1.南京林业大学土木工程学院,江苏 南京,210042
2.河海大学水利水电学院,江苏 南京,210098
3.河海大学水灾害抵御国家重点实验室,江苏 南京,210098
李扬涛,博士,主要从事水工建筑物智慧运维和安全诊断方向的研究。liyangtao@hhu.edu.cn
包腾飞,博士,教授。baotf@hhu.edu.cn
收稿:2023-01-18,
纸质出版:2025-04-05
移动端阅览
李扬涛,包腾飞,李田雨.深水大坝缺陷鲁棒实时检测方法[J].武汉大学学报(信息科学版),2025,50(4):684-698.
LI Yangtao,BAO Tengfei,LI Tianyu.A Robust Real-Time Detection Method for Deepwater Dam Defects[J].Geomatics and Information Science of Wuhan University,2025,50(4):684-698.
李扬涛,包腾飞,李田雨.深水大坝缺陷鲁棒实时检测方法[J].武汉大学学报(信息科学版),2025,50(4):684-698. DOI:10.13203/j.whugis20220734
LI Yangtao,BAO Tengfei,LI Tianyu.A Robust Real-Time Detection Method for Deepwater Dam Defects[J].Geomatics and Information Science of Wuhan University,2025,50(4):684-698. DOI:10.13203/j.whugis20220734
大坝长期服役过程中,在水环境和外部荷载的交互耦合作用下,其深水结构部位易出现各类缺陷病害,影响工程服役安全稳定和功能发挥。水下机器人搭载可见光相机,可以非接触形式实现结构损伤的高分辨率空间信息采集,如何从海量图像视频数据中提取结构损伤密切相关信息成为当前亟待解决的关键问题。结合机器视觉和深度学习理论方法,提出了一种兼顾检测精度和推理效率的大坝深水多类别缺陷实时目标检测方法。该框架以单阶段目标检测网络YOLOv5-s为基模型,构建大坝多类别缺陷识别器;利用模型稀疏化和剪枝策略,改变模型批处理层权重分布并去除模型冗余参数;进一步地,综合运用模型迁移和知识蒸馏理论,恢复由于剪枝压缩带来的精度劣化问题,据此构建出强背景干扰下大坝深水多类别缺陷实时检测方法。以某高坝深水探测工程为实例,引入多种深度学习目标检测算法作为对比,验证所提方法在障碍物遮挡、低可见度、光照不均等复杂深水检测场景的效果。案例分析结果表明,该方法可有效克服多种水下不利成像环境干扰,并准确辨识、区分不同类型缺陷,量化其真实尺寸。此外,剪枝后轻量化模型每秒可推理超过100张缺陷图像,具备较强的实时推理能力。
Objectives
2
Under the coupling action of environment and loads
dam underwater structures suffer from defects
affecting the safety
stability
and functional performance of the project. Underwater robots like remotely operated vehicles (ROV) equipped with visible light cameras can realize the high-resolution spatial information in a non-contact form for underwater damage. However
it is still a challenging task that needs to be solved urgently to efficiently extract effective information from massive image and video data.
Methods
2
First
we propose a real-time multi-class defect automatic identification framework for dam underwater structures. Specifically
the single-stage object detection network YOLOv5-s is utilized as the base model to develop the damage detector. Then
the model sparsity and pruning strategies are combined to change the batch layer weight distribution and remove model redundant parameters. Next
transfer learning and knowledge distillation are combined to recover the accuracy degradation caused by model pruning and compression.
Results
2
As an example
the underwater detection of a high dam is considered. The effectiveness of the proposed method is validated in complex underwater scenes like obstacle occlusion
low visibility
and uneven illumination.
Conclusions
2
The experimental results indicate that the proposed method can effectively overcome the interference of complicated underwater imaging environments and accurately identify different types of defects. Moreover
the proposed method achieves an inference speed of processing 100 defect images per second
demonstrating its real-time detection capability.
