The Journal of the Acoustical Society of Korea (한국음향학회지)

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

DOI QR Code

Side scan sonar image super-resolution using an improved initialization structure

향상된 초기화 구조를 이용한 측면주사소나 영상 초해상도 영상복원

  • Received : 2021.01.18
  • Accepted : 2021.03.04
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper deals with a super-resolution that improves the resolution of side scan sonar images using learning-based compressive sensing. Learning-based compressive sensing combined with deep learning and compressive sensing takes a structure of a feed-forward network and parameters are set automatically through learning. In particular, we propose a method that can effectively extract additional information required in the super-resolution process through various initialization methods. Representative experimental results show that the proposed method provides improved performance in terms of Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) than conventional methods.

본 논문에서는 학습 기반 압축 센싱을 이용하여 측면 주사 소나 영상의 해상도를 향상하는 초해상도 기법을 다룬다. 딥러닝과 압축 센싱이 접목된 학습 기반 압축 센싱은 구조적인 측면에서 피드-포워드(feed forward) 네트워크 형태이며 학습을 통하여 파라미터들을 자동으로 설정하게 된다. 본 논문에서는 초해상도 과정에서 필요한 추가 정보들을 다양한 초기화 방법을 통해 효과적으로 추출할 수 있는 방법을 제안한다. 다양한 모의 실험에서 제안하는 방법은 기존 방식보다 Peak Signal-to-Noise Ratio(PSNR) 및 Structure Similarity Index Measure(SSIM) 지표상 향상된 성능 결과를 나타내었다.

Keywords

References

  1. J. Lee, J. Park, K. Lee, J. Min, G. Kim, B. Lee, B. Ku, D. K. Han, and H. Ko, "FBRNN: Feedback recurrent neural network for extreme image super-resolution," Proc. of the IEEE/CVF conf. on CVPR. 1-8 (2020).
  2. L. Y. Ma, X. L. He, and Z. S. Huang, "Side scan sonar image super resolution based on sparse representation," Applied Mechanics and Materials, 48, 1049-1052 (2011). https://doi.org/10.4028/www.scientific.net/AMM.48-49.1049
  3. J. Park, B. Ku, Y. Jin, and H. Ko, "Side scan sonar image super resolution via region-selective sparse coding," IEICE Trans. on Information and Systems, 102, 210-213 (2019).
  4. B. Lim, S. Son, H. Kim, S. Nah, and K. M. Lee, "Enhanced deep residual networks for single image super-resolution," Proc. of the IEEE conf. on CVPR. 136-144 (2017).
  5. J. Zhang and B. Ghanem, "ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing," Proc. of the IEEE conf. on CVPR. 1828-1837 (2018).
  6. J. Hu, L. Shen, S. Albanie, and G. Sun, "Squeeze-and-excitation networks," Proc. of the IEEE conf. on CVPR. 7132-7141 (2018).
  7. Z. WANG, J. Chen, and S. C. H. Hoi, "Deep learning for image super-resolution: A survey," IEEE Trans. on Pattern Analysis and Machine Intelligence, 1-1 (2020).
  8. H. Chen, X. He, L. Qing, and Q. Then, "Single image super-resolution via adaptive transform-based nonlocal self-similarity modeling and learning-based gradient regularization," IEEE Trans. on Multimedia 19, 1702-1717 (2017). https://doi.org/10.1109/TMM.2017.2688920
  9. W. Dong, L. Zhang, G. Shi, and X. Wu, "Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization," IEEE TIP. 20, 1838-1857 (2011).
  10. Z. WANG and A. C. Bovik, Modern Image Quality Assessment (Morgan & Claypool, San Rafael, 2006), pp. 1-156.