research-article

A super-resolution reconstruction method of underwater target detection image by side scan sonar

Authors:

Shujia WangAuthors Info & Claims

CCRIS '21: Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System

Pages 135 - 140

https://doi.org/10.1145/3483845.3483869

Published: 22 October 2021 Publication History

Abstract

However, the scope and distance of optical imaging were limited, especially in the case of muddy water, the propagation of optical information was seriously interfered, and imaging became more difficult. Due to the complex and changeable underwater environment and the nature of acoustic imaging, sonar image has noise, low resolution and fuzzy details, which has a great impact on the recognition and interpretation of sonar image. On the basis of the original SRGAN network, this paper improves and optimates its network structure and loss function. Replace the ordinary convolution layer with the void convolution layer in the residual block structure of the generated network, delete the batch normalization layer (BN layer), reduce the resource consumption and expand the receiver field, so as to improve the training efficiency of the network; A gradient penalty term is added to the improved discriminant network loss function to accelerate the convergence of the network and improve the stability of training. Four classical image super resolution algorithms are compared with the improved SRGAN algorithm under the verification of sonar dataset. The experimental results show that the improved SRGAN network is superior to the traditional super resolution method in the reconstruction of sonar image in terms of rich texture and details, and improves the quality of sonar image super resolution reconstruction.

References

[1]

Lai W S, Huang J B, Ahuja N, Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution[J]. IEEE Computer Society, 2017, 34(1)5835-5843.

[2]

Tai Y, Yang J, Liu X. Image Super-Resolution via Deep Recursive Residual Network[C].IEEE Computer Vision and Pattern Recognition (CVPR 2017). Honolulu, 2017: 298-298.

[3]

Youm G Y, Bae S H, Kim M. Image super-resolution based on convolution neural networksusing multi-channel input[C]. Image, Video, & Multidimensional Signal Processing Workshop. Bordeaux, France, 2016: 1-4.

[4]

Arjovsky M, Chintala S, Bottou L. Wasserstein GAN[J]. arXiv preprint ar Xiv: 1701.07875,2017.

[5]

Tai Y, Yang J, Liu X . Image Super-Resolution via Deep Recursive Residual Network[C]. IEEE Computer Vision and Pattern Recognition (CVPR 2017). Honolulu, 2017: 298-298.

[6]

GOODFELLOW I J, POUGET-ABADAIE J, MIRZA M, Generative Adversarial Nets[C]//ACM. 27th International Conference on Neural Information Processing Systems, December 8-13, 2014, Montreal, Canada. New York: ACM, 2014: 2672-2680.

[7]

Youm G Y, Bae S H, Kim M. Image super-resolution based on convolution neural networks using multi-channel input[C]. Image, Video, & Multidimensional Signal Processing Workshop. Bordeaux, France, 2016: 1-4.

[8]

Lai W S, Huang J B, Ahuja N, Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution[J]. IEEE Computer Society, 2017, 34(1)5835-5843.

[9]

Liu M. Image inpainting and super-resolution using non-local recursive deep convolutional network with skip connections[C]. International Conference on Digital Image Processing. Hong Kong, China, 2017: 10-12.

[10]

Zhao Y, Takaki S, Luong H T, Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder[J]. IEEE Access, 2018, (99):1-8.

[11]

Aitken A, Ledig C, Theis L, Checkerboard artifact free sub-pixel convolution: Anote on sub-pixel convolution, resize convolution and convolution resize[J]. 2017.

[12]

Mirza M, Osindero S. Conditional generative adversarial nets [J]. arXiv preprint ar Xiv:1411. 1784, 2014.

[13]

Radford, L. Metz, and S. Chintala. Unsupervised representation learning with deepconvolutional generative adversarial networks. In International Conference on LearningRepresentations (ICLR), 2016. 3, 4

[14]

D. Kingma and J. Ba. Adam: A method for stochastic optimization. In InternationalConference on Learning Representations (ICLR),2015. 6

[15]

S. Gross and M.Wilber.Training and investigating residual nets,on-lineathttp://torch.ch/blog/2016/02/04/resnets.html.2016.4

[16]

Aitken A,Ledig C,Theis L,et al.Checkerboard artifact free sub-pixel convolution:Anote on sub-pixel convolution, resize convolution and convolution resize[J].2017.

[17]

Zhang Y, Tian Y, Kong Y, Residual Dense Network for Image Super-Resolution[J].The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp.2472-2481.

Cited By

Rao JPeng YChen JTian X(2024)Various Degradation: Dual Cross-Refinement Transformer for Blind Sonar Image Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.339818862(1-14)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3398188
Jing CHuang ZLing Z(2023)An Image Super-Resolution Reconstruction Method Based on PEGANIEEE Access10.1109/ACCESS.2022.314204911(102550-102561)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2022.3142049
Cheng KYan LDing YZhou HLi MGhafoor H(2023)Sonar image garbage detection via global despeckling and dynamic attention graph optimizationNeurocomputing10.1016/j.neucom.2023.01.081529:C(152-165)Online publication date: 7-Apr-2023
https://dl.acm.org/doi/10.1016/j.neucom.2023.01.081

Index Terms

A super-resolution reconstruction method of underwater target detection image by side scan sonar
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision tasks
  2. Machine learning

Index terms have been assigned to the content through auto-classification.

Recommendations

$S^{2} RGAN$ : sonar-image super-resolution based on generative adversarial network
Abstract
As an important display mode of underwater environments, the sonar image has limitations on the resolution, which often leads to problems with low resolution of underwater objects. Therefore, the image super-resolution algorithm is needed to ... $^{}$ $^{}$ $^{}$ $^{}$
Grand Challenges in Super-resolution Image Reconstruction
ICBDC '23: Proceedings of the 2023 8th International Conference on Big Data and Computing

Image resolution reflects the richness of detail information contained in the image. Compared with low-resolution images, high-resolution images usually contain greater pixel density, richer texture details and higher reliability. In reality, constrained ...
Deeper super-resolution generative adversarial network with gradient penalty for sonar image enhancement
Abstract
In the field of underwater wireless communication, the acoustic signal has the advantages of low attenuation, long propagation distance, and high fidelity compared with electromagnetic wave signals. Therefore, as an important acoustic sensor, the ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

CCRIS '21: Proceedings of the 2021 2nd International Conference on Control, Robotics and Intelligent System

August 2021

278 pages

ISBN:9781450390453

DOI:10.1145/3483845

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

National sonar Key Laboratory Open Fund
National Fund Youth Project

Conference

CCRIS'21

CCRIS'21: 2021 2nd International Conference on Control, Robotics and Intelligent System

August 20 - 22, 2021

Qingdao, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
110
Total Downloads

Downloads (Last 12 months)16
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Rao JPeng YChen JTian X(2024)Various Degradation: Dual Cross-Refinement Transformer for Blind Sonar Image Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.339818862(1-14)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3398188
Jing CHuang ZLing Z(2023)An Image Super-Resolution Reconstruction Method Based on PEGANIEEE Access10.1109/ACCESS.2022.314204911(102550-102561)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2022.3142049
Cheng KYan LDing YZhou HLi MGhafoor H(2023)Sonar image garbage detection via global despeckling and dynamic attention graph optimizationNeurocomputing10.1016/j.neucom.2023.01.081529:C(152-165)Online publication date: 7-Apr-2023
https://dl.acm.org/doi/10.1016/j.neucom.2023.01.081

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten