|Table of Contents|

Citation:
　Mansour Taheri Andani,Farhad Ameri.Automated Pipe Defect Identification in Underwater Robot Imagery with Deep Learning[J].Journal of Marine Science and Application,2026,(1):197-215.[doi:10.1007/s11804-025-00617-4]
Click and Copy

Automated Pipe Defect Identification in Underwater Robot Imagery with Deep Learning

Info

Title:
Automated Pipe Defect Identification in Underwater Robot Imagery with Deep Learning
Author(s):
Mansour Taheri Andani1;  Farhad Ameri2
Affilations:
Author(s):
Mansour Taheri Andani1;  Farhad Ameri2
1. Department of Engineering Technology, Texas State University, San Marcos, TX, 78666, USA;
2. School of Manufacturing Systems and Networks, Arizona State University, Tempe, AZ, 85283, USA
Keywords:
YOLO8; Underwater robot; Object detection; Underwater pipelines; Remotely operated vehicle; Deep learning
分类号:
-
DOI:
10.1007/s11804-025-00617-4
Abstract:
Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems. However, the inspection of underwater pipelines presents a challenge due to factors such as light scattering, absorption, restricted visibility, and ambient noise. The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments. This study evaluated the efficacy of the You Only Look Once (YOLO) algorithm, a real-time object detection and localization model based on convolutional neural networks, in identifying and classifying various types of pipeline defects in underwater settings. YOLOv8, the latest evolution in the YOLO family, integrates advanced capabilities, such as anchor-free detection, a cross-stage partial network backbone for efficient feature extraction, and a feature pyramid network+ path aggregation network neck for robust multi-scale object detection, which make it particularly well-suited for complex underwater environments. Due to the lack of suitable open-access datasets for underwater pipeline defects, a custom dataset was captured using a remotely operated vehicle in a controlled environment. This application has the following assets available for use. Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks, rust, corners, defective welds, flanges, tapes, and holes. This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.

References:

