Received 30.08.2024, Revised 12.11.2024, Accepted 26.12.2024

Correction of roll-caused stripe noise in side scan sonar images

Oleksandr Katrusha

Ensuring high-quality images obtained using side-scan sonar is crucial for enhancing the effectiveness of underwater research, as distortions such as striping noise can complicate data analysis. The aim of this paper was to investigate the nature of striping noise, determine the correlation between image intensity and the tilt of the sonar, and develop a new method to improve the quality of sonar images. The study employed a statistical correction method based on calculating a horizontal moving average for intensity correction, as well as a machine learning model using a threelayer neural network to predict the horizontal moving average considering the beam’s incidence angle, the sonar’s height above the seafloor, and the initial line intensity. Statistical methods and machine learning techniques were applied to correct the striping noise caused by tilting in sonar images, significantly enhancing their quality. The statistical approach, which uses the mean value of the horizontal sway, effectively reduced noise while preserving critical details and improving overall clarity. The machine learning model incorporated additional parameters, enhancing intensity prediction accuracy and improving adaptability to various sonar positioning conditions. Moreover, the new method accounts for varying environmental conditions, making it flexible and effective for real-world underwater research. These results provide valuable insights for improving sonar image processing methods, paving the way for more efficient underwater exploration and improving the accuracy of object detection on the seafloor

seafloor; greyscale; intensity; roll; correction; machine learning; neural network
77-85
Katrusha, O. (2024). Correction of roll-caused stripe noise in side scan sonar images. Information Technologies and Computer Engineering, 21(3), 77-85. https://doi.org/10.63341/vitce/3.2024.77

References

[1] Al-Rawi, M., Galdran, A., Isasi, A., & Elmgren, F. (2017). Cubic spline regression based enhancement of side-scan sonar imagery. In Proceedings of the OCEANS 2017 (pp. 1-7). Aberdeen: Institute of Electrical and Electronics Engineers. doi: 10.1109/oceanse.2017.8084567.

[2] Al-Rawi, M.S. (2016). Intensity normalization of sidescan sonar imagery. In Proceedings of the international conference on image processing theory, tools and applications (pp. 1-6). Oulu: IEEE. doi: 10.1109/IPTA.2016.7820967.

[3] Burguera, A., & Oliver, G. (2014). Intensity correction of side-scan sonar images. In Proceedings of the emerging technology and factory automation (pp. 1-4). Barcelona: Institute of Electrical and Electronics Engineers. doi: 10.1109/ ETFA33519.2014.

[4] Capus, C.G., Banks, A.C., Coiras, E., Tena Ruiz, I., Smith, C.J., & Petillot, Y.R. (2008). Data correction for visualisation and classification of sidescan SONAR imagery. IET Radar, Sonar & Navigation, 2(3), 155-169. doi: 10.1049/ietrsn:20070032.

[5] Chang, Y.-C., Hsu, S.-K., & Tsai, C.-H. (2020). Sidescan sonar image processing: Correcting brightness variation and patching gaps. Journal of Marine Science and Technology, 18(6), 721-730. doi: 10.51400/2709-6998.1935.

[6] Chen, Y., Huang, T.-Z., Zhao, X.-L., Deng, L.-J., & Huang, J. (2017). Stripe noise removal of remote sensing images by total variation regularization and group sparsity constraint. Remote Sensing, 9(6), article number 559. doi: 10.3390/ rs9060559.

[7] Guan, J., Lai, R., & Xiong, A. (2019). Wavelet deep neural network for stripe noise removal. IEEE Access, 7, 4454444554. doi: 10.1109/ACCESS.2019.2908720.

[8] Hughes Clarke, J.E. (2004). Seafloor characterization using keel-mounted sidescan: Proper compensation for radiometric and geometric distortion. In Canadian hydrography conference 2004 (pp. 1-18). Ottawa: Hydro International.

[9] Li, M., Nong, S., Nie, T., Han, C., Huang, L., & Qu, L. (2022). A novel stripe noise removal model for infrared images. Sensors, 22(8), article number 6971. doi: 10.3390/s22082971.

[10] Li, M., Rieck, J., Noheda, B., Roerdink, J., & Wilkinson, M. (2024). Stripe noise removal in conductive atomic force microscopy. Scientific Reports, 14(1), article number 3931. doi: 10.1038/s41598-024-54094-w.

[11] Lu, Z., Zhu, T., Zhou, H., Zhang, L., & Jia, C. (2023). An image enhancement method for side-scan sonar images based on multi-stage repairing image fusion. Electronics, 12(17), article number 3553. doi: 10.3390/electronics12173553.

[12] Navigation Messages. (n.d.). Retrieved from https://www.lsts.pt/docs/imc/master/Navigation.html.

[13] Shaobo, S., Jianhu, L., Yongcan, Y., Yunlong, W., Shaofeng, B., & Guojun, Z. (2022). Anisotropic total variation regularized low-rank approximation for SSS images radiometric distortion correction. IEEE Transactions on Geoscience and Remote Sensing, 60, article number 5925412. doi: 10.1109/TGRS.2022.3229301.

[14] Shippey, G., Bolinder, A., & Finndin, R. (1994). Shade correction of side-scan sonar imagery by histogram transformation. In Proceedings of the OCEANS’94 (pp. 439-443). Brest: Institute of Electrical and Electronics Engineers. doi: 10.1109/ OCEANS.1994.364084.

[15] Sivachandra, K., & Kumudham, R. (2024). A review: Object detection and classification using side scan sonar images via deep learning techniques. In V.K. Gunjan, J.M. Zurada, N. Singh (Eds.), Modern approaches in machine learning and cognitive science: A walkthrough (pp. 229-249). Cham: Springer. doi: 10.1007/978-3-031-43009-1_20.

[16] Steiniger, Y., Kraus, D., & Meisen, T. (2022). Survey on deep learning based computer vision for sonar imagery. Engineering Applications of Artificial Intelligence, 114, article number 105157. doi: 10.1016/j.engappai.2022.105157.

[17] Wilken, D., Feldens, P., Wunderlich, T., & Heinrich, C. (2012). Application of 2D Fourier filtering for elimination of stripe noise in side-scan sonar mosaics. Geo-Marine Letters, 32(4), 337-347. doi: 10.1007/s00367-012-0293-z.

[18] Xia, H., Cui, Y., Jin, S., Bian, G., Liu, G., Zhang, W., & Peng, C. (2024). Improvement of Criminisi’s stripe noise suppression method for side-scan sonar images. Applied Sciences, 14(20), article number 9574. doi: 10.3390/app14209574.

[19] Ye, X., Yang, H., Li, C., Jia, Y., & Li, P. (2019). A gray scale correction method for side-scan sonar images based on Retinex. Remote Sensing, 11(11), article number 1281. doi: 10.3390/rs11111281.

[20] Zhao, J., Yan, J., Zhang, H., & Meng, J. (2017). A new radiometric correction method for side-scan sonar images in consideration of seabed sediment variation. Remote Sensing, 9(6), article number 575. doi: 10.3390/rs9060575.

[21] Zhou, P., Chen, J., Tang, P., Gan, J., & Zhang, H. (2024). A multi-scale fusion strategy for side scan sonar image correction to improve low contrast and noise interference. Remote Sensing, 16(10), article number 1752. doi: 10.3390/ rs16101752.