基于改进DeeplabV3+和迁移学习的桥梁裂缝检测

doi:10.3778/j.issn.1002-8331.2204-0503

摘要/Abstract

摘要： 裂缝作为桥梁最主要的病害之一，及时高效地发现和评估裂缝对保持桥梁的健康状况至关重要。针对裂缝标注数据集成本高、检测精度低等问题，提出了一种基于注意力机制和迁移学习的改进DeeplabV3+模型。该模型通过添加注意力机制来获取丰富上下文信息，提高裂缝特征通道的学习能力，降低背景噪声影响；通过公共数据集和小样本数据集组合建立源域数据集、目标域数据集以供迁移学习使用，以此来降低训练样本过少对检测性能的影响。实验结果表明，改进DeeplabV3+模型对桥梁裂缝检测获得了较好的检测效果，检测精度达到了93.3%，较原始模型提高了3个百分点；通过迁移学习训练模型在小样本数据上取得较高的检测精度，可节省大量标注成本。

关键词: 裂缝检测, 小样本学习, 迁移学习, 语义分割, 注意力机制

Abstract: Cracks are one of the most important diseases of bridges. Timely and efficient detection and evaluation of cracks is very important to maintain the health of bridges. Aiming at the high integration cost and low detection accuracy of fracture annotation data, an improved DeeplabV3+ model based on attention mechanism and transfer learning is proposed. The model adds attention mechanism to obtain rich context information, improve the learning ability of crack feature channel and reduce the influence of background noise and other features. Then, through the combination of public data set and small sample data set, the source domain data set and target domain data set are established for migration learning, so as to reduce the impact of too few training samples on detection performance. The experimental results show that the improved DeeplabV3+ model has achieved good detection effect on bridge crack detection, and the detection accuracy has reached 93.3%, which is 3 percentage points higher than the original model. The transfer learning training model achieves high detection accuracy on small sample data, which can save a lot of labeling costs.

Key words: crack detection, small sample learning, transfer learning, semantic segmentation, attention mechanism

赵雪冰, 王俊杰. 基于改进DeeplabV3+和迁移学习的桥梁裂缝检测[J]. 计算机工程与应用, 2023, 59(5): 262-269.

ZHAO Xuebing, WANG Junjie. Bridge Crack Detection Based on Improved DeeplabV3+ and Migration Learning[J]. Computer Engineering and Applications, 2023, 59(5): 262-269.

