Task-Specific Image Enhancement for Underwater Turtle Detection and Segmentation: An Investigation on a Benchmark Dataset
Keywords:
Image segmentation, Intelligent vision systems, Marine turtle dataset, Object detection, Segment anything model, Underwater image enhancement, YOLOAbstract
Underwater images often present challenges related to color distortion, low contrast, and loss of texture, severely degrading the performance of computer vision models involved in ecological monitoring or autonomous systems. This work investigates the performance of various enhancement techniques based on two main downstream tasks: turtle detection using the YOLO model and turtle segmentation using SAM. A multi-species dataset of turtles was collected from public resources, and five representative enhancement schemes, including classic contrast enhancement, generative learning-based enhancement, physics-guided correction, fusion-based processing, and the proposed TOUE method, were tested. Experimental results illustrate that the effectiveness of enhancement is very task dependent. That is, TOUE had the best detection accuracy and generalization capability on both the custom dataset and the SUIM benchmark, whereas CLAHE generated the best segmentation accuracy owing to consistent local contrast refinement. No single enhancement method effectively produced the optimal outcome in these two tasks. Guided by this observation, a dual-stage pipeline has been proposed, utilizing TOUE for detection and CLAHE for segmentation, a more reliable end-to-end pipeline for underwater vision. These findings underline the necessity of choosing enhancement methods based on the downstream application and provide, for the first time, a practical framework for optimizing detection-segmentation systems in real underwater scenarios.
Downloads
References
Schettini, R., & Corchs, S. (2010). Underwater image processing: state of the art of restoration and image enhancement methods. EURASIP Journal on Advances in Signal Processing, 2010(1). https://doi.org/10.1155/2010/746052
Zuiderveld, K. (1994). Contrast limited adaptive histogram equalization. In Elsevier eBooks (pp. 474–485). https://doi.org/10.1016/b978-0-12-336156-1.50061-6
Ancuti, C. O., Ancuti, C., De Vleeschouwer, C., & Bekaert, P. (2017). Color balance and fusion for underwater image enhancement. IEEE Transactions on Image Processing, 27(1), 379–393. https://doi.org/10.1109/tip.2017.2759252
Islam, J., Xia, Y., & Sattar, J. (2020). Fast underwater image enhancement for improved visual perception. IEEE Robotics and Automation Letters, 5(2), 3227–3234. https://doi.org/10.1109/lra.2020.2974710
Wang, Z., Shen, L., Xu, M., Yu, M., Wang, K., & Lin, Y. (2023). Domain adaptation for underwater image enhancement. IEEE Transactions on Image Processing, 32, 1442–1457. https://doi.org/10.1109/tip.2023.3244647
Jamieson, S., How, J. P., & Girdhar, Y. (2023). DeepSeeColor: Realtime adaptive color correction for autonomous underwater vehicles via deep learning methods. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2303.04025
Li, M., Pang, H., Jiang, C., Li, M., Pang, H., & Jiang, C. (2025). SGL-YOLO: Lightweight underwater object detection algorithm based on feature fusion. Signal Image and Video Processing, 19(16). https://doi.org/10.1007/s11760-025-04962-3
Huang, J., Fang, C., Zheng, X., & Liu, J. (2024). YOLOV8-UC: an improved YOLOV8-Based Underwater Object Detection Algorithm. IEEE Access, 12, 172186–172195. https://doi.org/10.1109/access.2024.3496925
Baek, J., Kim, J., & Kim, C. (2024). Deep learning-based image classification of sea turtles using object detection and instance segmentation models. PLoS ONE, 19(11), e0313323. https://doi.org/10.1371/journal.pone.0313323
Islam, J., Edge, C., Xiao, Y., Luo, P., Mehtaz, M., Morse, C., Enan, S. S., & Sattar, J. (2020). Semantic Segmentation of Underwater Imagery: Dataset and Benchmark. Computer Vision and Pattern Recognition, 1769–1776. https://doi.org/10.1109/iros45743.2020.9340821
Zuo, X., Jiang, J., Shen, J., & Yang, W. (2025). Improving underwater semantic segmentation with underwater image quality attention and muti-scale aggregation attention. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.23422
