基于改进DeepLabv3+模型的桥梁裂缝图像分割方法

doi:10.13229/j.cnki.jdxbgxb.20220205

摘要/Abstract

摘要：

针对桥梁中的裂缝病害智能化检测，深度学习方法中DeepLabv3+分割模型因其提出了新的Encoder-Decoder结构，其融合了目标的高层语义信息与浅层特征并采用了深度分离卷积的方式，取得了优越的图像分割效果。但是，在编码模块训练过程中逐渐缩减输入数据的空间维度导致有用信息丢失，对尺度大小不一的小目标的识别带来一定的局限性。为了提高网络的分割性能，本文提出了一种基于改进DeepLabv3+的图像分割方法。通过增加的YOLOF模块与Resnet模块，进一步扩大感受野同时获取到更精确的裂缝特征图，为了验证本文改进算法的有效性，将大量实际桥梁裂缝图像作为原始数据集，将其与当前具有代表性的图像分割模型（如Mask R-CNN、DeepLabv3+）在相同数据集上进行对比。结果表明，本文算法在裂缝像素精度上相比Mask R-CNN、DeepLabv3+分别提高了12%与8%，平均像素精确度达到91.99%，平均交并比达到了81.43%，更加适用于桥梁裂缝分割任务，具有工程实际应用意义。

关键词: 桥梁工程, 桥梁裂缝检测, DeepLabv3+, 像素精度, 图像分割

Abstract:

Crack disease is the most common disease of bridges， DeepLabv3+ segmentation model puts forward a new Encoder-Decoder structure among deep learning methods. It combines the high-level semantic information and shallow features of the target， and adopts the method of deep separation and convolution， which achieves superior image segmentation effect. However， in the training process of the coding module， the spatial dimension of the input data is gradually reduced， resulting in the loss of useful information， which brings some limitations to the recognition of small targets with different scales. In order to improve the segmentation performance of the network， this paper proposes an image segmentation method based on improved DeepLabv3+.By adding Yolof module and Resnet module， the receptive field is further expanded and more accurate crack feature map is obtained at the same time. In order to verify the effectiveness of the improved algorithm， a large number of actual bridge crack images are taken as the original data set， which is compared with the current representative image segmentation models such as Mask R-CNN and DeepLabv3+ on the same dataset. The results show that the algorithm in this paper improves the accuracy of crack pixels by 12% and 8% respectively compared with Mask R-CNN and DeepLabv3+. The average pixel accuracy is 91.99%， and Mean Intersection over Union is 81.43%， which is more suitable for the task of bridge crack segmentation and has practical engineering application significance.

Key words: bridge engineering, bridge crack detection, DeepLabv3+, pixel accuracy, image segmentation

中图分类号:

U446

谭国金,欧吉,艾永明,杨润超. 基于改进DeepLabv3+模型的桥梁裂缝图像分割方法[J]. 吉林大学学报(工学版), 2024, 54(1): 173-179.

Guo-jin TAN,Ji OU,Yong-ming AI,Run-chao YANG. Bridge crack image segmentation method based on improved DeepLabv3+ model[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(1): 173-179.

图/表 9

图1

图2

图3

图4

图5

表1

表2

图6

图7

参考文献 22

1	楼伟. 高等级公路路面病害识别与检测中的算法研究[D]. 西安:西安工业大学光电工程学院, 2001.
	Lou Wei. Algodthm research on indentifies and detection the disease of highway surface[D]. Xi'an: School of Optoelectronic Engineering, Xi'an Polytechnic University, 2001.
2	王卫星, 吴林春. 基于分数阶积分谷底边界检测的路面裂缝提取[J]. 华南理工大学学报:自然科学版, 2014, 42(1): 117-122.
	Wang Wei-xing, Wu Lin-chun. Extraction of pavement cracks based on valley edge detection of fractional integral[J]. Journal of South China University of Technology(Natural Science Edition), 2014, 42(1): 117-122.
3	Zhao H L, Qin G F, Wang X J. Improvement of canny algorithm based on pavement edge detection[C]∥The 3rd International Congress on Image and Signal Processing, Yantai, China, 2010: 964-967.
4	Lim R S, La H M, Shan Z Y, et al. Developing a crack inspection robot for bridge maintenance [C]∥IEEE International Conference on Robotics and Automation, Shanghai, China, 2011: 6288-6293.
5	Tsai Y C, Kaul V, Mersereau R M. Critical assessment of pavement distress segmentation methods[J]. Journal of Transportation Engineering, 2010, 136(1): 11-19.
6	Zhang D J, Li Q Q, Chen Y, et al. An efficient and reliable coarse-to-fine approach for asphalt pavement crack detection[J]. Image and Vision Computing, 2017, 57: 130-146.
7	Cha Y J, Choi W, Buyukozturk O. Deep learning-based crack damage detection using convolutional neural networks[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361-378.
8	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 Liang-fu, Ma Wei-fei, Li Li, et al. Research on detection algorithm for bridge cracks based on deep learning[J]. Acta Automatica Sinica, 2019, 45(9): 1727-1742.
9	蔡逢煌,张岳鑫,黄捷. 基于YOLOv3与注意力机制的桥梁表面裂痕检测算法[J]. 模式识别与人工智能, 2020, 33(10): 926-933.
	Cai Feng-huang, Zhang Yue-xin, Huang Jie. Bridge surface crack detection algorithm based on YOLOv3 and attention mechanism[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(10): 926-933.
10	Jenkins M D, Carr T A, Iglesias M I, et al. A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks[C]∥The 26th European Signal Processing Conference, Rome, Italy, 2018: 2120-2124.
11	朱苏雅, 杜建超, 李云松, 等. 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 Su-ya, Du Jian-chao, Li Yun-song, et al. Method for bridge crack detection based on the U-Net convolutional networks[J]. Journal of Xidian University, 2019, 46(4): 35-42.
12	刘承飞. 基于双卷积神经网络的桥梁裂纹实时检测技术研究[D]. 哈尔滨: 哈尔滨工业大学机电工程学院, 2020.
	Liu Cheng-fei. Based on the double convolutional neural network research on real-time crack detection technology of bridge[D]. Harbin: School of Mechatronics Engineering, Harbin Institute of Technology, 2020.
13	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90.
14	Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston,USA,2015: 1-9.
15	Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, USA,2016: 2818-2826.
16	Girshick R. Fast R-CNN[C]∥Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440-1448.
17	Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
18	He K M, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386-397.
19	He K M, Gkioxari G, Dollar P, et al. Mask R-CNN[C]∥IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2980-2988.
20	Chen L C, Zhu Y K, Papandreou G, et al. Encoder-Decoder with atrous separable convolution for semantic image segmentation[C]∥European Conference Computer Vision, Munich, Germany, 2018: 833-851.
21	Chollet F. Xception: Deep learning with depthwise separable convolutions[C]∥The 30th IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, USA, 2017: 1800-1807.
22	苏可. 基于目标检测与语义分割的道路损伤识别方法[D]. 太原: 太原理工大学电气与动力工程学院, 2021.
	Su Ke. Road damage recognition method based on target detection and semantic segmentation[D]. Taiyuan: School of Electrical and Power Engineering, Taiyuan University of Technology, 2021.

