首页|期刊导航|水力发电学报|深水大坝混凝土裂缝实时像素级分割与量化方法

深水大坝混凝土裂缝实时像素级分割与量化方法OA

Method for real-time pixel-level segmentation and quantification of concrete cracks in underwater dams

中文摘要英文摘要

为解决深水大坝混凝土裂缝检测困难的问题,提出一种深水大坝混凝土裂缝实时像素级分割与量化方法.模型采用对称型结构,各层特征采用跳跃连接传递,通过视觉变换器(ViT)和卷积块注意力网络(CBAM)组合策略实现对水下复杂裂缝特征的充分提取,采用深度可分离卷积对网络模型实现轻量化,选取Focal Tversky Loss对损失函数进行优化,克服了水下裂缝前后背景不平衡问题,实现对水下裂缝区域的准确识别.依托观音岩水电站,进行水下裂缝分割的消融实验和对比实验,验证了本文方法相比其余模型的分割性能优势,本文方法的平均交并比(mIoU)、召回率(Recall)、精确率(Precision)和F1分数(F1_score)分别为0.913、0.949、0.957和0.953.同时将区域像素提取与红外激光测距技术相结合,对裂缝的几何尺寸进行量化,得到的量化结果与基于标注掩膜的结果拟合较好.

To address the challenge of detecting concrete cracks in underwater dams,this study develops a novel method for real-time pixel-level segmentation and quantification of underwater crack images.It adopts a model of symmetric architecture,with skip connections used for transmitting features across layers,and uses a combination of Vision Transformer(ViT)and Convolutional Block Attention Module(CBAM)to fully extract complicated crack features.To mitigate the issue of foreground-background imbalance in the images,we use the depthwise separable convolution to lighten the network and the Focal Tversky Loss to optimize the loss function,thereby enhancing the accuracy of crack area recognition.In a case study of the Guanyinyan hydropower station,we conduct an ablation experiment of underwater crack segmentation and compare different methods,verifying the performance advantage of our model over other models-with the mean Intersection over Union(mIoU),Recall,Precision,and F1 score of 0.913,0.949,0.957,and 0.953,respectively.And,we combine regional pixel extraction with the infrared laser ranging technology to quantify the geometric dimensions of the cracks,and achieve the results that agree well with those derived from the annotated masks.

麻昀霖;包腾飞;李扬涛;李田雨;汪万升;张礼兵

河海大学 水灾害防御全国重点实验室,南京 210098||河海大学 水利水电学院,南京 210098河海大学 水灾害防御全国重点实验室,南京 210098||河海大学 水利水电学院,南京 210098南京林业大学 土木工程学院,南京 210037三江学院 土木工程学院,南京 210012河海大学 水灾害防御全国重点实验室,南京 210098||河海大学 水利水电学院,南京 210098中国电建集团昆明勘测设计研究院有限公司,昆明 650051

建筑与水利

深水大坝裂缝识别深度学习像素级分割遥控潜水器红外激光测距

underwater damcrack detectiondeep learningpixel-level segmentationremotely operated vehicleinfrared laser ranging

《水力发电学报》 2026 (10)

56-67,12

江苏省研究生科研创新项目(26CXJH1474)宁波市水利科技资助项目(NSKA202409)云南省工程研究中心创新能力建设提升专项(202310)

10.11660/slfdxb.20261006

评论