[1] Aboah A, Wang B, Bagci U, Adu-Gyamfi Y (2023) Real-time multiclass helmet violation detection using few-shot data sampling technique and YOLOv8. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE 5349-5357. https://doi.org/10.1109/CVPRW59228.2023.00564
[2] Adarsh P, Rathi P, Kumar M (2020) YOLO v3-Tiny: Object detection and recognition using one stage improved model. Proceedings of the 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS). Piscataway: IEEE 687-694. https://doi.org/10.1109/ICACCS48705.2020.9074315
[3] Al Muksit A, Hasan F, Emon MFHB, Haque MR, Anwary AR, Shatabda S (2022) YOLO-fish: A robust fish detection model to detect fish in realistic underwater environment. Ecological Informatics 72: 101847. https://doi.org/10.1016/j.ecoinf.2022.101847
[4] Asyraf MS. Isa IS, Marzuki MIF, Sulaiman SN, Hung CC (2021) CNN-based YOLO v3 comparison for underwater object detection. Journal of Electrical and Electronic Systems Research 18: 30-37. https://doi.org/10.24191/jeesr.v18i1.005
[5] Avsar E, Feekings JP, Krag LA (2023) Estimating catch rates in real time: Development of a deep learning based Nephrops (Nephrops norvegicus) counter for demersal trawl fisheries. Frontiers in Marine Science 10: 1129852. https://doi.org/10.3389/fmars.2023.1129852
[6] Burguera A, Bonin-Font F (2022) Advances in autonomous underwater robotics based on machine learning. Journal of Marine Science and Engineering 10(10): 1481. https://doi.org/10.3390/jmse10101481
[7] Cao C, Yu Y, Xie Y, Sun C (2021) An efficient approach for gastric polyps detection based on improved SSD. Proceedings of the 2021 China Automation Congress (CAC). Piscataway: IEEE 852-857. https://doi.org/10.1109/CAC52703.2021.9727623
[8] Chen Y, Li Q, Lu D, Kou L, Ke W, Bai Y, Wang Z (2023) A novel underwater image enhancement using optimal composite backbone network. Biomimetics 8(3): 275. https://doi.org/10.3390/biomimetics8030275
[9] Cheng C (2022) Real-time mask detection based on SSDMobileNetV2. In Proceedings of the 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE). Piscataway: IEEE 761-767. https://doi.org/10.1109/AUTEEE56487.2022.9994442
[10] Chi Y, Zhang C (2024) Underwater image enhancement methods using biovision and type-II fuzzy set. Journal of Marine Science and Engineering 12(11): 2080. https://doi.org/10.3390/jmse12112080
[11] Du P, Song X (2024) Lightweight target detection: An improved YOLOv8 for small target defect detection on printed circuit boards. Proceedings of the 2024 International Conference on Generative Artificial Intelligence and Information Security (GAIIS). New York: ACM 329-334. https://doi.org/10.1145/3665348.3665404
[12] Fayaz S, Parah SA, Qureshi GJ (2022) Underwater object detection: Architectures and algorithms—A comprehensive review. Multimedia Tools and Applications 81(15): 20871-20916. https://doi.org/10.1007/s11042-022-12502-1
[13] Fu C, Liu R, Fan X, Chen P, Fu H, Yuan W, Zhu M, Luo Z (2023) Rethinking general underwater object detection: Datasets, challenges, and solutions. Neurocomputing, 517: 243-256. https://doi.org/10.1016/j.neucom.2022.10.039
[14] Gao Y, Liu W, Chui H-C, Chen X (2024) Large span sizes and irregular shapes target detection methods using variable convolutionimproved YOLOv8. Sensors 24(8): 2560. https://doi.org/10.3390/s24082560
[15] Ga?parovi? B, Lerga J, Mau?a G, Iva?i?-Kos M (2022) Deep learning approach for objects detection in underwater pipeline images. Applied Artificial Intelligence 36(1): 2146853. https://doi.org/10.1080/08839514.2022.2146853
[16] Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE 580-587. https://doi.org/10.1109/CVPR.2014.81
[17] Han M, Lyu Z, Qiu T, Xu M (2020) A review on intelligence dehazing and color restoration for underwater images. IEEE Transactions on Systems, Man, and Cybernetics: Systems 50(5): 1820-1832. https://doi.org/10.1109/TSMC.2017.2788902
[18] He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 37(9): 1904-1916. https://doi.org/10.1007/978-3-319-10578-9_23
