基于特征增强的水工结构裂缝语义分割方法  

Semantic segmentation method of hydraulic structure crack based on feature enhancement

作　　者：陈波 张华[1,2] 陈永灿[3,4] 李永龙 熊劲松 CHEN Bo;ZHANG Hua;CHEN Yongcan;LI Yonglong;XIONG Jinsong(School of Information Engineering,Southwest University of Science and Technology,Mianyang 621000,China;Innovation Research Institute of Sichuan Tianfu New District,Southwest University of Science and Technology,Chengdu 621010,China;State Key Laboratory of Hydroscience and Engineering,Tsinghua University,Beijing 100084,China;College of Civil Engineering and Surveying and Mapping,Southwest Petroleum University,Chengdu 610500,China;Department of Electronic Engineering,Tsinghua University,Beijing 100084,China;Sichuan Energy Internet Research Institute,Tsinghua University,Chengdu 610213,China;Chongqing Hongyan Construction Machinery Manufacturing Co.,Ltd.,Chongqing 400712,China)

机构地区：[1]西南科技大学信息工程学院,绵阳621000 [2]西南科技大学西南科大四川天府新区创新研究院,成都621010 [3]清华大学水沙科学与水利水电工程国家重点实验室,北京100084 [4]西南石油大学土木工程与测绘学院,成都610500 [5]清华大学电子工程系,北京100084 [6]清华四川能源互联网研究院,成都610213 [7]重庆红岩建设机械制造有限责任公司,重庆400712

出　　处：《清华大学学报（自然科学版）》2023年第7期1135-1143,共9页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金资助项目(U21A20157);四川省科技计划项目(2022YFSY0011,2022YFQ0080,2023YFS0410)。

摘　　要：基于计算机视觉的混凝土裂缝自动检测方法逐渐成为大坝、廊道和引水隧洞等水工结构场景检测任务的主流选择。然而,目前大多数方法在裂缝特征提取过程中均存在不同程度的损耗,缺乏针对性的补偿措施,导致最终检测效果不佳。该文提出了一种基于特征增强的水工结构裂缝语义分割方法,主要用于解决混凝土水工结构裂缝高精度语义分割问题。该方法通过对裂缝数据进行统计学分析,获取裂缝像素与非裂缝像素关系及其对应分布情况;采用ResNet-152特征提取网络提取裂缝图像抽象语义信息,并根据统计分析结果对高维特征进行区域聚集,构建自注意力模块,增强模型对裂缝的定位性能;结合裂缝信息分布情况,对网络损失函数进行优化,增加裂缝特征对总体损失值的贡献率,提升模型对裂缝的识别精度。该文采用智能化设备获取大坝和廊道2种水工结构场景的图像数据,图像数据经图像预处理和标注整理后获得的裂缝图像和标签共3000张;将由训练获得的分割模型在测试集上进行测试,裂缝像素准确率、召回率、交并比和总像素准确率分别达92.48%、86.52%、80.82%和99.79%。该文提出的分割方法在水工结构裂缝检测方面具有一定应用研究价值和推广意义。[Objective]Scientific,comprehensive,and standardized health monitoring is critical in the operation and maintenance of all types of water conservancy infrastructure.In this study,intelligent equipment is used to capture crack images of concrete dams and corridor hydraulic engineering scenes,and an artificial intelligence algorithm is used to achieve accurate recognition of crack information.However,most current research on concrete crack recognition lacks the analysis of crack information and simply obtains crack features through convolution and pooling to form a feature extraction network.The extracted high-dimensional features are not enhanced further,so the recognition effect cannot be continuously improved.A semantic segmentation technique for feature enhancement is proposed to solve the problem of low accuracy of crack location in the automatic detection of concrete cracks.[Methods] Statistical theory is used in this study to assess the pixel values of the cracked and non-cracked regions in three color channels and the proportion of the cracked region in the image.The size relationship and corresponding distribution of cracked and non-cracked regions on the pixel level are also obtained.Then,the ResNet-152 feature extraction network based on the residual structure is used to extract high-dimensional abstract semantic features from crack images.Due to the particularity of the residual structure,it can effectively reduce the loss of crack information during feature transmission and improve feature interoperability between different layers of the network so as to avoid the problem of gradient disappearance or explosion.Then,based on the results of statistical analysis,high-dimensional abstract features are sampled into two coarse segmentation feature maps corresponding to cracks and non-cracks.The similarity between the high-dimensional abstract features and the coarse segmentation feature map is calculated,the results of which are then used as weights to update high-dimensional abstract features to realize reg

关 键 词：水工裂缝 卷积神经网络 统计学分析 语义分割 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]