Hybrid object detection in low visibility underwater imagery
DOI:
https://doi.org/10.33216/1998-7927-2026-304-6-67-72Keywords:
object detection, low visibility, underwater imagery, physics-guided learningAbstract
This study presents a multilevel analysis of object detection in underwater and aerial imagery captured under limited-visibility conditions. The physical causes of input-signal degradation, including wavelength-dependent absorption, scattering, non-uniform illumination, and low-contrast blur, are systematized, feature representations that can preserve object information under low contrast are considered, and a conceptual hybrid approach to robust detection is formalized. Analysis of recent research indicates that YOLO-, Faster R-CNN-, and transformer-based detectors may lose accuracy under adverse observation conditions when low-level visual features are strongly degraded, which reduces detection confidence and increases the number of false positives. To address this problem, a conceptual multi-branch architecture is proposed that coordinates detector-oriented image enhancement, physics-guided degradation estimation, attention/context mechanisms, multiscale feature fusion, and a real-time detector based on YOLO or RT-DETR. The enhancement branch is intended to be evaluated primarily by its influence on downstream localization rather than by visual-quality metrics alone. The experimental part of this study is deliberately limited to establishing a reference baseline: YOLO11n was trained and evaluated on the single-class Common Objects Underwater (COU) dataset for underwater technical-object detection. On the held-out test split, the baseline achieved Precision = 0.889, Recall = 0.832, mAP@0.50 = 0.888, and mAP@0.50:0.95 = 0.751. These values characterize only the YOLO11n baseline and do not constitute experimental validation of the complete hybrid architecture. Accordingly, the expected contributions of the enhancement, physics-guided, attention, and fusion branches are formulated as testable hypotheses to be verified by controlled ablation studies under identical data splits and training protocols. The principal contributions of the present work are the formalization of the conceptual architecture, the definition of the baseline experimental protocol, and the specification of a validation strategy for subsequent experiments.
References
1. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. Pp. 779–788. DOI: https://doi.org/ 10.1109/CVPR.2016.91
2. Wang C.-Y., Bochkovskiy A., Liao H.-Y. M. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. Pp. 7464–7475. DOI: https://doi.org/ 10.1109/CVPR52729.2023.00721
3. Wang C.-Y., Yeh I.-H., Liao H.-Y. M. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv preprint arXiv:2402.13616. 2024. 17 p. DOI: https://doi.org/ 10.48550/arXiv.2402.13616
4. Wang A., Chen H., Liu L., Chen K., Lin Z., Han J., Ding G. YOLOv10: Real-time End-to-End Object Detection. arXiv preprint arXiv:2405.14458. 2024. 21 p. DOI: https://doi.org/ 10.48550/arXiv.2405.14458
5. Carion N., Massa F., Synnaeve G., Usunier N., Kirillov A., Zagoruyko S. End-to-End Object Detection with Transformers. Springer, 2020. Pp. 213–229. DOI: https://doi.org/ 10.1007/978-3-030-58452-8_13
6. Zhao Y., Lv W., Xu S., Wei X., Wang G., others. DETRs Beat YOLOs on Real-Time Object Detection. arXiv preprint arXiv:2304.08069. 2023. 14 p. DOI: https://doi.org/ 10.48550/arXiv.2304.08069
7. Li C., Guo C., Ren W., Cong R., Hou J., Kwong S., Tao D. An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Transactions on Image Processing. 2020. Vol. 29. Pp. 4376–4389. DOI: https://doi.org/ 10.1109/TIP.2019.2955241
8. Jian M., Yang N., Tao C., Zhi H., Luo H. Underwater Object Detection and Datasets: A Survey. Intelligent Marine Technology and Systems. 2024. Vol. 2. P. 9 (23 p.). DOI: https://doi.org/ 10.1007/s44295-024-00023-6
9. Zhu P., Wen L., Du D., Bian X., Hu Q., Ling H. Vision Meets Drones: A Challenge. Springer, 2021. Pp. 444–460. DOI: https://doi.org/ 10.1007/978-3-030-11021-5_29
10. Tahir N. U. A., Tahir M., Ahn C. W., Hwang S. O. Object Detection in Autonomous Vehicles Under Adverse Weather: A Review of Traditional and Deep Learning Approaches. Algorithms. 2024. Vol. 17, No. 3. P. 103 (29 p.). DOI: https://doi.org/ 10.3390/a17030103
11. Kumar D., Muhammad N. Object Detection in Adverse Weather for Autonomous Driving Through Data Merging and YOLOv8. Sensors. 2023. Vol. 23, No. 20. P. 8471 (18 p.). DOI: https://doi.org/ 10.3390/s23208471
12. He K., Sun J., Tang X. Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2011. Vol. 33, No. 12. Pp. 2341–2353. DOI: https://doi.org/ 10.1109/TPAMI.2010.168
13. Islam M. J., Edge C., Xiao Y., Luo P., Mehtaz M., Morse C., Enan S. S., Sattar J. Semantic Segmentation of Underwater Imagery: Dataset and Benchmark. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2020. Pp. 1766–1773. DOI: https://doi.org/ 10.1109/IROS45743.2020.9340821
14. Meng X., Liu Y., Fan L., Fan J. YOLOv5s-Fog: An Improved Model Based on YOLOv5s for Object Detection in Foggy Weather Scenarios. Sensors. 2023. Vol. 23, No. 11. P. 5321 (16 p.). DOI: https://doi.org/ 10.3390/s23115321
15. Li Q., Shi H. YOLO-GE: An Attention Fusion Enhanced Underwater Object Detection Algorithm. Journal of Marine Science and Engineering. 2024. Vol. 12, No. 10. P. 1885 (22 p.). DOI: https://doi.org/ 10.3390/jmse12101885
16. Yan J., Zhou C., Zhang J., Feng H., Wang Y., Cui Y., Wang Z. Underwater Object Detection Algorithm Based on Attention Mechanism and Cross-Stage Partial Fast Spatial Pyramidal Pooling. Frontiers in Marine Science. 2022. Vol. 9. P. 1056300 (12 p.). DOI: https://doi.org/ 10.3389/fmars.2022.1056300
17. Ultralytics. Ultralytics YOLO11 Documentation. 2024. URL: https://docs.ultralytics.com/models/yolo11/ (accessed 16 May 2026).
