Skip to main content
SpringerLink
Log in

YOLOv5-Based Seabed Sediment Recognition Method for Side-Scan Sonar Imagery

  • Published:
Journal of Ocean University of China Aims and scope Submit manuscript

Abstract

Seabed sediment recognition is vital for the exploitation of marine resources. Side-scan sonar (SSS) is an excellent tool for acquiring the imagery of seafloor topography. Combined with ocean surface sampling, it provides detailed and accurate images of marine substrate features. Most of the processing of SSS imagery works around limited sampling stations and requires manual interpretation to complete the classification of seabed sediment imagery. In complex sea areas, with manual interpretation, small targets are often lost due to a large amount of information. To date, studies related to the automatic recognition of seabed sediments are still few. This paper proposes a seabed sediment recognition method based on You Only Look Once version 5 and SSS imagery to perform real-time sediment classification and localization for accuracy, particularly on small targets and faster speeds. We used methods such as changing the dataset size, epoch, and optimizer and adding multiscale training to overcome the challenges of having a small sample and a low accuracy. With these methods, we improved the results on mean average precision by 8.98% and F1 score by 11.12% compared with the original method. In addition, the detection speed was approximately 100 frames per second, which is faster than that of previous methods. This speed enabled us to achieve real-time seabed sediment recognition from SSS imagery.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Berthold, T., Leichter, A., Rosenhahn, B., Berkhahn, V., and Valerius, J., 2018. Seabed sediment classification of side-scan sonar data using convolutional neural networks. 2017 IEEE Symposium Series on Computational Intelligence. Honolulu, 1–8.

  • Blondel, P., 2000. Automatic mine detection by textural analysis of COTS sidescan sonar imagery. International Journal of Remote Sensing, 21 (16): 3115–3128.

    Article  Google Scholar 

  • Bochkovskiy, A., Wang, C. Y., and Hong, Y., 2020. YOLOv4: Optimal speed and accuracy of object detection. ArXiv Pre-Print Server: https://doi.org/10.48550/arXiv.2004.10934.

  • Chik, W. B., 2008. Lord of your domain, but master of none: The need to harmonize and recalibrate the domain name regime of ownership and control. International Journal of Law and Information Technology, 16 (1): 8–72.

    Article  Google Scholar 

  • Coiras, E., Petillot, Y., and Lane, D. M., 2007. Multiresolution 3D reconstruction from side-scan sonar images. IEEE Transactions on Image Processing, 16 (2): 382–390.

    Article  Google Scholar 

  • Collier, J. S., and Humber, S. R., 2007. Time-lapse side-scan sonar imaging of bleached coral reefs: A case study from the Seychelles. Remote Sensing of Environment, 108 (4): 339–356.

    Article  Google Scholar 

  • Dewi, C., Chen, R. C., and Yu, H., 2020. Weight analysis for various prohibitory sign detection and recognition using deep learning. Multimedia Tools and Applications, 79 (43): 32897–32915.

    Article  Google Scholar 

  • Dura, E., Zhang, Y., Liao, X. J., Dobeck, G. J., and Carin, L., 2005. Active learning for detection of mine-like objects in side-scan sonar imagery. IEEE Journal of Oceanic Engineering, 30 (2): 360–371.

    Article  Google Scholar 

  • Flores, N. Y., Collas, F. P. L., Mehler, K., Schoor, M. M., Feld, C. K., and Leuven, R. S. E. W., 2021. Assessing habitat suitability for native and alien freshwater mussels in the River Waal (the Netherlands), using hydroacoustics and species sensitivity distributions. Environmental Modeling and Assessment, 27 (1): 187–204.

    Article  Google Scholar 

  • Greene, A., Rahman, A. F., Kline, R., and Rahman, M. S., 2018. Side scan sonar: A cost-efficient alternative method for measuring seagrass cover in shallow environments. Estuarine, Coastal and Shelf Science, 207: 250–258.

    Article  Google Scholar 

  • Gruzinov, V. M., Dyakov, N. N., Mezenceva, I. V., Malchenko, Y. A., and Korshenko, A. N., 2019. Sources of coastal water pollution near sevastopol. Oceanology, 59 (4): 523–532.

    Article  Google Scholar 

  • Kingma D., and Ba J., 2014. Adam: A method for stochastic optimization. ArXiv Pre-Print Server: https://doi.org/10.48550/arXiv.1412.6980.

  • Kumar, A., Kalia, A., Verma, K., Sharma, A., and Kaushal, M., 2021. Scaling up face masks detection with YOLO on a novel dataset. Optik, 239: 166744.

    Article  Google Scholar 

  • Lamarche, L. G., 2011. Unsupervised fuzzy classification and object-based image analysis of multibeam data to map deep water substrates, Cook Strait, New Zealand. Continental Shelf Research, 31 (11): 1236–1247.

    Article  Google Scholar 

  • Li, S., Gu, X., Xu, X., Xu, D., Zhang, T., Liu, Z., et al., 2021. Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm. Construction and Building Materials, 273: 121949.

    Article  Google Scholar 

  • Lucieer, V., and Lucieer, A., 2009. Fuzzy clustering for seafloor classification. Marine Geology, 264 (3): 230–241.

