用YOLO改进水下管道检测，低能见度下识别更准。
YOLO-Based Pipeline Monitoring in Challenging Visual Environments
- 采用YOLOv8和YOLOv11的分割变体处理模糊水下图像
- YOLOv11在复杂环境下结构识别准确率更高
- 适合水下巡检、智能运维等工业场景应用
在低能见度的水下环境中进行海底管道状态监测面临浊度高、光线畸变和图像退化等挑战。传统视觉检测系统常因环境恶劣难以提供可靠的数据用于地图构建、目标识别或缺陷检测。本研究探索将先进的人工智能技术融入图像增强、管道结构识别与自主故障诊断流程。对比分析了两种最鲁棒的YOLOv8与YOLOv11及其针对图像分割任务定制的三种变体在复杂低可视性水下环境中的表现。基于海底拍摄的管道检测数据集，评估模型在恶劣视觉条件下的目标结构精确勾画能力。结果表明，YOLOv11在整体性能上优于YOLOv8。
原文摘要 · Abstract (English)
Condition monitoring subsea pipelines in low-visibility underwater environments poses significant challenges due to turbidity, light distortion, and image degradation. Traditional visual-based inspection systems often fail to provide reliable data for mapping, object recognition, or defect detection in such conditions. This study explores the integration of advanced artificial intelligence (AI) techniques to enhance image quality, detect pipeline structures, and support autonomous fault diagnosis. This study conducts a comparative analysis of two most robust versions of YOLOv8 and Yolov11 and their three variants tailored for image segmentation tasks in complex and low-visibility subsea environments. Using pipeline inspection datasets captured beneath the seabed, it evaluates model performance in accurately delineating target structures under challenging visual conditions. The results indicated that YOLOv11 outperformed YOLOv8 in overall performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。