采用U-Net卷积网络的桥梁裂缝检测方法

doi:10.19665/j.issn1001-2400.2019.04.006

摘要/Abstract

摘要：

针对传统的桥梁裂缝检测准确性不高、丢失细节信息、宽度信息获取困难等问题,提出一种采用U-Net卷积网络的像素级、小样本的裂缝检测方法。该方法使用多层卷积自动提取裂缝特征,并利用浅层网络与深层网络叠加的方法实现裂缝局部特征与抽象特征的融合,从而保留裂缝细节特征,使得检测准确性大大提升。对检测结果中出现的背景杂波和伪裂缝,采用阈值法和改进的迪杰斯特拉连接算法来实现裂缝的精细提取。最后,采用八方向搜索法实现裂缝宽度的精确测量。实验证明,所提方法能准确、完整地对桥梁裂缝进行提取,宽度测量准确,可以满足应用需求。

关键词: 图像处理, 桥梁裂缝检测, 卷积神经网络, U-Net网络

Abstract:

In order to improve the accuracy of bridge crack detection, retain details, and get information on the crack width, the paper proposes a pixel-wise and small sample crack detection method by using U-Net convolutional neural networks. The method uses a U-Net network to extract crack features automatically by using multi-layer convolutions, and uses the superposition of the shallow network and deep network to realize the fusion of local features and abstract features of cracks. This method can retain the details of cracks and greatly improve the accuracy of detection. In order to refine the detection results, the paper presents the threshold method and an improved Dijkstra minimum spanning tree algorithm for eliminating noise and pseudo cracks. Finally, an eight-direction searching method is applied to measure the width of cracks in pixels. Experiments prove that the proposed method can accurately and completely detect bridge cracks and measure the width, which can meet the application requirements.

Key words: image processing, bridge cracks detection, convolutional neural networks, U-Net network

中图分类号:

TP751

朱苏雅,杜建超,李云松,汪小鹏. 采用U-Net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(4): 35-42.

ZHU Suya,DU Jianchao,LI Yunsong,WANG Xiaopeng. Method for bridge crack detection based on the U-Net convolutional networks[J]. Journal of Xidian University, 2019, 46(4): 35-42.

图/表 9

图1

图2

图3

图4

表1

图5

图6

图7

表2

参考文献 15

[1]	TONG X, GUO J, LING Y. et al. A New Image-based Method for Concrete Bridge Bottom Crack Detection [C]//Proceedings of the 2011 International Conference on Image Analysis and Signal Processing. Washington: IEEE Computer Society, 2011: 568-571.
[2]	XU H, TIAN Y, LIN S. et al. Research of Image Segmentation Algorithm Applied to Concrete Bridge Cracks [C]//Proceedings of the 2013 IEEE Third International Conference on Information Science and Technology. Washington: IEEE Computer Society, 2013: 1637-1640.
[3]	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.
[4]	GUAN H, LI J, YU Y , et al. Iterative Tensor Voting for Pavement Crack Extraction Using Mobile Laser Scanning Data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015,53(3):1527-1537.
[5]	马苗, 许西丹, 武杰 . 一种耦合深度信念网络的图像识别方法[J]. 西安电子科技大学学报, 2018,45(5):102-107.
	MA Miao, XU Xidan, WU Jie . Coupled-deep Belief NetworkBased Method for Image Recognition[J]. Journal of Xidian University, 2018,45(5):102-107.
[6]	许强, 李伟, 占荣辉 , 等. 一种改进的卷积神经网络SAR目标识别算法[J]. 西安电子科技大学学报, 2018,45(5):177-183.
	XU Qiang, LI Wei, ZHAN Ronghui , et al. Improved Algorithm for SAR Target RecognitionBased on the Convolutional Neural Network[J]. Journal of Xidian University, 2018,45(5):177-183.
[7]	ZHANG L, YANG F, ZHANG Y. et al. Road Crack Detection Using Deep Convolutional Neural Network [C]//Proceedings of the 2016 IEEE International Conference on Image Processing. Washington: IEEE Computer Society, 2016: 3708-3712.
[8]	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.
[9]	RONNERBERGER O, FISCHER P, BROX T. U-Net: Convolutional Networks for Biomedical Image Segmentation [C]//Lecture Notes in Computer Science: 9351. Heidelberg: Springer Verlag, 2015: 234-241.
[10]	LIU Z, SONG Y Q, SHENG V S , et al. Liver CT Sequence Segmentation Based with Improved U-Net and Graph Cut[J]. Expert Systems with Applications, 2019,126:54-63.
[11]	LIAN S, LUO Z, ZHONG Z , et al. Attention Guided U-Net for Accurate Iris Segmentation[J]. Journal of Visual Communication and Image Representation, 2018,56:296-304.
[12]	FENG W, SUI H, HUANG W , et al. Water Body Extraction From Very High-resolution Remote Sensing Imagery Using Deep U-Net and a Superpixel-based Conditional Random Field Model[J]. IEEE Geoscience and Remote Sensing Letters, 2019,16(4):618-622.
[13]	ZHANG Z, LIU Q, WANG Y . Road Extraction by Deep Residual U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2018,15(5):749-753.
[14]	任亮, 徐志刚, 赵祥模 , 等. 基于Prim最小生成树的路面裂缝连接算法[J]. 计算机工程, 2015,41(1):31-36. doi: 10.3969/j.issn.1000-3428.2015.01.006
	REN Liang, XU Zhigang, ZHAO Xiangmo , et al. Pavement Crack Connection Algorithm Based on Prim Minimum Spanning Tree[J]. Computer Engineering, 2015,41(1):31-36. doi: 10.3969/j.issn.1000-3428.2015.01.006
[15]	BATAINEH B . An Iterative Thinning Algorithm for Binary Images Based on Sequential and Parallel Approaches[J]. Pattern Recognition and Image Analysis, 2018,28(1):34-43.

算法	样本总数	无裂缝	完全检测	部分检测	漏检	误检	准确率/%	漏检率/%	误检率/%
张量投票	384	133	120	35	88	8	65.9	22.9	2.10
笔者提出	384	133	218	22	9	2	91.4	2.3	0.52

数据组	比例尺/ (毫米·像素^-1)	实际测量宽度/mm	平均像素距离/像素	检测裂缝宽度/mm	误差/ mm
1	0.088 7	0.35	4.25	0.377	0.027
2	0.089 9	0.40	4.67	0.420	0.020
3	0.093 0	0.45	5.00	0.465	0.015
4	0.088 3	0.50	5.29	0.467	0.033
5	0.090 0	0.55	6.26	0.563	0.013