Real-Time AI Water Surface Obstacle Detection for Small Boat Navigation Using Stereo Vision and Edge Computing
Keywords:
AI Water Surface Obstacle Detector, Computer vision, Marine navigation, YOLOv11, Object detectionAbstract
Reliable perception of water surface obstacles is essential for safe boat navigation and maritime monitoring. This paper presents an AI-based water surface obstacle detection system using stereo vision and an NVIDIA Jetson Orin NX edge platform. A custom Roboflow dataset with four target classes (boat, debris, structures, aquatic plant) was developed, and a YOLOv11 model was fine-tuned using pretrained COCO weights. Evaluation on unseen samples achieved mAP@0.5 of 0.7561, precision 0.7988, recall 0.6586 and F1-score of 0.7220. The results highlight strong detection performance, demonstrating potential for real-time deployment in boat navigation safety applications. Future work includes dataset expansion and sensor fusion.
References
Al-Hattab, Y. A., Abidin, Z. Z., Faizabadi, A. R., Zaki, H. F. M., & Ibarahim, A. I. (2023). Integration of stereo vision and MOOS-IvP for enhanced obstacle detection in USVs. IEEE Access, 11,pp 128932-128956. Doi: 10.1109/ACCESS.2023.3332032
Haijoub, A., Hatim, A., Guerrero-Gonzalez, A., Arioua, M., & Chougdali, K. (2024). Enhanced YOLOv8 Ship Detection Empower Unmanned Surface Vehicles for Advanced Maritime Surveillance. Journal of Imaging, 10(12), 303. https://doi.org/10.3390/jimaging10120303
Khanam, R., & Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv:2410.17725v1
Kim, J.-H., Kim, N., Park, Y. W., & Won, C. S. (2022). Object Detection and Classification Based on YOLO-V5 with Improved Maritime Dataset. Journal of Marine Science and Engineering, 10(3), 377. https://doi.org/10.3390/jmse10030377
Li, Y., Li, Y., Jiang, Z. & Wang, H. (2023). Real-time Detection of Surface Floating Garbage Based on Improved YOLOv7. Intelligent Robotics and Application, ICIRA 2023 proceeding, Part VI, pp. 573-582. https://doi.org/10.1007/978-981-99-6480-2_47
Lin, F., Hou, T., Jin, Q., & You, A. (2021). Improved YOLO Based Detection Algorithm for Floating Debris in Waterway. Entropy, 23(9), 1111. https://doi.org/10.3390/e2309111
Reddy, K. G. & Basha, S. S. (2025). Real Time Object Identification : A Study on COCO Dataset. Advance in Engineering Research 257, 860-870.
Signaroli, M., Lana, A., Cutolo, E., Alos, J., & Gonzalez-Cid, Y. (2025). Real-time tracking of recreational boats in coastal areas using deep learning. Ocean and Coastal Management, 267(2025) 107762, https://doi.org/10.1016/j.ocecoaman.2025.107762
Sung, L., Myung, I. & M, O. (2020). Image-based ship detection using deep learning. Ocean Systems Engineering, 4(40), 415-434. https://doi.org/10.12989/ose.2020.10.4.415
Wang, L., Xiao, Y., Zhang, B., Liu, R., & Zhao, B. (2023). Water Surface Targets Detection Based on the Fusion of Vision and LiDAR. Sensors, 23(4),1768. https://doi.org/10.3390/s23041768
Yang, D., Solihin, M. I., Zhao, Y., Li, W., Cai, B. & Chen, C. (2024). A streamlined approach for intelligent ship object detection using EL-YOLO algorithm. Scientific Reports, 14, Article 15234. https://doi.org/10.1038/s41598-024-64225-y
Yu, C., Yin, H., Rong, C., Zhao, J., Liang, X., Li, R., & Mo, X. (2024). YOLO-MRS: An efficient deep learning-based maritime object detection method for unmanned surface vehicles. Applied Ocean Research, 153, Article 104240. https://doi.org/10.1016/j.apor.2024.104240
Zhang, L., Wei, Y., Wang, H., Shao, Y., & Shen, J. (2021). Real-Time Detection of River Surface Floating Object Based on Improved RefineDet. IEEE Access, vol. 9, pp. 81147-81160. doi: 10.1109/ACCESS.2021.3085348
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Abdullah Atiq Arifin, Mohd Fahmi Mat Zin, Noor Haslyena Hassan
This work is licensed under a Creative Commons Attribution 4.0 International License.