    Article  Google Scholar 

  • Luo, X., Qin, X., Wu, Z., Yang, F., Wang, M., and Shang, J., 2019. Sediment classification of small-size seabed acoustic images using convolutional neural networks. IEEE Access, 7: 98331–98339.

    Article  Google Scholar 

  • Ma, H., Liu, Y., Ren, Y., and Yu, J., 2019. Detection of collapsed buildings in post-earthquake remote sensing images based on the improved YOLOv3. Remote Sensing, 12 (1): 44.

    Article  Google Scholar 

  • Microsoft, 2017. Common objects in context dataset. https://co-codataset.org/.

  • Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., and Rajendra Acharya, U., 2020. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121: 103792.

    Article  Google Scholar 

  • Padilla, R., Netto, S. L., and Silva, E., 2020. A survey on performance metrics for object-detection algorithms. 27th International Conference on Systems, Signals and Image Processing. Niteroi, 237–242.

  • Qin, X., Luo, X., Wu, Z., and Shang, J., 2021. Optimizing the sediment classification of small side-scan sonar images based on deep learning. IEEE Access, 9: 29416–29428.

    Article  Google Scholar 

  • Ren, S., He, K., Girshick, R., and Sun, J., 2017. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39 (6): 1137–1149.

    Article  Google Scholar 

  • Sun, C., Hu, Y., and Shi, P., 2020. Probabilistic neural network based seabed sediment recognition method for side-scan sonar imagery. Sedimentary Geology, 410: 105792.

    Article  Google Scholar 

  • Sun, C., Wang, L., Wang, N., and Jin, S., 2021. Image recognition technology in texture identification of marine sediment sonar image. Complexity, 2021 (2): 1–8.

    Google Scholar 

  • Sutskever, I., Martens, J., Dahl, G., and Hinton, G., 2013. On the importance of initialization and momentum in deep learning. 30th International Conference on Machine Learning. Atlanta, Georgia, USA, 2176–2184.

  • Uchimoto, K., Nishimura, M., Watanabe, Y., and Xue, Z., 2020. An experiment revealing the ability of a side-scan sonar to detect CO2 bubbles in shallow seas. Greenhouse Gases: Science and Technology, 10 (3): 591–603.

    Article  Google Scholar 

  • Ultralytics, 2020. YOLOv5. https://github.com/ultralytics/YOLO-v5.

  • Wang, X., Zhao, J. H., Zhu, B. Y., Jiang, T. C., and Qin, T. T., 2018. A side scan sonar image target detection algorithm based on a neutrosophic set and diffusion maps. Remote Sensing, 10 (2): 295.

    Article  Google Scholar 

  • Xi, H. Y., Wan, L., Sheng, M. W., Li, Y. M., and Liu, T., 2017. The study of the seabed side-scan acoustic images recognition using BP neural network. In: Parallel Architecture, Algorithm and Programming, PAAP 2017. Communications in Computer and Information Science. Chen, G., et al., eds., Springer, Singapore, 130–141.

    Google Scholar 

  • Yan, J., Meng, J., and Zhao, J., 2021. Bottom detection from backscatter data of conventional side scan sonars through 1D-UNet. Remote Sensing, 13 (5): 1–23.

    Article  Google Scholar 

  • Yu, Y., Zhao, J., Gong, Q., Huang, C., Zheng, G., and Ma, J., 2021. Real-time underwater maritime object detection in side-scan sonar images based on transformer-YOLOv5. Remote Sensing, 13 (18): 3555.

    Article  Google Scholar 

  • Yulin, T., Jin, S., Bian, G., and Zhang, Y., 2020. Shipwreck target recognition in side-scan sonar images by improved YOLOv3 Model based on transfer learning. IEEE Access, 8: 173450–173460.

    Article  Google Scholar 

  • Zhu, Z., Cui, X., Zhang, K., Ai, B., Shi, B., and Yang, F., 2021. DNN-based seabed classification using differently weighted MBES multifeatures. Marine Geology, 438: 106519.

    Article  Google Scholar 

  • Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., et al., 2021. A comprehensive survey on transfer learning. Proceedings of the IEEE, 109 (1): 43–76.

    Article  Google Scholar 

Download references

Acknowledgements

This work is funded by the Natural Science Foundation of Fujian Province (No. 2018J01063), the Project of Deep Learning Based Underwater Cultural Relics Recognization (No. 38360041), and the Project of the State Administration of Cultural Relics (No. 2018300).

Author information

Authors and Affiliations

  1. National Center for Materials Service Safety, University of Science and Technology Beijing, Beijing, 100083, China

    Ziwei Wang & Peng Shi

  2. Laboratory of Coast and Marine Geology, Third Institute of Oceanography, MNR, Xiamen, 361000, China

    Yi Hu

  3. College of Liberal Arts, Shanghai University, Shanghai, 200444, China

    Jianxiang Ding

Authors
  1. Ziwei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yi Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianxiang Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peng Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Peng Shi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Z., Hu, Y., Ding, J. et al. YOLOv5-Based Seabed Sediment Recognition Method for Side-Scan Sonar Imagery. J. Ocean Univ. China 22, 1529–1540 (2023). https://doi.org/10.1007/s11802-023-5427-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11802-023-5427-6

Key words

Search

Navigation