基于分层特征残差神经网络的桥梁水下结构裂缝分割

王明俊; 苏智文; 陈炳聪; 刘爱荣

doi:10.3724/j.gyjzG23030303

基于分层特征残差神经网络的桥梁水下结构裂缝分割

doi: 10.3724/j.gyjzG23030303

1. 广州市中心区交通项目管理中心, 广州 510030;
2. 广州大学, 广州 510006

基金项目:

国家自然科学基金项目（52279127）。

详细信息

作者简介:
王明俊，女， 1972 年出生，硕士，主要从事桥梁检测方面的研究。

通讯作者:
陈炳聪， bc_chen@gzhu.edu.cn。

计量
- 文章访问数: 64
- HTML全文浏览量: 1
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2023-03-03
- 网络出版日期: 2024-05-29

Crack Segmentation of Underwater Structures of Bridges Based on Hierarchical Feature Residual Neural Network

1. Traffic Project Management Center of Guangzhou Central District, Guangzhou 510030, China;
2. Guangzhou University, Guangzhou 510006, China

摘要

摘要: 为提高桥梁水下结构裂缝检测任务的自动化水平，提出了一种基于分层残差神经网络的裂缝检测方法。该方法利用多层次特征残差连接机构，抑制了建筑表面噪声特征的干扰，提取并融合了不同层次的特征图像，增强了模型对裂缝区域和非裂缝区域的精确划分能力。同时借助迁移学习方法，利用预训练模型的参数初始化模型并借助水下裂缝数据集调整权重，使模型具备分析数据量极少的桥梁水下结构裂缝数据集的能力。该模型在自采集的桥梁水下结构裂缝数据集上进行了试验验证。结果表明：分层残差神经网络具备精确划分裂缝像素与非裂缝像素的能力，预测像素准确率达到87.2%，证明了该方法的可行性。该模型为桥梁水下结构裂缝检测任务的自动化提供了一种有效的解决方案，同时也为其他类似的图像检测任务提供了一种参考思路。
- 桥梁检测 /
- 裂缝检测 /
- 迁移学习
Abstract: A crack detection method based on hierarchical residual neural network is proposed to improve the automation of the crack detection task for underwater structures of bridges. The method utilizes a multi-level feature residual linkage mechanism, which suppresses the interference of noise features on the building surface, extracts and fuses feature images at different levels, and enhances the model's capacity to accurately delineate cracked and non-cracked regions. Meanwhile, with the help of transfer learning method, the model is initialized with the parameters of the pre-trained model and the weights are adjusted with the underwater crack dataset, so that the model has the capacity to analyze the bridge underwater structure crack dataset with very small amount of data. The model was experimentally validated on a self-collected bridge underwater structural crack dataset. The results showed that the hierarchical residual neural network could accurately classify cracked pixels from non-cracked pixels, and the predicted pixel accuracy reached 87.2%, which proved the feasibility of the method. The model provides an effective solution for automating the bridge underwater structural crack detection task, and also provides a reference idea for other similar image detection tasks.
- bridge inspection /
- crack detection /
- transfer learning

HTML全文

参考文献(22)

[1]	陈子龙.桥梁工程裂缝成因及防治措施[J].交通世界, 2022(23):114-116.
[2]	ZOU Q, CAO Y, LI Q, et al. CrackTree:automatic crack detection from pavement images[J].Pattern Recognit Lett, 2012, 33(3):227-238.
[3]	LI Q, ZOU Q, ZHANG D, et al. FoSA:F*Seed-growing approach for crack-line detection from pavement images[J]. Image Vis Comput, 2011, 29(12):861-872.
[4]	XIE S, TU Z. et al. Holistically-nested edge detection[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015:1395-1403.
[5]	KIM B, CHO S. Image-based concrete crack assessment using mask and region-based convolutional neural network[J]. Structure Control Health Monitoring, 2019, 26(8), e2381.
[6]	LI C, XU P, NIU L, et al. Tunnel crack detection using coarseto-fine region localization and edge detection[J]. Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery, 2019, 9(5), e1308.
[7]	胡文魁,邓晖,付志旭,等.基于全卷积神经网络的桥梁裂缝分割和测量方法[J].工业建筑, 2022, 52(4):192-201 , 218.
[8]	HUBEL D H, WIESEL T N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex[J]. The Journal of Physiology, 1962, 160(1):106-154.
[9]	HU Y, ZHAO C. A novel LBP based methods for pavement crack detection[J]. Journal of Pattern Recognition Research, 2010, 5(1):140-147.
[10]	LI Q, LIU X. Novel approach to pavement image segmentation based on neighboring difference histogram method[C]//2008 Congress on Image and Signal Processing. Sanya, China:IEEE, 2008:792-796.
[11]	TAN M, LE Q. Efficientnet:rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning. California, USA:PMLR, 2019:6105-6114.
[12]	LIU W, RABINOVICH A, BERG A C, et al. ParseNet:looking wider to see better[J/OL]. Computer Science, 2015[2023-03-03]. http://arxiv.org/abs/1506.04579
[13]	KONG T, YAO A, CHEN Y, et al. HyperNet:towards accurate region proposal generation and joint object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA:2016:845-853.
[14]	HARIHARAN B, ARBELÁEZ P, GIRSHICK R, et al. Hypercolumns for object segmentation and fine-grained localization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA:2015:447-456.
[15]	WEISS K, KHOSHGOFTAAR T M, WANG D D, et al. A survey of transfer learning[J]. Journal of Big Data, 2016, 3(1):1-40.
[16]	ZHUANG F, QI Z, DUAN K, et al. A comprehensive survey on transfer learning[J]. Proceedings of the IEEE, 2020, 109(1):43-76.
[17]	ELHASSOUNY A, SMARANDACHE F. Trends in deep convolutional neural Networks architectures:a review[C]//2019 International Conference of Computer Science and Renewable Energies (ICCSRE). Agadir, Morocco:IEEE, 2019:1-8.
[18]	SHAFIQ M, GU Z. Deep residual learning for image recognition:a survey[J]. Applied Sciences, 2022, 12(18), 8972.
[19]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA:2016:770-778.
[20]	XIE S, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA:2017:1492-1500.
[21]	LIU Y, YAO J, LU X, et al. DeepCrack:a deep hierarchical feature learning architecture for crack segmentation[J]. Neurocomputing, 2019, 338:139-153.
[22]	谢文高,张怡孝,刘爱荣,等.基于水下机器人与数字图像技术的混凝土结构表面裂缝检测方法[J].工程力学, 2022, 39(增刊1):64-70.