相关文章 15

[1]	安然,王有志. 剪力钉连接件拉剪共同作用抗剪性能[J]. 吉林大学学报(工学版), 2023, 53(9): 2554-2562.
[2]	左新黛,张劲泉,赵尚传. 在役混凝土T梁疲劳刚度退化及寿命预测方法[J]. 吉林大学学报(工学版), 2023, 53(9): 2563-2572.
[3]	吴春利,黄诗茗,李魁,顾正伟,黄晓明,张炳涛,杨润超. 基于数值仿真和统计分析的洪水作用下桥墩作用效应分析[J]. 吉林大学学报(工学版), 2023, 53(6): 1612-1620.
[4]	顾正伟,张攀,吕东冶,吴春利,杨忠,谭国金,黄晓明. 基于数值仿真的简支梁桥震致残余位移分析[J]. 吉林大学学报(工学版), 2023, 53(6): 1711-1718.
[5]	谭国金,孔庆雯,何昕,张攀,杨润超,朝阳军,杨忠. 基于动力特性和改进粒子群优化算法的桥梁冲刷深度识别[J]. 吉林大学学报(工学版), 2023, 53(6): 1592-1600.
[6]	江辉,李新,白晓宇. 桥梁抗震结构体系发展述评：从延性到韧性[J]. 吉林大学学报(工学版), 2023, 53(6): 1550-1565.
[7]	王俊,李加武,王峰,张久鹏,黄晓明. 简化U形峡谷风速分布及其对悬索桥抖振响应的影响[J]. 吉林大学学报(工学版), 2023, 53(6): 1658-1668.
[8]	王峰,刘双瑞,王佳盈,宋佳玲,王俊,张久鹏,黄晓明. 尺寸和形状效应对多孔结构风阻系数的影响[J]. 吉林大学学报(工学版), 2023, 53(6): 1677-1685.
[9]	王华,王龙林,张子墨,何昕. 基于裂缝宽度变化的连续刚构桥安全性预警技术[J]. 吉林大学学报(工学版), 2023, 53(6): 1650-1657.
[10]	冯宇,郝键铭,王峰,张久鹏,黄晓明. 非平稳极端风作用下大跨桥梁瞬态风致效应分析[J]. 吉林大学学报(工学版), 2023, 53(6): 1638-1649.
[11]	袁野. 温度和车辆作用下梁式桥梁结构固有频率分析方法[J]. 吉林大学学报(工学版), 2023, 53(6): 1702-1710.
[12]	刘子玉,陈士通,支墨墨,黄晓明,陈哲心. 可“临-永”转换抢修钢墩应急使用极限承载力[J]. 吉林大学学报(工学版), 2023, 53(6): 1601-1611.
[13]	张玥,刘传森,宋飞. 桥台背墙对连续梁桥地震易损性的影响[J]. 吉林大学学报(工学版), 2023, 53(5): 1372-1380.
[14]	兰树伟,周东华,陈旭,莫南明. 双柱式高墩桥梁整体稳定性的实用算法[J]. 吉林大学学报(工学版), 2023, 53(4): 1105-1111.
[15]	孙琪凯,张楠,刘潇,周子骥. 基于Timoshenko梁理论的钢-混组合梁动力折减系数[J]. 吉林大学学报(工学版), 2023, 53(2): 488-495.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

实验环境	配置说明
硬件环境	CPU：Intel（R） Xeon（R） W-2245 CPU @3.90 GHz
	GPU：NVIDIA Quadro P4000
	内存：64 GB
软件环境	操作系统：Windows10专业版
开发环境	Pycharm集成开发环境
算法编程环境	Pytorch深度学习框架