The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지
DOI QR코드

DOI QR Code

Lofargram analysis and identification of ship noise based on Hough transform and convolutional neural network model

허프 변환과 convolutional neural network 모델 기반 선박 소음의 로파그램 분석 및 식별

  • 조준범 (국방대학교 국방과학학과) ;
  • 하용훈 (국방대학교 국방과학학과)
  • Received : 2023.09.14
  • Accepted : 2023.11.13
  • Published : 2024.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a method to improve the performance of ship identification through lofargram analysis of ship noise by applying the Hough Transform to a Convolutional Neural Network (CNN) model. When processing the signals received by a passive sonar, the time-frequency domain representation known as lofargram is generated. The machinery noise radiated by ships appears as tonal signals on the lofargram, and the class of the ship can be specified by analyzing it. However, analyzing lofargram is a specialized and time-consuming task performed by well-trained analysts. Additionally, the analysis for target identification is very challenging because the lofargram also displays various background noises due to the characteristics of the underwater environment. To address this issue, the Hough Transform is applied to the lofargram to add lines, thereby emphasizing the tonal signals. As a result of identification using CNN models on both the original lofargrams and the lofargrams with Hough transform, it is shown that the application of the Hough transform improves lofargram identification performance, as indicated by increased accuracy and macro F1 scores for three different CNN models.

본 논문은 Convolutional Neural Network(CNN) 모델을 이용하여 선박 소음의 로파그램 분석을 통한 선박 식별 시 허프 변환을 적용함으로써 성능을 향상시키는 방안을 제안한다. 수동소나에 수신된 신호를 처리하면 시간-주파수 영역인 로파그램이 생성된다. 로파그램에는 선박이 방사하는 기계류 소음이 토널 신호로 나타나고 이를 분석하면 선박의 클래스를 특정할 수 있다. 그러나 로파그램의 분석은 숙달된 인원에 의해 진행되는 전문적이고 오랜 시간이 소요되는 작업이다. 또한, 로파그램에는 수중환경 특성 상 다양한 배경소음이 같이 전시되기 때문에 표적 식별을 위한 분석이 매우 어렵다. 이 문제를 해결하기 위해 로파그램에 허프 변환을 적용하여 선을 추가함으로써 토널 신호를 강조하였다. 원본 로파그램과 허프 변환을 적용한 로파그램에 대해 CNN 모델을 이용해 식별을 시도한 결과, CNN 모델의 정확도와 매크로 F1 점수를 통해 허프 변환을 적용한 것이 로파그램 식별 성능을 향상시켰음을 보여주었다.

Keywords

References

  1. R. J. Urick, Principles of Underwater Sound (McGrawHill, New York, 1975), pp. 299-310.
  2. N. N. de Moura, J. M. de Seixas, and R. Ramos, "Passive sonar signal detection and classification based on independent component analysis," in Sonar Systems, edited by N. Z. Kolev (InTech, Available from: https://www.intechopen.com/chapters/18872, 2011).
  3. J. Park and D.-J. Jung, "Deep convolutional neural network architectures for tonal frequency identification in a lofargram," Int. J. Control Autom. Syst. 19, 1103-1112 (2020). https://doi.org/10.1007/s12555-019-1014-4
  4. D. W. Kim, J. W. Seok, and K. S. Bae, "Target/non-target classification using active sonar spectrogram image and CNN" (in Korean), J. IKEEE, 22, 1044-1049 (2018).
  5. D. S. Dominguez, S. T. Guijarro, A. C. Lopez, and A. P. Gimenez, "ShipsEar: An underwater vessel noise database," Appl. Acoust. 113, 64-69 (2016). https://doi.org/10.1016/j.apacoust.2016.06.008
  6. M. Irfan, Z. Jiangbin, S. Ali, M. Iqbal, Z. Masood, and U. Hamid, "DeepShip: an underwater acoustic benchmark dataset and a separable convolution based auto-encoder for classification," Expert Syst. Appl. 183, 115270 (2021).
  7. K. M. Park and D. Kim, "Preprocessing performance of convolutional neural networks according to characteristic of underwater targets" (in Korean), J. Acoust. Soc. Kr. 41, 629-636 (2022).
  8. H. Yang, H. Gu, J. Yin, and J. Yang, "GAN-based sample expansion for underwater acoustic signal," J. Phys. Conf. Ser. 1544, 012104 (2020).
  9. Q. Yao, Y. Wang, and Y. Yang, "Underwater acoustic target recognition based on data augmentation and residual CNN," Electronics, 12, 1206 (2023).
  10. Y. C. Jung, B. U. Kim, S. K. An, W. J. Seong, K. H. Lee, and J. Y. Hahn, "An algorithm for submarine passive sonar simulator" (in Korean), J. Acoust. Soc. Kr. 32, 472-483 (2013). https://doi.org/10.7776/ASK.2013.32.6.472
  11. R. O. Duda and P. E. Hart, "Use of the Hough transformation to detect lines and curves in pictures," Commun. ACM, 15, 11-15 (1972). https://doi.org/10.1145/361237.361242
  12. J. Wang and P. J. Howarth, "Use of the Hough transform in automated lineament detection," IEEE Trans. Geosci. Remote Sensing, 28, 561-567 (1990). https://doi.org/10.1109/TGRS.1990.572949
  13. S. Chen, S. Guan, H. Wang, N. Ye, and Z. Wei, "A new method of ship type identification based on underwater radiated noise signals," J. Mar. Sci. Eng. 11, 963 (2023).
  14. M. Grandini, E. Bagli, and G. Visanim "Metrics for multi-class classification: an overview," arXiv preprint arXiv: 2008.05756 (2020).