metrics

Related

Export File

Citation

Format

Content