徐丛 , 王少伟 , 顾冲时 , 等 . 融合空间关联性的特高拱坝位移概率性预测模型 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 3 ): 433 - 442 .
XU Cong , WANG Shaowei , GU Chongshi , et al . A Probabilistic Prediction Model for Displacement of Super High Arch Dams Considering Deformation Spatial Association [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 3 ): 433 - 442 .
盛金保 , 向衍 , 杨德玮 , 等 . 水库大坝安全诊断与智慧管理关键技术与应用 [J]. 岩土工程学报 , 2022 , 44 ( 7 ): 1351 - 1366 .
SHENG Jinbao , XIANG Yan , YANG Dewei , et al . Key Technologies and Applications of Safety Diagnosis and Smart Management of Reservoir Dams [J]. Chinese Journal of Geotechnical Engineering , 2022 , 44 ( 7 ): 1351 - 1366 .
向衍 , 盛金保 , 袁辉 , 等 . 中国水库大坝降等报废现状与退役评估研究 [J]. 中国科学: 技术科学 , 2015 , 45 ( 12 ): 1304 - 1310 .
XIANG Yan , SHENG Jinbao , YUAN Hui , et al . Research on Degrading and Decommissioning Assessment of Reservoir in China [J]. Scientia Sinica (Technologica) , 2015 , 45 ( 12 ): 1304 - 1310 .
吴中如 , 顾冲时 , 苏怀智 , 等 . 水工结构工程分析计算方法回眸与发展 [J]. 河海大学学报(自然科学版) , 2015 , 43 ( 5 ): 395 - 405 .
WU Zhongru , GU Chongshi , SU Huaizhi , et al . Review and Prospect of Calculation Analysis Methods in Hydro-Structure Engineering [J]. Journal of Hohai University (Natural Sciences) , 2015 , 43 ( 5 ): 395 - 405 .
肖力炀 , 李伟 , 袁博 , 等 . 一种基于改进实例分割模型的路面裂缝检测方法 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 5 ): 765 - 776 .
XIAO Liyang , LI Wei , YUAN Bo , et al . A Pavement Crack Identification Method Based on Improved Instance Segmentation Model [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 5 ): 765 - 776 .
谢文高 , 张怡孝 , 刘爱荣 , 等 . 基于水下机器人与数字图像技术的混凝土结构表面裂缝检测方法 [J]. 工程力学 , 2022 , 39 ( S1 ): 64 - 70 .
XIE Wengao , ZHANG Yixiao , LIU Airong , et al . Method for Concrete Surface Cracking Detection Based on Rov and Digital Image Technology [J]. Engineering Mechanics , 2022 , 39 ( S1 ): 64 - 70 .
魏康 , 员方 , 董志强 , 等 . 基于标志点的多相机数字图像相关方法精度分析及土木工程中的应用 [J]. 东南大学学报(自然科学版) , 2021 , 51 ( 2 ): 219 - 226 .
WEI Kang , YUAN Fang , DONG Zhiqiang , et al . Precision Analysis and Civil Application of Multi-Camera Digital Image Correlation Method Based on Encoded Targets [J]. Journal of Southeast University (Natural Science Edition) , 2021 , 51 ( 2 ): 219 - 226 .
刘宇飞 , 樊健生 , 聂建国 , 等 . 结构表面裂缝数字图像法识别研究综述与前景展望 [J]. 土木工程学报 , 2021 , 54 ( 6 ): 79 - 98 .
LIU Yufei , FAN Jiansheng , NIE Jianguo , et al . Review and Prospect of Digital-Image-Based Crack Detection of Structure Surface [J]. China Civil Engineering Journal , 2021 , 54 ( 6 ): 79 - 98 .
刘宇飞 , 齐玉 , 李保罗 , 等 . 工程结构运维多场景的敏感服役指标智能识别 [J]. 建筑结构学报 , 2022 , 43 ( 10 ): 1 - 15 .
