FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-110443

Research Article |

Deep Learning for Enhanced Marine Vision: Object Detection in Underwater Environments

Author(s): Radhwan Adnan Dakhil* and Ali Retha Hasoon Khayeat

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 11, Issue 4

Publisher : FOREX Publication

Published : 26 December 2023

e-ISSN : 2347-470X

Page(s) : 1209-1218

DOI: https://doi.org/10.37391/ijeer.110443

Abstract

This study leverages the Semantic Segmentation of Underwater Imagery (SUIM) dataset, encompassing over 1,500 meticulously annotated images that delineate eight distinct object categories. These categories encompass a diverse array, ranging from vertebrate fish and invertebrate reefs to aquatic vegetation, wreckage, human divers, robots, and the seafloor. The use of this dataset involves a methodical synthesis of data through extensive oceanic expeditions and collaborative experiments, featuring both human participants and robots. The research extends its scope to evaluating cutting-edge semantic segmentation techniques, employing established metrics to gauge their performance comprehensively. Additionally, we introduce a fully convolutional encoder-decoder model designed with a dual purpose: delivering competitive performance and computational efficiency. Notably, this model boasts a remarkable accuracy of 88%, underscoring its proficiency in underwater image segmentation. Furthermore, this model's integration within the autonomy pipeline of visually-guided underwater robots presents its tangible applicability. Its rapid end-to-end inference capability addresses the exigencies of real-time decision-making, vital for autonomous systems. This study elucidates the model's practical benefits across diverse applications like visual serving, saliency prediction, and intricate scene comprehension. Crucially, the utilization of the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) elevates image quality, enriching the foundation upon which our model's success rests. This research establishes a solid groundwork for future exploration in underwater robot vision by presenting the model and the benchmark dataset.

Keywords: Underwater Object Detection, Deep Learning, Convolutional Neural Network (CNN), Underwater Imaging, Image Enhancement.




Radhwan Adnan Dakhil*, Department of Computer Science, College of Computer Science and Information Technology, University of Kerbala, Karbala, Iraq; Email: radhwan.a@s.uokerbala.edu.iq

Ali Retha Hasoon Khayeat, Department of Computer Science, College of Computer Science and Information Technology, University of Kerbala, Karbala, Iraq; Email: ali.r@uokerbala.edu.iq