[19] Jin ZZ, Zheng YF (2020) Research on application of improved YOLO V3 algorithm in road target detection. Journal of Physics: Conference Series, 1654: 012060. https://doi.org/10.1088/1742-6596/1654/1/012060
[20] Jocher G, Chaurasia A, Stoken A, Borovec J, NanoCode012, Kwon Y, Michael K, Taoxie, Fang J, Imyhxy, Lorna, Zeng Y, Wong C, Abhiram V, Montes D, Wang Z, Fati C, Nadar J, Laughing, UnglvKitDe, Sonck V, tkianai, YxNong, Skalski P, Hogan A, Nair D, Strobel M, Jain M (2022) ultralytics/yolov5: v7.0-YOLOv5 SOTA realtime instance segmentation. Zenodo. https://doi.org/10.5281/zenodo.7347926
[21] Karimanzira D, Renkewitz H, Shea D, Albiez J (2020) Object detection in sonar images. Electronics, 9(7): 1180. https://doi.org/10.3390/electronics9071180
[22] Kim JH, Kim N, Won CS (2023) High-speed drone detection based on YOLO-V8. Proceedings of the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Piscataway: IEEE 1-2. https://doi.org/10.1109/ICASSP49357.2023.10095516
[23] Kim N, Kim JH, Won CS (2022) FAFD: Fast and accurate face detector. Electronics 11(6): 875. https://doi.org/10.3390/electronics11060875
[24] Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, Li Y, Zhang B, Liang Y, Zhou L, Xu X, Chu X, Wei X, Wei X (2022) YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint, arXiv: 2209.02976. https://arxiv.org/abs/2209.02976
[25] Li H, Gu Z, He D, Wang X, Huang J, Mo Y, Li P, Huang Z, Wu F (2024) A lightweight improved YOLOv5s model and its deployment for detecting pitaya fruits in daytime and nighttime light-supplement environments. Computers and Electronics in Agriculture 220: 108914. https://doi.org/10.1016/j.compag.2024.108914
[26] Liu K, Sun Q, Sun D, Peng L, Yang M, Wang N (2023) Underwater target detection based on improved YOLOv7. Journal of Marine Science and Engineering 11(3): 677. https://doi.org/10.3390/jmse11030677
[27] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: Single shot multiBox detector. Computer Vision — ECCV 2016: 14th European Conference. Berlin: Springer Part I: 21-37. https://doi.org/10.48550/arXiv.1512.02325
[28] Meng F, Li J, Zhang Y, Qi S, Tang Y (2023) Transforming unmanned pineapple picking with spatio-temporal convolutional neural networks. Computers and Electronics in Agriculture 214: 108298. https://doi.org/10.1016/j.compag.2023.108298
[29] Nguyen QH, Ly HB, Ho LS, Al-Ansari N, Le HV, Tran VQ, Prakash I, Pham BT (2021) Influence of data splitting on performance of machine learning models in prediction of shear strength of soil. Mathematical Problems in Engineering 2021: 4832864. https://doi.org/10.1155/2021/4832864
[30] Orinait? U, Karaliūt? V, Pal M, Ragulskis M (2023) Detecting underwater concrete cracks with machine learning: A clear vision of a murky problem. Applied Sciences 13(12): 7335. https://doi.org/10.3390/app13127335
[31] Park CW, Eom IK (2024) Underwater image enhancement using adaptive standardization and normalization networks. Engineering Applications of Artificial Intelligence 127(Part A): 107445. https://doi.org/10.1016/j.engappai.2023.107445
[32] Pavani D, Reddy ANN, Saw N, Prasad S, Naik, SM (2023) Octacleaner: Underwater trash detection through YOLO. Proceedings of the 2023 3rd International Conference on Mobile Networks and Wireless Communications (ICMNWC). Piscataway: IEEE 1-6. https://doi.org/10.1109/ICMNWC60182.2023.10435715
[33] QYSEA (2022) FIFISH V6 plus official website. https://www.qysea.com/v6-expert.html (Accessed: 23 August 2022)
[34] Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE 779-788. https://doi.org/10.1109/CVPR.2016.91
[35] Rahman S, Rony JH, Uddin J, Samad MA (2023) Real-time obstacle detection with YOLOv8 in a WSN using UAV aerial photography. Journal of Imaging 9(10): 216. https://doi.org/10.3390/jimaging9100216
[36] Raza K, Hong S (2020) Fast and accurate fish detection design with improved YOLO-v3 model and transfer learning. International Journal of Advanced Computer Science and Applications 11(2): 7-16. https://doi.org/10.14569/IJACSA.2020.0110202
[37] Redmon J, Farhadi A ((2018) YOLOv3: An incremental improvement. arXiv preprint, arXiv: 1804.02767. https://doi.org/10.48550/arXiv.1804.02767
