基于深度学习的水下混凝土结构表观缺陷智能化识别研究
Intelligent Identification of Apparent Defects in Underwater Structures Based on Deep Learning
受水体浑浊度、水下光线、水流速度等复杂因素的影响,传统的人工检测方法难以对水下混凝土结构的表观缺陷实施精确的检测与识别。本文提出基于深度学习算法的水下结构表观缺陷智能化识别技术,通过模拟复杂水域环境建立水下结构典型表观缺陷的数据库,再由图像增强算法进行小样本数据扩充和预处理,最后通过YOLOv5 (You Only Look Once)目标识别算法实现不同类别缺陷的自动化识别与定位。结果表明,该技术能够取得良好的效果,平均精度均值mAP值、查准率(Precision)都达到了83%以上,在一定程度上能解决因水下场景复杂、采集样本量少而导致的模型识别精度不高的问题。
Apparent defects in underwater concrete structures are significantly challenged by complex environmental factors including water turbidity, variable lighting conditions, and flow velocity. These interferences lead to difficulties in defect localization and low recognition accuracy during underwater inspections. To address these limitations, this study proposes an intelligent recognition framework based on deep learning. The methodology integrates three key components: generation of a multi-scenario defect database replicating complex underwater environments; application of small-sample expansion and image enhancement algorithms for robust preprocessing; implementation of the YOLOv5 target detection algorithm for multi-category defect identification and localization. Experimental results demonstrate that the proposed approach achieves a mean average precision (mAP) of 83% and a recognition precision exceeding 83%. This framework effectively mitigates accuracy degradation caused by underwater environmental complexities and limited sample sizes, providing a reliable technical solution for automated structural health monitoring of submerged infrastructure.
| [1] |
陈从平,邹雷,汪卫.基于轮廓特征的水下混凝土结构表面裂缝检测算法[J].计算机测量与控制,2014,22(5):1496-1498. |
| [2] |
CHEN Congping,ZOU Lei,WANG Wei.Underwater concrete structure surface crack detection algorithm based on contour features[J].Computer Measurement and Control,2014,22(5):1496-1498.(in Chinese) |
| [3] |
陈龙彪,谌雨章,王晓晨,基于深度学习的水下图像超分辨率重建方法[J].计算机应用,2019,39(9):2738-2743. |
| [4] |
CHEN Longbiao,CHEN Yuzhang,WANG Xiaochen,et al.Underwater image super-resolution reconstruction method based on deep learning[J].Journal of Computer Applications,2019,39(9):2738-2743.(in Chinese) |
| [5] |
LEDIG C,THEIS L,HUSZAR F,et al.Photo-realistic single image super-resolution using a generative adversarial network[C].2017 IEEE Conference on Computer Vision and Pattern Recognition,2016:105-114. |
| [6] |
谢坤.基于暗通道先验和水体浑浊度识别的水下图像增强算法[D].厦门:厦门大学,2018. |
| [7] |
XIE Kun.An underwater image enhancement algorithm based on dark channel prior and water turbidity recognition[D].Xiamen:Xiamen University,2018.(in Chinese) |
| [8] |
骆剑彬,姜绍飞,沈圣,基于声呐成像的水下桩墩表观病害深度学习与智能检测[J].土木工程学报,2021,54(7):90-100. |
| [9] |
LUO Jianbin,JIANG Shaofei,SHEN Sheng,et al.Deep learning and intelligent detection of apparent defects on underwater foundations of bridges with sonar imaging[J].China Civil Engineering Journal,2021,54(7):90-100.(in Chinese) |
| [10] |
吉同元,李鹏飞,张润,三维成像声呐在水下灌注桩缺陷检测中的应用探讨[J].岩土工程学报,2021,43(S2):170-173. |
| [11] |
JI Tongyuan,LI Pengfei,ZHANG Run,et al.Application of 3D imaging sonar in defect detection of underwater bored piles[J].Chinese Journal of Geotechnical Engineering,2021,43(S2):170-173.(in Chinese) |
| [12] |
LI L,ZHANG H,PANG J,et al.Dam surface crack detection based on deep learning[C]//2019 International Conference on Robotics,Intelligent Control and Artificial Intelligence,New York,USA:738-743. |
| [13] |
ALI L,ALNAJJAR F,JASSMI H A,et al.Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures[J].Sensors,2021,21(5):1688. |
| [14] |
ZENG L,SUN B,ZHU D.Underwater target detection based on Faster R-CNN and adversarial occlusion network[J].Engineering Applications of Artificial Intelligence,2021,100(4):104190. |
| [15] |
夏坚,周利君,张伟.基于迁移学习与VGG16深度神经网络的建筑物裂缝检测方法[J].福建建设科技,2022(1):19-22,60. |
| [16] |
XIA Jian,ZHOU Lijun,ZHANG Wei.Building crack detection method based on transfer learning and VGG16 deep neural network[J].Fujian Construction Science and Technology,2022(1):19-22,60.(in Chinese) |
| [17] |
周中,闫龙宾,张俊杰,基于YOLOX-G算法的隧道裂缝实时检测[J].铁道科学与工程学报,2023,20(7):2751-2762. |
| [18] |
ZHOU Zhong,YAN Longbin,ZHANG Junjie,et al.Real-time detection of tunnel cracks based on YOLOX-G algorithm[J].Journal of Railway Science and Engineering,2023,20(7):2751-2762.(in Chinese) |
| [19] |
REZATOFIGHI H,TSOI N,GWAK J Y,et al.Generalized intersection over union:A metric and a loss for bounding box regression[J].IEEE,2019. |
| [20] |
GUO T,WEI Y,SHAO H,et al.Research on underwater target detection method based on improved MSRCP and YOLOv3[C]//2021 IEEE International Conference on Mechatronics and Automation (ICMA).IEEE,2021:1158-1163. |
| [21] |
EVERINGHAM M,ZISSERMAN A,WILLIAMS C K I,et al.The PASCAL visual object classes challenge 2006 (VOC2006) results[R].2006. |
| [22] |
PADILLA R,PASSOS W L,DIAS T L B,et al.A comparative analysis of object detection metrics with a companion open-source toolkit[J].Electronics,2021,10(3):279. |
国家自然科学基金项目(51908136)
/
| 〈 |
|
〉 |