Volume 16 , Issue 2 , PP: 187-208, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Maddukuri Srinadh 1 * , J. B. Seventline 2
Doi: https://doi.org/10.54216/JCIM.160213
This paper discusses about implementing Machine Learning Models with the Marine_Pulse dataset. This is about side-scan sonar images that have four groups: Engineering Platform (EP), Pipeline/Cable (P/C), Sea Bed Surface (SBS), and Underwater Residual Mound (URM). This manuscript performed some difficult feature extraction and classification methods using the DenseNet-DNN framework. This paper delves deeply into the implementation of the DenseNet121 Dropout, DenseNet201 Dropout, DenseNet201 Enhanced Dropout, and DenseNet201 Transfer Learning models. It investigates how these models perform on feature extraction and classification using a DNN. We enhanced the performance and reduced overfitting by applying a dropout to DenseNet121 and DenseNet201 and by adding transfer learning (TL) to DenseNet201, respectively. The models were evaluated based on the accuracy, precision, recall, F1-score, specificity, and classification errors of the training and testing samples. We observed that DenseNet201 Enhanced Dropout outperformed the other models, achieving the highest accuracy of 95.79%. DenseNet201 Dropout followed this achievement with an accuracy of 94.74% and DenseNet121 Dropout with an accuracy of 92.11%. DenseNet201 Transfer Learning, on the other hand, had the worst accuracy (92.11%). Specificity is a measure of how well the model represents negative examples correctly. The maximum specificity was observed in DenseNet201 Enhanced Dropout (98.38%). DenseNet201 Dropout follows it at 97.96% and DenseNet121 Dropout at 97.18%. The smallest specificity was reported on DenseNet201 TL with 96.60%. This result demonstrates that our keys can generalize well and that they maintain high classification accuracy on the test data.
Side Scan SONAR Images , DenseNet121 , DenseNet201 , Transfer Learning , Deep Neural Network (DNN) , Multi Class Classification
[1] A.C. Wölfl, H. Snaith, S. Amirebrahimi, C.W. Devey, B. Dorschel, V. Ferrini, V.A.I. Huvenne, M. Jakobsson, J. Jencks, G. Johnston, et al., "Seafloor Mapping—The Challenge of a Truly Global Ocean Bathymetry," Frontiers in Marine Science, vol. 6, p. 283, 2019. doi: 10.3389/fmars.2019.00283.
[2] D. Eleftherakis and R. Vicen-Bueno, "Sensors to Increase the Security of Underwater Communication Cables: A Review of Underwater Monitoring Sensors," Sensors, vol. 20, p. 737, 2020. doi: 10.3390/s20030737.
[3] K. Sun, W. Cui, and C. Chen, "Review of Underwater Sensing Technologies and Applications," Sensors, vol. 21, p. 7849, 2021. doi: 10.3390/s21237849.
[4] Y. Tang, L. Wang, S. Jin, J. Zhao, C. Huang, and Y. Yu, "AUV-Based Side-Scan Sonar Real-Time Method for Underwater-Target Detection," Journal of Marine Science and Engineering, vol. 11, p. 690, 2023. doi: 10.3390/jmse11040690.
[5] R. Kumudham and V. Rajendran, "Super Resolution Enhancement of Underwater Sonar Images," SN Applied Sciences, vol. 1, p. 852, 2019. doi: 10.1007/s42452-019-0886-5.
[6] J.J. Schultz, C.A. Healy, K. Parker, and B. Lowers, "Detecting Submerged Objects: The Application of Side Scan Sonar to Forensic Contexts," Forensic Science International, vol. 231, pp. 306–316, 2013. doi: 10.1016/j.forsciint.2013.05.032.
[7] N. Nayak, M. Nara, T. Gambin, Z. Wood, and C.M. Clark, "Machine Learning Techniques for AUV Side-Scan Sonar Data Feature Extraction as Applied to Intelligent Search for Underwater Archaeological Sites," in Field and Service Robotics, G. Ishigami and K. Yoshida, Eds. Springer, 2021, pp. 1-16. doi: 10.1007/978-981-15-9460-1_16.
[8] C. Langner, W. Knauer, J. Jans, and A. Ebert, "Side Scan Sonar Image Resolution and Automatic Object Detection, Classification and Identification," in OCEANS 2009-EUROPE, Bremen, Germany, 2009, pp. 1-8. doi: 10.1109/OCEANSE.2009.5278183.
[9] Y. Dura, Y. Zhang, X. Liao, G.J. Dobeck, and L. Carin, "Active Learning for Detection of Mine-Like Objects in Side-Scan Sonar Imagery," IEEE Journal of Oceanic Engineering, vol. 30, no. 2, pp. 360-371, Apr. 2005. doi: 10.1109/JOE.2005.850931.
[10] Kaggle Dataset, "Marine Pulse," [Online]. Available: https://www.kaggle.com/datasets/khajaahmed1/marine-pulse.
[11] C. Li, X. Ye, D. Cao, J. Hou, and H. Yang, "Zero Shot Objects Classification Method of Side Scan Sonar Image Based on Synthesis of Pseudo Samples," Applied Acoustics, vol. 173, p. 107691, 2021. doi: 10.1016/j.apacoust.2020.107691.
