基于HU-ResNet的混凝土表观裂缝信息提取

doi:10.19678/j.issn.1000-3428.0056061

摘要/Abstract

摘要： 针对混凝土结构表观裂缝检测准确率低、细节信息丢失及精度不高等问题，提出一种利用HU-ResNet卷积神经网络的混凝土表观裂缝检测方法。基于改进U-Net网络建立HU-ResNet模型，采用经ImageNet预训练的ResNet34残差网络作为编码器，以保留裂缝细节信息并加速网络收敛，引入scSE注意力机制模块在空间和通道重新标定编码块与解码块的输出特征，并利用超柱模块融合解码器各阶段所输出特征图获取更精确的裂缝图像语义信息和定位，同时采用组合损失函数进一步提高裂缝图像精度。实验结果表明，该模型的像素准确率、交并比和F1值分别达到0.990 4、0.693 3和0.816 6，优于Canny、区域生长等传统数字图像模型和FCN8s、U-Net、U-ResNet等深度学习模型且裂缝检测更精准。

关键词: 混凝土表观裂缝, HU-ResNet卷积神经网络, 组合损失函数, scSE模块, 超柱模块

Abstract: Existing detection methods for apparent crack of concrete structure are inaccurate and low-precision,losing much detail information.To address the problem,this paper proposes an apparent crack detection method for concrete based on the HU-ResNet Convolutional Neural Networks(CNN).Based on improved U-Net,the HU-ResNet model is established using the ResNet34 residual network trained by ImageNet as the encoder to retain crack details and accelerate network convergence.The scSE attention mechanism module is also introduced to recalibrate the output characteristics of the encoding block and decoding block in space and channel.At the same time,the output feature maps of each stage of the decoder are fused by the hypercolumn module to obtain more accurate semantic information and location of crack images,and the precision of which is further improved by using the combined loss function.Experimental results show that the pixel accuracy,Intersection-over-Union and F1 value of the proposed model reach 0.990 4,0.693 3 and 0.816 6 respectively,which are better than that of Canny, region growing and other traditional digital image models and FCN8s,U-Net,U-ResNet and other deep learning models,and the proposed model has more accurate crack detection results.

Key words: apparent crack of concrete, HU-ResNet Convolutional Neural Networks(CNN), combined loss function, scSE module, hypercolumn module

中图分类号:

TP391

徐国整, 廖晨聪, 陈锦剑, 董斌, 周越. 基于HU-ResNet的混凝土表观裂缝信息提取[J]. 计算机工程, 2020, 46(11): 279-285.

XU Guozheng, LIAO Chencong, CHEN Jinjian, DONG Bin, ZHOU Yue. Extraction of Apparent Crack Information of Concrete Based on HU-ResNet[J]. Computer Engineering, 2020, 46(11): 279-285.