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W., Dollár, P., & Girshick, R. (2023). Segment anything. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2304.02643
Huang, Y., Lai, W., Ji, J., Cao, L., Zhang, S., & Ji, R. (2024). HRSAM: Efficient Interactive Segmentation in High-Resolution Images. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2407.02109
Ma, J., He, Y., Li, F., Han, L., You, C., & Wang, B. (2024). Segment anything in medical images. Nature Communications, 15(1), 654. https://doi.org/10.1038/s41467-024-44824-z
Land, E. H., & McCann, J. J. (1971). Lightness and retinex theory. Journal of the Optical Society of America, 61(1), 1. https://doi.org/10.1364/josa.61.000001
Zhang, D., He, Z., Zhang, X., Wang, Z., Ge, W., Shi, T., & Lin, Y. (2023). Underwater image enhancement via multi-scale fusion and adaptive color-gamma correction in low-light conditions. Engineering Applications of Artificial Intelligence, 126, 106972. https://doi.org/10.1016/j.engappai.2023.106972
Mishra, P., Vipparthi, S. K., & Murala, S. (2025). U-ENHANCE: Underwater image enhancement using WaVELet Triple Self-attention. In Lecture notes in computer science (pp. 87–104). https://doi.org/10.1007/978-981-96-2641-0_6
Wang, Y., Guo, J., He, W., Gao, H., Yue, H., Zhang, Z., & Li, C. (2023). Is underwater image enhancement all object detectors need? arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.18814
Lucas, E., Awad, A., Geglio, A., Saleem, A., Moradi, S., Havens, T. C., Galloway, A., & Paheding, S. (2025, February 28). Underwater Image Enhancement and Object Detection: Are Poor Object Detection Results On Enhanced Images Due to Missing Human Labels? In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). https://doi.org/10.1109/wacvw65960.2025.00167
Yang, M., Hu, J., Li, C., Rohde, G., Du, Y., & Hu, K. (2019). An In-Depth Survey of Underwater image Enhancement and Restoration. IEEE Access, 7, 123638–123657. https://doi.org/10.1109/access.2019.2932611
Nabahirwa, E., Song, W., Zhang, M., Fang, Y., & Ni, Z. (2025). A structured review of underwater object detection challenges and solutions: from traditional to large vision language models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2509.08490
Awad, A., Saleem, A., Paheding, S., Lucas, E., Al-Ratrout, S., & Havens, T. C. (2024). Beneath the surface: The role of underwater image enhancement in object detection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.14626
Putro, M. D., Mose, Y., Andaria, A. C., Litouw, J., Poekoel, V. C., & Najoan, X. (2024). Streamlining deep learning network for real-time sea turtle detection. Jurnal Rekayasa Elektrika, 20(3). https://doi.org/10.17529/jre.v20i3.35236
Xiao, Z., Li, Z., Li, H., Li, M., Liu, X., & Kong, Y. (2024). Multi-Scale Feature Fusion Enhancement for Underwater Object Detection. Sensors, 24(22), 7201. https://doi.org/10.3390/s24227201
Wang, J., He, X., Shao, F., Lu, G., Hu, R., & Jiang, Q. (2022). Semantic segmentation method of underwater images based on encoder-decoder architecture. PLoS ONE, 17(8), e0272666. https://doi.org/10.1371/journal.pone.0272666
Chen, T., Zhu, L., Ding, C., Cao, R., Wang, Y., Zhang, S., Li, Z., Sun, L., Zang, Y., & Mao, P. (2023). SAM-Adapter: Adapting Segment Anything in under-performed scenes. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2023) (pp. ––). IEEE. https://openaccess.thecvf.com/content/ICCV2023W/VCL/papers/Chen_SAM-Adapter_Adapting_Segment_Anything_in_Underperformed_Scenes_ICCVW_2023_paper.pdf
Hong, Y., Zhou, X., Hua, R., Lv, Q., & Dong, J. (2024). WaterSAM: Adapting SAM for Underwater Object Segmentation. Journal of Marine Science and Engineering, 12(9), 1616. https://doi.org/10.3390/jmse12091616
Abhisheka, T. E., Jagadale, B. N., Madhuri, G. R., & Chandrakantha, T. S. (2024). Enhancing Underwater Image Segmentation Through Deep Learning-Based Image Enhancement Techniques: A Study on EUVP and SUIM Datasets. Journal of Information Systems Engineering and Management, 9(4), 31027. https://doi.org/10.52783/jisem.v9i4.78
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