[38] Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: Towards realtime object detection with region proposal networks. Advances in Neural Information Processing Systems 28 (NeurIPS) arXiv: 1506.01497. https://doi.org/10.48550/arXiv.1506.01497
[39] Selcuk B, Serif T (2023) A comparison of YOLOv5 and YOLOv8 in the context of mobile UI detection. In Proceedings of the International Conference on Mobile Web and Intelligent Information Systems 161-174. https://doi.org/10.1007/978-3-031-39764-6_11
[40] Shankar R, Muthulakshmi M (2023) Comparing YOLOv3, YOLOv5 & YOLOv7 architectures for underwater marine creatures detection. Proceedings of the 2023 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE). Piscataway: IEEE 25-30. https://doi.org/10.1109/ICCIKE58312.2023.10131703
[41] Shen L, Tao H, Ni Y, Wang Y, Stojanovic V ((2023) Improved YOLOv3 model with feature map cropping for multi-scale road object detection. Measurement Science and Technology 34(4): 045406. https://doi.org/10.1088/1361-6501/acb075.s
[42] Soorma MS, Chaudhary A, Sonali S, Pal S, Upadhyay DK (2023) Underwater image processing with normalized AttUNet. 2023 International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3). Piscataway: IEEE 1-5. https://doi.org/10.1109/IC2E357697.2023.10262737
[43] Vidhya SK, Deepthi PS (2023) A comprehensive analysis of underwater image processing based on deep learning techniques. Proceedings of the 2023 International Conference on Control, Communication and Computing (ICCC). Piscataway: IEEE 1-6. https://doi.org/10.1109/ICCC57789.2023.10165168
[44] Wang T, Li Y, Zhai Y, Wang W, Huang R ((2023) A sewer pipeline defect detection method based on improved YOLOv5. Processes 11(8): 2508. https://doi.org/10.3390/pr11082508
[45] Xu S, Zhang M, Song W, Mei H, He Q, Liotta A ((2023) A systematic review and analysis of deep learning-based underwater object detection. Neurocomputing 527: 204-232. https://doi.org/10.1016/j.neucom.2023.01.056
[46] Yaseen M (2024) What is YOLOv9: An in-depth exploration of the internal features of the next-generation object detector. arXiv preprint arXiv: 2409.07813. https://arxiv.org/abs/2409.07813
[47] Zhang H, Zhang S, Wang Y, Liu Y, Yang Y, Zhou T, Bian H ((2021) Subsea pipeline leak inspection by autonomous underwater vehicle. Applied Ocean Research 107: 102321. https://doi.org/10.1016/j.apor.2020.102321
[48] Zhang H, Dai C, Chen C, Zhao Z, Lin M ((2024) One stage multiscale efficient network for underwater target detection. Review of Scientific Instruments 95(6): 065108. https://doi.org/10.1063/5.0206734
[49] Zhang J, Liu X, Zhang X, Xi Z, Wang S ((2023) Automatic detection method of sewer pipe defects using deep learning techniques. Applied Sciences, 13(7): 4589. https://doi.org/10.3390/app13074589
[50] Zhang L, Lin L, Liang X, He K (2016) Is faster R-CNN doing well for pedestrian detection? Computer Vision—ECCV 2016: 14th European Conference. ECCV 2016. Lecture Notes in Computer Science Part II: 443-457. https://doi.org/10.1007/978-3-319-46475-6_28
[51] Zhang Y, Ni Q ((2023) A novel weld-seam defect detection algorithm based on the S-YOLO model. Axioms 12(7): 697. https://doi.org/10.3390/axioms12070697
[52] Zhou H, Kong M, Yuan H, Pan Y, Wang X, Chen R, Lu W, Wang R, Yang Q ((2024) Real-time underwater object detection technology for complex underwater environments based on deep learning. Ecological Informatics, 82: 102680. https://doi.org/10.1016/j.ecoinf.2024.102680
[53] Zhong J, Gao C, Tian Y, Zhang M (2023) Research on the influence of hydrodynamic analysis to dynamic modeling of underwater manipulator. Proceedings of the 2023 IEEE 6th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Piscataway: IEEE 6: 982-986. https://doi.org/10.1109/ITNEC56291.2023.10082093
[54] Zhao S, Zheng J, Sun S, Zhang L ((2022) An improved YOLO algorithm for fast and accurate underwater object detection. Symmetry 14(8): 1669. https://doi.org/10.3390/sym14081669

Memo

Memo:
Received date:2024-7-15;Accepted date:2025-3-19。<br>Corresponding author:Farhad Ameri,Email:E-mail:farhad.ameri@asu.edu
Last Update: 2026-03-10