LIU Yufei , QI Yu , LI Baoluo , et al . Intelligent Detection of Sensitive Service Indicators in Multiple Scenarios of Structural Maintenance [J]. Journal of Building Structures , 2022 , 43 ( 10 ): 1 - 15 .
刘春磊 , 陈天恩 , 王聪 , 等 . 小样本目标检测研究综述 [J]. 计算机科学与探索 , 2023 , 17 ( 1 ): 53 - 73 .
LIU Chunlei , CHEN Tian’en , WANG Cong , et al . Survey of Few-Shot Object Detection [J]. Journal of Frontiers of Computer Science and Technology , 2023 , 17 ( 1 ): 53 - 73 .
XUE Y D , LI Y C . A Fast Detection Method via Region-Based Fully Convolutional Neural Networks for Shield Tunnel Lining Defects [J]. Computer-Aided Civil and Infrastructure Engineering , 2018 , 33 ( 8 ): 638 - 654 .
ZHOU Z , ZHANG J J , GONG C J . Automatic Detection Method of Tunnel Lining Multi-defects via an Enhanced You Only Look Once Network [J]. Computer-Aided Civil and Infrastructure Engineering , 2022 , 37 ( 6 ): 762 - 780 .
尚文卿 , 齐红波 . 基于改进Faster R-CNN与迁移学习的农田杂草识别算法 [J]. 中国农机化学报 , 2022 , 43 ( 10 ): 176 - 182 .
SHANG Wenqing , QI Hongbo . Identification Algorithm of Field Weeds Based on Improved Faster R-CNN and Transfer Learning [J]. Journal of Chinese Agricultural Mechanization , 2022 , 43 ( 10 ): 176 - 182 .
王伟 , 唐心瑶 , 崔华 , 等 . 基于CenterNet的路侧单目视角车辆3D形态精确感知 [J]. 中国公路学报 , 2022 , 35 ( 9 ): 104 - 118 .
WANG Wei , TANG Xinyao , CUI Hua , et al . Accurate Perception of Three-Dimensional Vehicle Form in Roadside Monocular Perspective Based on CenterNet [J]. China Journal of Highway and Transport , 2022 , 35 ( 9 ): 104 - 118 .
杨真真 , 郑艺欣 , 邵静 , 等 . 基于改进路径聚合和池化YOLOv4的目标检测 [J]. 南京邮电大学学报(自然科学版) , 2022 , 42 ( 5 ): 1 - 7 .
YANG Zhenzhen , ZHENG Yixin , SHAO Jing , et al . An Object Detection Method Based on Improved YOLOv4 Path Aggregation and Pooling [J]. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition) , 2022 , 42 ( 5 ): 1 - 7 .
徐继尚 , 柳翠寅 , 刘明 . 改进YOLOV4-Tiny的SAR图像舰船小目标检测 [J]. 小型微型计算机系统 , 2023 , 44 ( 12 ): 2791 - 2796 .
XU Jishang , LIU Cuiyin , LIU Ming . Small Target Ship Detection in SAR Image Based on Improved YOLOV4-Tiny [J]. Journal of Chinese Computer Systems , 2023 , 44 ( 12 ): 2791 - 2796 .
郭克友 , 李雪 , 杨民 . 基于轻量化YOLOv4的交通信息实时检测方法 [J]. 计算机应用 , 2023 , 43 ( 1 ): 74 - 80 .
GUO Keyou , LI Xue , YANG Min . Real-Time Detection Method of Traffic Information Based on Lightweight YOLOv4 [J]. Journal of Computer Applications , 2023 , 43 ( 1 ): 74 - 80 .
CHOI W , CHA Y J . SDDNet: Real-Time Crack Segmentation [J]. IEEE Transactions on Industrial Electronics , 2020 , 67 ( 9 ): 8016 - 8025 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621