Automatic Classification of Coral Reef Model based on Deep Learning Method for Underwater Images
DOI:
https://doi.org/10.58915/aset.v5i2.3515Keywords:
Classification of coral reef, YOLOv11, Deep learningAbstract
Coral reefs play a vital role in maintaining the balance of marine life. However, coral reefs are facing threats due to human activities and environmental issues. Coral reefs’ population is slowly decreasing day by day. It is crucial to monitor the health of coral reefs. Traditionally, researchers use manual monitoring to assess the health of coral reefs. This way is too time-consuming and not accurate. Therefore, an automatic coral reef monitoring model is proposed by using image classification and deep learning. Underwater images of coral reefs are collected from various locations. The datasets consist of 20830 images from seven different locations. The images are classified by using a deep learning method called YOLOv11. YOLOv11 consists of three main components, backbone, neck and head. Backbone extracts the features from the image using the C3k2 block. Neck combines all the extracted features. The head provides the final coral classification output and the model or class scores. Using YOLOv11, coral reef classification achieves an F1-score of up to 70%. YOLOv11 helps to detect and classify the coral reef automatically and faster compared to the manual method.
References
[1] Razak, F., Lua, W. Y., Abd Rasid, N. H., Aziz, N., Repin, I. M., Xue, X. Z., Safuan, C. D. M. Adopting Marine Spatial Planning (MSP) using coral health assessment as indicator: A case study in Pulau Redang Marine Park, Malaysia. Ocean & Coastal Management, vol 248 (2024) pp.106943. https://doi.org/10.1016/j.ocecoaman.2023.106943
[2] Narciso, G. A. M., Tamondong, A. M., Blanco, A. C., Nakamura, T., Nadaoka, K. Supervised image classification model for coral bleaching detection using a bi-temporal Sentinel-2 image stack. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol 48 (2024) pp.395-401. https://doi.org/10.5194/isprs-archives-XLVIII-4-W8-2023-395-2024
[3] Manessa, M. D. M., Ummam, M. A. F., Efriana, A. F., Semedi, J. M., Ayu, F. Assessing Derawan Island's coral reefs over two decades: A machine learning classification perspective. Sensors, vol 24, issue 2 (2024) pp.466. https://doi.org/10.3390/s24020466
[4] Fauzan, A. C., Sari, H. E. Coral reef image classification using Multilayer Perceptron. MATICS: Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology), vol 17, issue 2 (2025) pp.76-81. https://doi.org/10.18860/mat.v17i2.32134
[5] Menaga, D., Deborah, S. L., Makizhna, M. Deep learning models for coral reef health classification: MobileNetV2, VGG16 and ResNet. International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024) (2025) pp.1241-1251. https://doi.org/10.2991/978-94-6463-718-2_103
[6] Anwarul, S., Tanwar, R. CoralClassify: Advancing coral health monitoring using deep learning. Procedia Computer Science, vol 259 (2025) pp.88-97. https://doi.org/10.1016/j.procs.2025.03.310
[7] Macrohon, J. J. E., Hung, G. Deep learning models for coral bleaching classification in multi-condition underwater image datasets. arXiv preprint (2025).
[8] Shao, X., Chen, H., Magson, K., Wang, J., Song, J., Chen, J., Sasaki, J. Deep learning for multilabel classification of coral reef conditions in the Indo-Pacific using underwater photo transect method. Aquatic Conservation: Marine and Freshwater Ecosystems, vol 34, issue 9 (2024) pp.e4241. https://doi.org/10.1002/aqc.4241
[9] Ogidi, M. S., Sah, M. Binary classification of coral reefs using deep learning for enhanced monitoring. 2025 9th International Symposium on Innovative Approaches in Smart Technologies (ISAS) (2025) pp.1-7. https://doi.org/10.1109/ISAS66241.2025.11101789
[10] Greeshma, P. M., Pallavi, K. G., BanuShree, T., Pranitha, T. M., Vinodh Kumar, S. Exploring machine learning models for coral reef classification from images. Journal of Emerging Technologies and Innovative Research (JETIR), vol 11, issue 5 (2024) pp.1-7.
[11] Alshahrani, A., Ali, H., Saif, E., Alsayed, M., Alshareef, F. Classification of coral reef species using computer vision and deep learning techniques. Engineering, Technology & Applied Science Research, vol 14, issue 5 (2024) pp.16478-16485. https://doi.org/10.48084/etasr.8044
[12] Ouassine, Y., Conruyt, N., Kayal, M., Martin, P. A., Bigot, L., Regine, V. L., Zahir, J. Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking. Ecological Informatics, vol 89 (2025) pp.103170. https://doi.org/10.1016/j.ecoinf.2025.103170
[13] Younes, O., Jihad, Z., Noël, C., Mohsen, K., Philippe, A. M., Eric, C., Regine, V. L. Automatic coral detection with YOLO: A deep learning approach for efficient and accurate coral reef monitoring. European Conference on Artificial Intelligence (2023) pp.170-177. https://doi.org/10.1007/978-3-031-50485-3_16
[14] Lu, Z., Liao, L., Xie, X., Yuan, H. SCoralDet: Efficient real-time underwater soft coral detection with YOLO. Ecological Informatics, vol 85 (2025) pp.102937. https://doi.org/10.1016/j.ecoinf.2024.102937
[15] Hung, G., Rodriguez, I. F. A comparative study of YOLOv8 to YOLOv11 performance in underwater vision tasks. arXiv preprint (2025).
[16] Wu, Y., Jiang, T., Xi, Z., Yin, F., Wang, X. YOLO-AR: An improved artificial reef segmentation algorithm based on YOLOv11. Sensors, vol 25, issue 17 (2025) pp.5426. https://doi.org/10.3390/s25175426
[17] Tao, J., Tian, H., Huang, S., Ye, Y., Xiong, Y., Huang, S., Wu, J. Coral-YOLO: An intelligent optical vision sensing framework for high-fidelity marine habitat monitoring and forecasting. Sensors (Basel, Switzerland), vol 25, issue 23 (2025) pp.7284. https://doi.org/10.3390/s25237284
[18] Ali, M. L., Zhang, Z. The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection. Computers, vol 13, issue 12 (2024) pp.336. https://doi.org/10.3390/computers13120336
[19] He, L., Zhou, Y., Liu, L., Ma, J. Research and application of YOLOv11-based object segmentation in intelligent recognition at construction sites. Buildings, vol 14, issue 12 (2024) pp.3777. https://doi.org/10.3390/buildings14123777
[20] Khanam, R., Hussain, M. YOLOv11: An overview of the key architectural enhancements. arXiv preprint (2024).
Downloads
Published
How to Cite
Issue
Section