参考文献

[1] PRASANNA P，DANA K J，GUCUNSKI N，et al.Automated crack detection on concrete bridges[J].IEEE Transactions on Automation Science and Engineering，2016，13（2）：591-599.
[2] 蒋文波，罗秋容，张晓华.基于数字图像的混凝土道路裂缝检测方法综述[J].西华大学学报（自然科学版），2018，37（1）：75-84.
JIANG W B，LUO Q R，ZHANG X H.A review of concrete roads crack detection methods based on digital image[J].Journal of Xihua University（Natural Science Edition），2018，37（1）：75-84.
[3] 顾书豪，李小霞，王学渊，等.增强语义信息与多通道特征融合的裂缝检测[J].计算机工程与应用，2021，57（10）：204-210.
GU S H，LI X X，WANG X Y，et al.Crack detection based on enhanced semantic information and multi-channel feature fusion[J].Computer Engineering and Applications，2021，57（10）：204-210.
[4] ELLENBERG A，KONTSOS A，BARTOLI I，et al.Masonry crack detection application of an unmanned aerial vehicle[C]//International Conference on Computing in Civil & Building Engineering，1995.
[5] 张诗慧，罗晖，裴莹玲，等.基于改进RetinaNet的高铁无砟轨道板表面裂缝检测[J/OL].计算机工程与应用：1-9[2022-03-08].http://kns.cnki.net/kcms/detail/11.2127.TP.20220226.
1844.004.html.
ZHANG S H，LUO H，PEI Y L，et al.Surface crack detection in ballastless slab track of high-speed railway based on improved RetinaNet[J/OL].Computer Engineering and Applications：1-9[2022-03-08].http://kns.cnki.net/kcms/detail/11.2127.TP.20220226.1844.004.html.
[6] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[J].arXiv：1505.04597，2015.
[7] BADRINARAYANAN V，KENDALL A，CIPOLLA R.SegNet：a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（12）：2481-2495.
[8] CHEN L C，ZHU Y，PAPANDREOU G，et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[J].arXiv：1802.02611，2018.
[9] 常惠，饶志强，赵玉林，等.基于改进U-Net网络的隧道裂缝分割算法研究[J].计算机工程与应用，2021，57（22）：215-222.
CHANG H，RAO Z Q，ZHAO Y L，et al.Research on tunnel crack segmentation algorithm based on improved U-Net network[J].Computer Engineering and Applications，2021，57（22）：215-222.
[10] LIU J，YANG X，LAU S，et al.Automated pavement crack detection and segmentation based on two-step convolutional neural network[J].Computer-Aided Civil and Infrastructure Engineering，2020，35（11）：1291-1305.
[11] CHEN T，CAI Z，ZHAO X，et al.Pavement crack detection and recognition using the architecture of SegNet[J].Journal of Industrial Information Integration，2020，18（2）：100144.
[12] CHEN J，ZHANG D，HUANG H，et al.Image-based segmentation and quantification of weak interlayers in rock tunnel face via deep learning[J].Automation in Construction，2020，120：103371.
[13] 袁嘉豪，张伟锋，岳学军，等.多种主干网络下DeepLabv3+的混凝土梁裂缝语义分割研究[C]//中国水利学会2021学术年会论文集第五分册，2021：160-164.
YUAN J H，ZHANG W F，YUE X J，et al.Research on semantic segmentation of concrete beam cracks based on DeepLabv3+ under various backbone networks[C]//Proceedings of 2021 Academic Annual Meeting of Chinese Hydraulic Engineering Society，Volume 5，2021：160-164.
[14] WANG H X，LI Y F，DANG L M，et al.Pixel-level tunnel crack segmentation using a weakly supervised annotation approach[J].Computers in Industry，2021，133：103545.
[15] 邱宁佳，王晓霞，王鹏，等.结合迁移学习模型的卷积神经网络算法研究[J].计算机工程与应用，2020，56（5）：43-48.
QIU N J，WANG X X，WANG P，et al.Research on convolutional neural network algorithm combined with transfer learning model[J].Computer Engineering and Applications，2020，56（5）：43-48.
[16] CHOLLET F.Xception：deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017.
[17] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016.
[18] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[19] HU J，SHEN L，SUN G，et al.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018.
[20] ROY A G，NAV AB N，WACHINGER C.Concurrent spatial and channel squeeze & excitation in fully convolutional networks[J].arXiv：1803.02579，2018.
[21] IOFFE S，SZEGEDY C.Batch normalization：accelerating deep network training by reducing internal covariate shift[J].arXiv：1502.03167，2015.
[22] WU Y，HE K.Group normalization[J].arXiv：1803.08494，2018.
[23] LEI Z，YANG F，ZHANG D，et al.Road crack detection using deep convolutional neural network[C]//IEEE International Conference on Image Processing，2016.
[24] ZGENEL F，SORGU A G.Performance comparison of pretrained convolutional neural networks on crack detection in buildings[C]//35th International Symposium on Automation and Robotics in Construction（ISARC 2018），2018.
[25] LIU Y，YAO J，LU X，et al.DeepCrack：a deep hierarchical feature learning architecture for crack segmentation[J].Neurocomputing，2019，338：139-153.
[26] ZOU Q，CAO Y，LI Q Q，et al.Crack tree：automatic crack detection from pavement images[J].Pattern Recognition Letters，2012，33（3）：227-238.
[27] SHI Y，CUI L M，QI Z Q，et al.Automatic road crack detection using random structured forests[J].IEEE Transactions on Intelligent Transportation Systems，2016，17（12）：3434-3445.
[28] RUSSELL B C，TORRALBA A，MURPHY K P，et al.LabelMe：a database and web-based tool for image annotation[J].International Journal of Computer Vision，2008，77：157-173.
[29] 李良福，马卫飞，李丽，等.基于深度学习的桥梁裂缝检测算法研究[J].自动化学报，2019，45（9）：1727-1742.
LI L F，MA W F，LI L，et al.Research on detection algorithm for bridge cracks based on deep learning[J].Acta Automatica Sinica，2019，45（9）：1727-1742.
[30] SANDLER M，HOWARD A，ZHU M，et al.MobileNetV2：inverted residuals and linear bottlenecks[J].arXiv：1801. 04381，2018.