[12] X. Wang, J. Jiao, J. Yin, W. Zhao, X. Han, and B. Sun, "Underwater Sonar Image Classification Using Adaptive Weights Convolutional Neural Network," Applied Acoustics, vol. 146, pp. 145-154, 2019. doi: 10.1016/j.apacoust.2018.11.003.
[13] X. Wang, J. Zhao, B. Zhu, T. Jiang, and T. Qin, "A Side Scan Sonar Image Target Detection Algorithm Based on a Neutrosophic Set and Diffusion Maps," Remote Sensing, vol. 10, p. 295, 2018. doi: 10.3390/rs10020295.
[14] X. Ye, C. Li, S. Zhang, P. Yang, and X. Li, "Research on Side-Scan Sonar Image Target Classification Method Based on Transfer Learning," in OCEANS 2018 MTS/IEEE Charleston, Charleston, SC, USA, 2018, pp. 1-6. doi: 10.1109/OCEANS.2018.8604691.
[15] K. Sivachandra and R. Kumudham, "A Review: Object Detection and Classification Using Side Scan Sonar Images via Deep Learning Techniques," in Modern Approaches in Machine Learning and Cognitive Science: A Walkthrough, V.K. Gunjan et al., Eds. Springer, 2024, pp. 1-20. doi: 10.1007/978-3-031-43009-1_20.
[16] J. Rhinelander, "Feature Extraction and Target Classification of Side-Scan Sonar Images," in 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece, 2016, pp. 1-6. doi: 10.1109/SSCI.2016.7850074.
[17] Q. Ge, F. Ruan, B. Qiao, Q. Zhang, X. Zuo, and L. Dang, "Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks," Electronics, vol. 10, p. 1823, 2021. doi: 10.3390/electronics10151823.
[18] B.W. Sheffield, J. Ellen, and B. Whitmore, "On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery," arXiv preprint arXiv:2409.12026, 2024. doi: 10.48550/arXiv.2409.12026.
[19] X. Du, Y. Sun, Y. Song, H. Sun, and L. Yang, "A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images," Remote Sensing, vol. 15, p. 593, 2023. doi: 10.3390/rs15030593.
[20] A. Preciado-Grijalva et al., "Self-Supervised Learning for Sonar Image Classification," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1-8. doi: 10.48550/arXiv.2204.09323.
[21] U. Anitha and S. Malarkkan, "Analysis of Edge Detection Techniques for Side Scan Sonar Image Using Block Processing and Fuzzy Logic Methods," in Advances in Intelligent Systems and Computing, vol. 363, pp. 363–370, 2016. doi: 10.1007/978-981-10-1678-3_35.
[22] G. Huo, Z. Wu, and J. Li, "Underwater Object Classification in Side-Scan Sonar Images Using Deep Transfer Learning and Semi-Synthetic Training Data," IEEE Access, vol. 8, pp. 123456-123467, 2020. doi: 10.1109/ACCESS.2020.2978880.
[23] M. Diesing, P. Mitchell, and D. Stephens, "Image-Based Seabed Classification: What Can We Learn from Terrestrial Remote Sensing?" ICES Journal of Marine Science, vol. 73, no. 10, pp. 2425–2441, 2016. doi: 10.1093/icesjms/fsw118.
[24] X. Wang, Y. Wang, and M.J. Er, "Review on Deep Learning Techniques for Marine Object Recognition: Architectures and Algorithms," Control Engineering Practice, vol. 118, p. 104458, 2022. doi: 10.1016/j.conengprac.2020.104458.
[25] J. Petrich, M.F. Brown, J.L. Pentzer, and J.P. Sustersic, "Side Scan Sonar Based Self-Localization for Small Autonomous Underwater Vehicles," Ocean Engineering, vol. 161, pp. 221–226, 2018. doi: 10.1016/j.oceaneng.2018.04.095.
[26] T. Sheffer and H. Guterman, "Geometrical Correction of Side-Scan Sonar Images," in 2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE), Eilat, Israel, 2018, pp. 1-5. doi: 10.1109/ICSEE.2018.8646188.
[27] M. Sung, J. Kim, and M. Lee, "Realistic Sonar Image Simulation Using Deep Learning for Underwater Object Detection," International Journal of Control, Automation and Systems, vol. 18, pp. 523–534, 2020. doi: 10.1007/s12555-019-0691-3.
[28] X. Du, Y. Sun, Y. Song, H. Sun, and L. Yang, "A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images," Remote Sensing, vol. 15, no. 3, p. 593, 2023. doi: 10.3390/rs15030593.
[29] M. Einsidler, P. Dhanak, and P.-P. Beaujean, "A Deep Learning Approach to Target Recognition in Side-Scan Sonar Imagery," in OCEANS 2018 MTS/IEEE Charleston, Charleston, SC, USA, 2018, pp. 1-4. doi: 10.1109/OCEANS.2018.8604879.
[30] H. Lei and J. Lei, "SI-GAT: Enhancing Side-Scan Sonar Image Classification Based on Graph Structure," IEEE Sensors Journal, vol. 24, no. 15, pp. 24388-24404, Aug. 2024. doi: 10.1109/JSEN.2024.3416193.