图/表 10

参考文献

[1] MOHAN A R,POOBAL S.Crack detection using image processing:a critical review and analysis[J].Alexandria Engineering Journal,2018,57(2):787-798.
[2] DAVIS L S.A survey of edge detection techniques[J].Computer Graphics and Image Processing,1975,4(3):248-270.
[3] HAN Siqi,WANG Lei.A survey of thresholding methods for image segmentation[J].Journal of Systems Engineering and Electronics,2002,24(6):91-94.(in Chinese)韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术,2002,24(6):91-94.
[4] ADHIKARI R S,MOSELHI O,BAGCHI A.Image-based retrieval of concrete crack properties for bridge inspection[J].Automation in Construction,2014,39(4):180-194.
[5] CHA Y J,CHOI W,BÜYÜKÖZTÜRK O.Deep learning-based crack damage detection using convolutional neural networks[J].Computer-Aided Civil and Infrastructure Engineering,2017,32(5):361-378.
[6] KIM B,CHO S.Automated vision-based detection of cracks on concrete surfaces using a deep learning technique[J].Sensors,2018,18(10):3452-3453.
[7] WEN Zuolin,SHEN Yonggang,SU Jian,et al.Concrete crack detection method based on CNN[J].Low Tem-perature Architecture Technology,2019,41(6):9-12.(in Chinese)温作林,申永刚,苏建,等.基于卷积神经网络的混凝土裂缝识别[J].低温建筑技术,2019,41(6):9-12.
[8] HAN Xiaojian,ZHAO Zhicheng.Structural surface crack detection method based on computer vision technology[J].Journal of Building Structures,2018,39(S1):418-427.(in Chinese)韩晓健,赵志成.基于计算机视觉技术的结构表面裂缝检测方法研究[J].建筑结构学报,2018,39(S1):418-427.
[9] LIU Xingen,CHEN Yingying,ZHU Aixi,et al.Tunnel crack identification based on deep learning[J].Journal of Guangxi University(Natural Science Edition),2018,43(6):2243-2251.(in Chinese)刘新根,陈莹莹,朱爱玺,等.基于深度学习的隧道裂缝识别方法[J].广西大学学报(自然科学版),2018,43(6):2243-2251.
[10] FENG Hui.Research and implementation of road crack detection algorithm based on deep learning[D].Beijing:Beijing University of Posts and Telecommunications,2019.(in Chinese)冯卉.基于深度学习的道路裂缝识别算法研究与实现[D].北京:北京邮电大学,2019.
[11] JIA Xiaoyu.Measurement based on convolutional neural networks[D].Liuzhou:Guangxi University of Science and Technology,2019.(in Chinese)贾潇宇.基于卷积神经网络的桥梁裂缝识别与测量方法研究[D].柳州:广西科技大学,2019.
[12] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[13] LI Shengyuan,ZHAO Xuefeng,ZHOU Guangyi.Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network[J].Computer-Aided Civil and Infrastructure Engineering,2019,34(7):616-634.
[14] YANG Xincong,LI Heng,YU Yantao,et al.Automatic pixel-level crack detection and measurement using fully convolutional network[J].Computer-Aided Civil and Infrastructure Engineering,2018,33(12):1090-1109.
[15] WANG Sen,WU Xing,ZHANG Yinhui,et al.Image crack detection with fully convolutional network based on deep learning[J].Journal of Computer-Aided Design and Computer Graphics,2018,30(5):859-867.(in Chinese)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.
[16] LI Chuanpeng,QIN Pinle,ZHANG Jinjing.Research on image denoising based on deep convolutional neural network[J].Computer Engineering,2017,43(3):253-260.(in Chinese)李传朋,秦品乐,张晋京.基于深度卷积神经网络的图像去噪研究[J].计算机工程,2017,43(3):253-260.
[17] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[18] NOH H,HONG S,HAN B.Learning deconvolution network for semantic segmentation[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:21-27.
[19] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of 2015 International Conference on Medical Image Computing and Computer-assisted Intervention.Berlin,Germany:Springer,2015:234-241.
[20] CHENG Jierong,XIONG Wei,CHEN Wenyu,et al.Pixel-level crack detection using U-Net[C]//Proceedings of TENCON'18.Washington D.C.,USA:IEEE Press,2018:462-466.
[21] ZHU Suya,DU Jianchao,LI Yunsong,et al.Method for bridge crack detection based on the U-Net convolutional networks[J].Journal of Xidian University,2019,46(6):1-8.(in Chinese)朱苏雅,杜建超,李云松,等.采用-卷积网络的桥梁裂缝检测方法[J].西安电子科技大学学报,2019,46(6):1-8.
[22] ROY A G,NAVAB N,WACHINGER C.Concurrent spatial and channel ‘squeeze & excitation’ in fully con-volutional networks[C]//Proceedings of MICCAI'18.Berlin,Germany:Springer 2018:421-429.
[23] WONG Piao.Research on segmentation algorithm of pavement crack in complex environment[D].Zhengzhou:Zhengzhou University,2019.(in Chinese)翁飘.复杂环境下路面裂缝分割算法研究[D].郑州:郑州大学,2019.
[24] HARIHARAN B,ARBELAEZ P,GIRSHICK R,et al.Hypercolumns for object segmentation and fine-grained localization[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:33-39.
[25] KANG Le,YE Peng,LI Yi,et al.Convolutional neural networks for no-reference image quality assessment[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:55-62.
[26] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:132-138.
[27] DORAFSHAN S,MAGUIRE M,THOMAS R.SDNET2018:a concrete crack image dataset for machine learning applications[EB/OL].[2019-08-03].https://www.researchgate.net/publication/325719429_SDNET2018_A_concrete_crack_image_dataset_for_machine_learning_applications.