Development of CNN-LSTM Model for Object Detection and Classification in Sonar Imagery in Maritime Defense Applications

Alan Fhajoeng Ramadhan, Gentio Harsono, Achmad Farid Wadjdi

Abstract


This research develops a combination model of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for the identification and classification of objects in sonar images, applied in the context of maritime defense and security. CNN is used to extract spatial features from sonar images, while LSTM processes the temporal sequences of these features to enhance the accuracy of underwater object classification. The dataset used consists of eight object classes: shipwrecks, plane wrecks, drowning victims, bottles, propellers, submarines, mines, and tires. The model was trained and tested using normalized and augmented data to enhance the variation and quality of the training data. The evaluation results show that the CNN-LSTM model achieves high accuracy in classifying underwater objects. At the end of the training, the training and validation accuracy reached 100% after 100 epochs, demonstrating the model's excellent ability to generalize knowledge from training data to unseen data. Additionally, the consistently decreasing loss value during the training process indicates the model's effectiveness in reducing prediction errors. This research proves that the combination of CNN and LSTM is an effective approach for identifying and classifying underwater objects in sonar images. With these promising results, the CNN-LSTM model has the potential to be implemented in real-world applications, supporting efforts to detect and identify underwater objects quickly and accurately, and contributing to the enhancement of maritime safety and security. This research makes a significant contribution to the development of underwater object detection and identification technology, which is crucial for maritime defense and security.


Keywords


Convolutional Neural Network; Long Short-Term Memory; Sonar Imaging; Object Identification; Object Classification; Maritime Defense; Maritime Security.

Full Text:

PDF

References


Anitha, U., Malarkkan, S., Anbarasi Jebaselvi, G. D., & Narmadha, R. (2019). Sonar image segmentation and quality assessment using prominent image processing techniques. Applied Acoustics, 148. https://doi.org/10.1016/j.apacoust.2018.12.038

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

https://doi.org/10.1109/JOE.2005.850931

Eleftherakis, D., & Vicen, R. (2020). Sensors to increase the security of underwater communication cables: A review of underwater monitoring sensors. Sensors (Switzerland), 20(3). https://doi.org/10.3390/s20030737

Fang, W., Zhang, F., Ding, Y., & Sheng, J. (2020). A new sequential image prediction method based on LSTM and DCGAN. Computers, Materials and Continua, 64(1). https://doi.org/10.32604/CMC.2020.06395

Hożyń, S. (2021). A review of underwater mine detection and classification in sonar imagery. In Electronics (Switzerland) (Vol. 10, Issue 23). https://doi.org/10.3390/electronics10232943

Huimei, H. A. N., Xingquan, Z. H. U., & Ying, L. I. (2020). Generalizing long short-term memory network for deep learning from generic data. ACM Transactions on Knowledge Discovery from Data, 14(2). https://doi.org/10.1145/3366022

Huo, G., Wu, Z., & Li, J. (2020). Underwater Object Classification in Sidescan Sonar Images Using Deep Transfer Learning and Semisynthetic Training Data. IEEE Access, 8. https://doi.org/10.1109/ACCESS.2020.2978880

Jiang, L., Cai, T., Ma, Q., Xu, F., & Wang, S. (2020). Active Object Detection in Sonar Images. IEEE Access, 8. https://doi.org/10.1109/ACCESS.2020.2999341

Kumudham, R., & Rajendran, V. (2019). Super resolution enhancement of underwater sonar images. SN Applied Sciences, 1(8). https://doi.org/10.1007/s42452-019-0886-5

Lyons, A. P., Olson, D. R., & Hansen, R. E. (2022). Modeling the effect of random roughness on synthetic aperture sonar image statistics. The Journal of the Acoustical Society of America, 152(3). https://doi.org/10.1121/10.0013837

Mahmoudi, M. A., Chetouani, A., Boufera, F., & Tabia, H. (2020). Learnable pooling weights for facial expression recognition. Pattern Recognition Letters, 138. https://doi.org/10.1016/j.patrec.2020.09.001

Meethongjan, K., Hoang, V. T., & Surinwarangkoon, T. (2022). Data augmentation by combining feature selection and color features for image classification. International Journal of Electrical and Computer Engineering, 12(6). https://doi.org/10.11591/ijece.v12i6.pp6172-6177

Mehmood, F., Ahmad, S., & Whangbo, T. K. (2023). An Efficient Optimization Technique for Training Deep Neural Networks. Mathematics, 11(6). https://doi.org/10.3390/math11061360

Mehra, S., Raut, G., Purkayastha, R. Das, Vishvakarma, S. K., & Biasizzo, A. (2023). An Empirical Evaluation of Enhanced Performance Softmax Function in Deep Learning. IEEE Access, 11. https://doi.org/10.1109/ACCESS.2023.3265327

Miller, A., Miller, B., & Miller, G. (2021). Navigation of underwater drones and integration of acoustic sensing with onboard inertial navigation system. In Drones (Vol. 5, Issue 3). https://doi.org/10.3390/drones5030083

