Aquatic object detection using YOLO (you only look once) algorithm
Main Article Content
Abstract
The automated classification of marine species using images is a challenging task for which various solutions have been developed over the past two decades. Oceans are complex environments that are difficult to access, and the images obtained are often of low quality. In such situations, the classification of aquatic organisms becomes difficult and time-consuming. Therefore, it is often necessary to apply image enhancement and preprocessing techniques before implementing classification algorithms.
The objective is to develop a highly accurate and efficient deep learning system using the YOLOv8 (You Only Look Once) algorithm for recognizing different underwater aquatic species. To achieve this, a submerged optical detection network (UODN) based on the YOLO algorithm is proposed. The results not only confirm the suitability of YOLOv8 for underwater exploration but also demonstrate its strong potential in various fields, including marine resource identification, rescue operations, and ecosystem conservation.
The integration of deep learning with underwater environments opens new opportunities for technological advancement with significant implications for both scientific research and practical applications.
Article Details
Section
How to Cite
References
Aguzzi, J., Chatzievangelou, D., Company, J.B., Thomsen, L., Marini, S., Bonofiglio, F., Juanes, F., Rountree, R., Berry, A., Chumbinho, R. and Lordan, C., 2020. The potential of video imagery from worldwide cabled observatory networks to provide information supporting fish-stock and biodiversity assessment. *ICES Journal of Marine Science*, 77(7-8), pp.2396-2410. [https://doi.org/10.1093/icesjms/fsaa169](https://doi.org/10.1093/icesjms/fsaa169)
Aguzzi, J., Chatzievangelou, D., Francescangeli, M., Marini, S., Bonofiglio, F., Del Rio, J. and Danovaro, R., 2020. The hierarchic treatment of marine ecological information from spatial networks of benthic platforms. *Sensors*, 20(6), p.1751. [https://doi.org/10.3390/s20061751](https://doi.org/10.3390/s20061751)
Aguzzi, J., Costa, C., Calisti, M., Funari, V., Stefanni, S., Danovaro, R., Gomes, H.I., Vecchi, F., Dartnell, L.R., Weiss, P. and Nowak, K., 2021. Research trends and future perspectives in marine biomimicking robotics. *Sensors*, 21(11), p.3778. [https://doi.org/10.3390/s21113778](https://doi.org/10.3390/s21113778)
Chatzievangelou, D., Bahamon, N., Martini, S., Del Rio, J., Riccobene, G., Tangherlini, M., Danovaro, R., De Leo, F.C., Pirenne, B. and Aguzzi, J., 2021. Integrating diel vertical migrations of bioluminescent deep scattering layers into monitoring programs. *Frontiers in Marine Science*, 8, p.661809. [https://doi.org/10.3389/fmars.2021.661809](https://doi.org/10.3389/fmars.2021.661809)
Ittoo, O. and Pudaruth, S., 2024. Automatic recognition of marine creatures using deep learning. *International Journal of Advanced Computer Science & Applications*, 15(1). [https://doi.org/10.14569/IJACSA.2024.0150106](https://doi.org/10.14569/IJACSA.2024.0150106)
Karimov, N., Kulmetov, M., Safarova, N., Jumaev, K., Fayzullaev, M., Sultanov, S. and Yakhshieva, Z., 2024. The ecotourism industry's role in environmental stewardship. *Natural and Engineering Sciences*, 9(2), pp.293-308. [https://doi.org/10.28978/nesciences.1574450](https://doi.org/10.28978/nesciences.1574450)
Liu, A., Liu, Y., Xu, K., Zhao, F., Zhou, Y. and Li, X., 2024. DeepSeaNet: A bio-detection network enabling species identification in deep-sea imagery. *IEEE Transactions on Geoscience and Remote Sensing*. [https://doi.org/10.1109/TGRS.2024.3359350](https://doi.org/10.1109/TGRS.2024.3359350)
Lopez-Vazquez, V., Lopez-Guede, J.M., Chatzievangelou, D. and Aguzzi, J., 2023. Deep learning based deep-sea automatic image enhancement and animal species classification. *Journal of Big Data*, 10(1), p.37. [https://doi.org/10.1186/s40537-023-00711-w](https://doi.org/10.1186/s40537-023-00711-w)
Ortenzi, L., Aguzzi, J., Costa, C., Marini, S., D'Agostino, D., Thomsen, L., De Leo, F.C., Correa, P.V. and Chatzievangelou, D., 2024. Automated species classification and counting by deep-sea mobile crawler platforms using YOLO. *Ecological Informatics*, 82, p.102788. [https://doi.org/10.1016/j.ecoinf.2024.102788](https://doi.org/10.1016/j.ecoinf.2024.102788)