    [1] A. Garcia-Garcia, S. Orts-Escolano, S. Oprea, V. Villena-Martinez, and J. J. a. p. a. Garcia-Rodriguez, "A review on deep learning techniques applied to semantic segmentation," 2017. https://doi.org/10.48550/arXiv.1704.06857.
    [2] M. Jian, Q. Qi, J. Dong, Y. Yin, K.-M. J. J. o. v. c. Lam, and i. representation, "Integrating QDWD with pattern distinctness and local contrast for underwater saliency detection," vol. 53, pp. 31-41, 2018. https://doi.org/10.1016/j.jvcir.2018.03.008.
    [3] M. Sharma, J. Lim, and H. J. A. S. Lee, "The amalgamation of the object detection and semantic segmentation for steel surface defect detection," vol. 12, no. 12, p. 6004, 2022. https://doi.org/10.3390/app12126004.
    [4] M. J. Islam, Y. Xia, J. J. I. R. Sattar, and A. Letters, "Fast underwater image enhancement for improved visual perception," vol. 5, no. 2, pp. 3227-3234, 2020. https://doi.org/10.1109/LRA.2020.2974710.
    [5] I. Alonso, M. Yuval, G. Eyal, T. Treibitz, and A. C. J. J. o. F. R. Murillo, "CoralSeg: Learning coral segmentation from sparse annotations," vol. 36, no. 8, pp. 1456-1477, 2019. https://doi.org/10.1002/rob.21915.
    [6] A. Haider, M. Arsalan, J. Choi, H. Sultan, and K. R. J. F. i. M. S. Park, "Robust segmentation of underwater fish based on multi-level feature accumulation," vol. 9, p. 1010565, 2022. https://doi.org/10.3389/fmars.2022.1010565.
    [7] S. Girija, A. Akhila, D. Deepthi, R. U. Kiran, and P. A. Krishna, "Saliency and Transmission Feature Extraction from Underwater Images Using Level Set Method," in 2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), 2022, pp. 1-7: IEEE. https://doi.org/10.1109/ICEEICT53079.2022.9768472.
    [8] Y. Girdhar, P. Giguere, and G. J. T. I. J. o. R. R. Dudek, "Autonomous adaptive exploration using realtime online spatiotemporal topic modeling," vol. 33, no. 4, pp. 645-657, 2014. https://doi.org/10.1177/02783649135073.
    [9] L. T. Parker IV, N. Gage, G. Van Anne, C. Tomaszewski, W. Newcomb, and A. Spears, "mTITAN: multi-domain tactical intelligent teaming and autonomous navigation," in Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2023, 2023, vol. 12544, pp. 55-64: SPIE. https://doi.org/10.1117/12.2663907.
    [10] J. Chamberlain, A. Garcia Seco De Herrera, A. Campello, and A. Clark, "ImageCLEFcoral task: coral reef image annotation and localisation," in CEUR Workshop Proceedings, 2022, vol. 3180, pp. 1318-1328: CEUR Workshop Proceedings.
    [11] D. Kim, D. Lee, H. Myung, and H.-T. J. I. S. R. Choi, "Artificial landmark-based underwater localization for AUVs using weighted template matching," vol. 7, pp. 175-184, 2014. https://doi.org/10.1007/s11370-014-0153-y.
    [12] M.-C. Chuang, J.-N. Hwang, and K. J. I. T. o. I. P. Williams, "A feature learning and object recognition framework for underwater fish images," vol. 25, no. 4, pp. 1862-1872, 2016. https://doi.org/10.48550/arXiv.1603.01696.
    [13] S. Y. Alaba et al., "Class-aware fish species recognition using deep learning for an imbalanced dataset," vol. 22, no. 21, p. 8268, 2022. https://doi.org/10.3390/s22218268.
    [14] L. Shen, H. Tao, Y. Ni, Y. Wang, V. J. M. S. Stojanovic, and Technology, "Improved YOLOv3 model with feature map cropping for multi-scale road object detection," vol. 34, no. 4, p. 045406, 2023. http://dx.doi.org/10.1088/1361-6501/acb075.
    [15] H. Yang, P. Liu, Y. Hu, and J. J. M. T. Fu, "Research on underwater object recognition based on YOLOv3," vol. 27, pp. 1837-1844, 2021. https://doi.org/10.1007/s00542-019-04694-8.
    [16] S. Bosse and P. J. E. P. Kasundra, "Robust Underwater Image Classification Using Image Segmentation, CNN, and Dynamic ROI Approximation," vol. 27, no. 1, p. 82, 2022. https://doi.org/10.3390/ecsa-9-13218.
    [17] Z. Chen et al., "Underwater sonar image segmentation combining pixel-level and region-level information," vol. 100, p. 107853, 2022. https://doi.org/10.1016/j.compeleceng.2022.107853.
    [18] D. Zhao, B. Yang, Y. Dou, and X. Guo, "Underwater fish detection in sonar image based on an improved Faster RCNN," in 2022 9th International Forum on Electrical Engineering and Automation (IFEEA), 2022, pp. 358-363: IEEE. https://doi.org/10.1109/IFEEA57288.2022.10038226.
    [19] J. Wang, X. He, F. Shao, G. Lu, R. Hu, and Q. J. P. o. Jiang, "Semantic segmentation method of underwater images based on encoder-decoder architecture," vol. 17, no. 8, p. e0272666, 2022.
    [20] Z. Liu et al., "Canet: Context aware network for brain glioma segmentation," vol. 40, no. 7, pp. 1763-1777, 2021.
    [21] G. Han, S. Huang, J. Ma, Y. He, and S. J. a. p. a. Chang, "Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment. arXiv 2021." https://doi.org/10.1609/aaai.v36i1.19959.
    [22] S. Villon, M. Chaumont, G. Subsol, S. Villéger, T. Claverie, and D. Mouillot, "Coral reef fish detection and recognition in underwater videos by supervised machine learning: Comparison between Deep Learning and HOG+ SVM methods," in International Conference on Advanced Concepts for Intelligent Vision Systems, 2016, pp. 160-171: Springer. https://doi.org/10.1007/978-3-319-48680-2_15.
    [23] Y. LeCun, Y. Bengio, and G. J. n. Hinton, "Deep learning," vol. 521, no. 7553, pp. 436-444, 2015. http://dx.doi.org/10.1038/nature14539.
    [24] M. Alavianmehr, M. Helfroush, H. Danyali, and A. J. J. o. r.-t. i. p. Tashk, "Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians," vol. 20, no. 1, p. 9, 2023. https://doi.org/10.1007/s11554-023-01273-z.
    [25] R. A. Dakhil and A. R. H. J. a. p. a. Khayeat, "Review On Deep Learning Technique For Underwater Object Detection," 2022. https://doi.org/10.48550/arXiv.2209.10151.
    [26] M. J. Islam, S. S. Enan, P. Luo, and J. Sattar, "Underwater image super-resolution using deep residual multipliers," in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 900-906: IEEE.
    [27] M. J. Islam, P. Luo, and J. J. a. p. a. Sattar, "Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception," 2020. https://doi.org/10.48550/arXiv.2002.01155.
    [28] "Marine Life Encyclopedia " 2001.
    [29] X. Wang et al., "Esrgan: Enhanced super-resolution generative adversarial networks," in Proceedings of the European conference on computer vision (ECCV) workshops, 2018, pp. 0-0. https://doi.org/10.1007/978-3-030-11021-5_5.
    [30] A. J. a. p. a. Aghelan, "Underwater Images Super-Resolution Using Generative Adversarial Network-based Model," 2022. https://doi.org/10.48550/arXiv.2211.03550.
    [31] N. C. Rakotonirina and A. Rasoanaivo, "ESRGAN+: Further improving enhanced super-resolution generative adversarial network," in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 3637-3641: IEEE. https://doi.org/10.48550/arXiv.2001.08073.
    [32] H. Wang et al., "Simultaneous restoration and super-resolution GAN for underwater image enhancement," vol. 10, p. 1162295, 2023. https://doi.org/10.3389/fmars.2023.1162295.
    [33] Z. Zhang and M. J. A. i. n. i. p. s. Sabuncu, "Generalized cross entropy loss for training deep neural networks with noisy labels," vol. 31, 2018. https://doi.org/10.48550/arXiv.1805.07836.
    [34] M. Abadi et al., "{TensorFlow}: a system for {Large-Scale} machine learning," in 12th USENIX symposium on operating systems design and implementation (OSDI 16), 2016, pp. 265-283.
    [35] D. P. Kingma and J. J. a. p. a. Ba, "Adam: A method for stochastic optimization," 2014. https://doi.org/10.48550/arXiv.1412.6980.

Radhwan Adnan Dakhil and Ali Retha Hasoon Khayeat (2023), Deep Learning for Enhanced Marine Vision: Object Detection in Underwater Environments. IJEER 11(4), 1209-1218. DOI: 10.37391/ijeer.110443.