Monteiro, H. A., Brito, A. V. de, & Melcker, E. U. K. (2021). Image normalization in embedded systems. Journal of Real-Time Image Processing, 18(6). https://doi.org/10.1007/s11554-021-01098-8

Palomeras, N., Furfaro, T., Williams, D. P., Carreras, M., & Dugelay, S. (2022). Automatic Target Recognition for Mine Countermeasure Missions Using Forward-Looking Sonar Data. IEEE Journal of Oceanic Engineering, 47(1). https://doi.org/10.1109/JOE.2021.3103269

Pham, T. D. (2021). Time–frequency time–space LSTM for robust classification of physiological signals. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-86432-7

Preciado-Grijalva, A., Wehbe, B., Firvida, M. B., & Valdenegro-Toro, M. (2022). Self-supervised Learning for Sonar Image Classification. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2022-June. https://doi.org/10.1109/CVPRW56347.2022.00156

Rusiecki, A. (2019). Trimmed categorical cross-entropy for deep learning with label noise. Electronics Letters, 55(6). https://doi.org/10.1049/el.2018.7980

Saha, S., Bovolo, F., & Bruzzone, L. (2022). Change Detection in Image Time-Series Using Unsupervised LSTM. IEEE Geoscience and Remote Sensing Letters, 19. https://doi.org/10.1109/LGRS.2020.3043822

Saleem, M. A., Senan, N., Wahid, F., Aamir, M., Samad, A., & Khan, M. (2022). Comparative Analysis of Recent Architecture of Convolutional Neural Network. Mathematical Problems in Engineering, 2022. https://doi.org/10.1155/2022/7313612

Sepas-Moghaddam, A., Etemad, A., Pereira, F., & Correia, P. L. (2021). Long Short-Term Memory with Gate and State Level Fusion for Light Field-Based Face Recognition. IEEE Transactions on Information Forensics and Security, 16. https://doi.org/10.1109/TIFS.2020.3036242

Shin, W., Kim, D. S., & Ko, H. (2023). Target Tracking from Weak Acoustic Signals in an Underwater Environment Using a Deep Segmentation Network. Journal of Marine Science and Engineering, 11(8). https://doi.org/10.3390/jmse11081584

Wang, Y., Shi, Z., Ma, X., & Liu, L. (2022). A Joint Sonar-Communication System Based on Multicarrier Waveforms. IEEE Signal Processing Letters, 29. https://doi.org/10.1109/LSP.2021.3106889

Watanabe, J., Shao, Y., & Miura, N. (2019). Underwater and airborne monitoring of marine ecosystems and debris. Journal of Applied Remote Sensing, 13(04). https://doi.org/10.1117/1.jrs.13.044509

Xu, X., & Yoneda, M. (2021). Multitask Air-Quality Prediction Based on LSTM-Autoencoder Model. IEEE Transactions on Cybernetics, 51(5). https://doi.org/10.1109/TCYB.2019.2945999

Yang, A., Yang, X., Wu, W., Liu, H., & Zhuansun, Y. (2019). Research on feature extraction of tumor image based on convolutional neural network. IEEE Access, 7. https://doi.org/10.1109/ACCESS.2019.2897131

Yang, M., Liu, J., Chen, L., Zhao, Z., Chen, X., & Shen, Y. (2020). An Advanced Deep Generative Framework for Temporal Link Prediction in Dynamic Networks. IEEE Transactions on Cybernetics, 50(12). https://doi.org/10.1109/TCYB.2019.2920268

Yang, W., Fan, S., Xu, S., King, P., Kang, B., & Kim, E. (2019). Autonomous Underwater Vehicle Navigation Using Sonar Image Matching based on Convolutional Neural Network. IFAC-PapersOnLine, 52(21). https://doi.org/10.1016/j.ifacol.2019.12.300

Yao, Q., Wang, Y., & Yang, Y. (2023). Underwater Acoustic Target Recognition Based on Data Augmentation and Residual CNN. Electronics (Switzerland), 12(5). https://doi.org/10.3390/electronics12051206

Ying, Y., Su, J., Shan, P., Miao, L., Wang, X., & Peng, S. (2019). Rectified Exponential Units for Convolutional Neural Networks. IEEE Access, 7. https://doi.org/10.1109/ACCESS.2019.2928442

Yu, H., Yang, L. T., Zhang, Q., Armstrong, D., & Deen, M. J. (2021).

Convolutional neural networks for medical image analysis: State-of-the-art, comparisons, improvement and perspectives. Neurocomputing, 444. https://doi.org/10.1016/j.neucom.2020.04.157

Yuan, F., Xiao, F., Zhang, K., Huang, Y., & Cheng, E. (2021). Noise reduction for sonar images by statistical analysis and fields of experts. Journal of Visual Communication and Image Representation, 74. https://doi.org/10.1016/j.jvcir.2020.102995




DOI: http://dx.doi.org/10.52155/ijpsat.v48.1.6790

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Alan Fhajoeng Ramadhan, Gentio Harsono, Achmad Farid Wadjdi

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.