唐东林;吴续龙;周立;宋一言;秦北轩;

• 1:西南石油大学机电工程学院

摘要(Abstract)：

为解决传统建筑墙体检测采用人工目视方式效率低、成本高、危险性大的问题，提出利用无人机拍摄建筑外墙缺陷图像，采用卷积神经网络(Convolutional Neural Network, CNN)结合注意力机制实现对威胁建筑外墙安全缺陷的识别分类。从获取建筑外墙缺陷图像数据开始，制作缺陷图像数据集，以威胁墙体安全的缺陷为学习样本，构造浅层卷积神经网络，融入BAM(Bottleneck Attention Module)注意力机制，从卷积神经网络提取的浅层特征中提炼缺陷特征进行学习，实现建筑外墙的安全检测。经试验，多类安全问题检测正确率达到96.18%,所提出的模型相较传统的CNN、VGG 16、ResNet 18算法，检测正确率分别提高了3.36个百分点、3.92个百分点、14.6个百分点。研究表明，卷积神经网络结合注意力机制的方法可以避免局部缺陷丢失，提高检测正确率。

关键词(KeyWords)： 安全工程;墙体缺陷;BAM注意力机制;卷积神经网络;深度学习

Abstract:

Keywords:

基金项目(Foundation):

作者(Authors): 唐东林;吴续龙;周立;宋一言;秦北轩;

DOI: 10.13637/j.issn.1009-6094.2020.1612

参考文献(References)：

• [1] FORSTER A,VALERO E,BOSCHé F.Automated defect detection and classification in ashlar masonry walls using machine learning[J].Automation in Construction,2019,106(5):102846.
• [2] 王森，伍星，张印辉，等.基于深度学习的全卷积网络图像裂纹检测[J].计算机辅助设计与图形学学报，2018,30(5):859-867.WANG S,WU X,ZHANG Y H,et al.Image crack detection with fully convolutional network based on deep learning[J].Journal of Computer-Aided Design & Computer Graphics,2018,30(5):859-867.
• [3] HANIF M U,IBRAHIM Z,GHAEDI K,et al.Damage assessment of reinforced concrete structures using a model-based nonlinear approach—a comprehensive review[J].Construction and Building Materials,2018,192:846-865.
• [4] STRAUB A.Dutch standard for condition assessment of buildings[J].Structural Survey,2009,27(1):23-35.
• [5] MOHSENI S A,WU H R,THOM J A,et al.Recognizinginduced emotions with only one feature:a novel color histogram-based system[J].IEEE Access,2020,8:37173-37190.
• [6] HALFAWY M R,HENGMEECHAI J.Automated defect detection in sewer closed circuit television images using histograms of oriented gradients and support vector machine[J].Automation in Construction,2014,38:1-13.
• [7] HU Y,ZHAO C.A novel LBP based methods for pavement crack detection[J].Journal of Pattern Recognition Research,2010,5(1):140-147.
• [8] ONIZAWA N,KATAGIRI D,MATSUMIYA K,et al.Gabor filter based on stochastic computation[J].IEEE Signal Processing Letters,2015,22(9):1224-1228.
• [9] BHARDWAJ J,NAYAK A.Haar wavelet transform-based optimal Bayesian method for medical image fusion[J].Medical & Biological Engineering & Computing,2020,58(10):2397-2411.
• [10] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
• [11] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J/OL].Computer Science,2014[2015-04-10].https://arxiv.org/pdf/1409.1556.pdf.
• [12] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Institute of Electrical and Electronics Engineers.Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington DC:IEEE Computer Society,2016:770-778.
• [13] 翟懿奎，刘健.面向人脸表情识别的迁移卷积神经网络研究[J].信号处理，2018,34(6):729-738.ZHAI Y K,LIU J.Facial expression recognition based on transferring convolutional neural network[J].Journal of Signal Processing,2018,34(6):729-738.
• [14] CHA Y J,CHOI W,BüYüK?ZTüRK O.Deep learning‐based crack damage detection using convolutional neural networks[J].Computer-Aided Civil and Infrastructure Engineering,2017,32(5):361-378.
• [15] REDDY A,GANDHI V I,RAVI L,et al.Detection ofcracks and damage in wind turbine blades using artificial intelligence-based image analytics[J].Measurement,2019,147(6):106823.
• [16] 郑伟皓，周星宇，李红梅，等.基于GIS空间分析及深度学习的调车场安全识别系统[J].安全与环境学报，2020,20(2):423-432.ZHENG W H,ZHOU X Y,LI H M,et al.Safety identification and recognition system of shunting yard based on the spatial analysis of GIS and deep learning[J].Journal of Safety and Environment,2020,20(2):423-432.
• [17] DENHOF D,STAAR B,LüTJEN M,et al.Automatic optical surface inspection of wind turbine rotor blades using convolutional neural networks[J].Procedia CIRP,2019,81:1166-1170.
• [18] PARK J,WOO S,LEE J Y,et al.Asimple and light-weight attention module for convolutional neural networks[J].International Journal of Computer Vision,2020,128(9):783-798.
• [19] LI L H,TANG S,ZHANG Y D,et al.GLA:global-local attention for image description[J].IEEE Transactions on Multimedia,2017,20(3):726-737.
• [20] LIU Q W,XIANG X Q,WANG Y F,et al.Aircraft detection in remote sensing image based on corner clustering and deep learning[J].Engineering Applications of Artificial Intelligence,2020,87:103333.