|本期目录/Table of Contents|

[1]陈 娟,张彦铎*,卢 涛.基于像素差分卷积神经网络的类岩石裂缝检测方法[J].武汉工程大学学报,2023,45(01):81-86.[doi:10.19843/j.cnki.CN42-1779/TQ. 202209019]
 CHEN Juan,ZHANG Yanduo*,LU Tao.Rock-Like Crack Detection via Pixel Differential ConvolutionNeural Network[J].Journal of Wuhan Institute of Technology,2023,45(01):81-86.[doi:10.19843/j.cnki.CN42-1779/TQ. 202209019]
点击复制

基于像素差分卷积神经网络的类岩石裂缝检测方法(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
45
期数:
2023年01期
页码:
81-86
栏目:
机电与信息工程
出版日期:
2023-02-28

文章信息/Info

Title:
Rock-Like Crack Detection via Pixel Differential Convolution
Neural Network
文章编号:
1674 - 2869(2023)01 - 0081 - 06
作者:
陈 娟12张彦铎*12卢 涛12
1. 智能机器人湖北省重点实验室(武汉工程大学),湖北 武汉 430205;
2. 武汉工程大学计算机科学与工程学院,湖北 武汉 430205
Author(s):
CHEN Juan12ZHANG Yanduo*12LU Tao12
1. Hubei Key Laboratory of Intelligent Robot(Wuhan Institute of Technology),Wuhan 430205,China;
2. School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205,China
关键词:
类岩石裂缝检测像素差分梯度信息
Keywords:
rock-like crack detection pixel difference gradient information
分类号:
TP391
DOI:
10.19843/j.cnki.CN42-1779/TQ. 202209019
文献标志码:
A
摘要:
针对现有裂缝检测算法提取的局部梯度信息不足而导致裂缝识别精度低的问题,提出了一种基于像素差分的编码器-解码器U型结构的裂缝检测方法。使用由像素差分卷积块和残差块组成的PDCBlock作为网络的编码器,将两种不同方向上的像素邻域的差分值计算融合到卷积网络运算中,以充分获取裂缝语义信息的同时更好地捕获局部梯度信息,使得在背景复杂的情景下裂缝边缘识别更准确。在混凝土类岩石裂缝数据集CRACK500上对比了同类方法,实验结果表明:该方法在上述数据集上的平均交并比和Dsc分别为0.436 3、0.580 4,裂缝分割精度、相似性上均优于对比方法。

Abstract:
Existing crack detection algorithms suffer from low crack recognition accuracy due to insufficient local gradient information. To address the problem, this paper proposes a crack detection method (pixel different U-Net,PDU-Net) based on pixel difference encoder-decoder U-shaped structure. Specifically, we adopted PDCBlock as the encoder of proposed method, which is composed of residual blocks and pixel difference convolution blocks. Then the difference values of pixel neighborhoods in two different directions can be computationally fused into the convolutional network operations. With the help of PDCBlock, our proposed network enables the semantic information of crack to be fully accessible and also better captures the local gradient information, which makes the crack edge recognition more accurate under complex background.Similar methods were compared on the concrete-similar rock crack dataset CRACK500.Extensive experiments demonstrate that the proposed method obtains a mean intersection over union of 0.436 3 and an average Dice similarity coefficient of 0.580 4, and outperforms existing state-of-the-art methods in terms of crack segmentation accuracy and similarity on the above data sets.

参考文献/References:

[1] KIM H, AHN E, SHIN M, et al. Crack and noncrack classification from concrete surface images using machine learning[J]. Structural Health Monitoring, 2019, 18(3):725-738.

[2] SPENCER B F, HOSKERE V, NARAZAKI Y. Advances in computer vision-based civil infrastructure inspection and monitoring[J]. Engineering, 2019, 5(2):199-222.
[3] BROERE W. Urban underground space: solving the problems of today’s cities[J]. Tunnelling and Underground Space Technology, 2016, 55: 245-248.
[4] DUNG C V, ANH L D. Autonomous concrete crack detection using deep fully convolutional neural network[J]. Automation in Construction, 2019, 99:52-58.
[5] WANG F K. Edge detection of inner crack defects based on improved sobel operator and clustering algorithm[J]. Applied Mechanics and Materials, 2011, 55/56/57:467-471.
[6] SUN L, XING J, XIE L, et al. An adaptive threshold based canny algorithm for crack detection[J]. Microcomputer & Its Applications,2017,36(5):35-37.
[7] WANG W J, ZHANG A, WANG K C P, et al. Pavement crack width measurement based on laplace’s equation for continuity and unambiguity[J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(2): 110-123.
[8] YANG F, ZHANG L, YU S J, et al. Feature pyramid and hierarchical boosting network for pavement crack detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(4):1525-1535.
[9] XIE S N, TU Z W. Holistically-nested edge detection[C]//Proceedings of the IEEE international conference on computer vision. Santiago:IEEE,2015:1395-1403.
[10] SCHMUGGE S J, RICE L, LINDBERG J, et al. Crack segmentation by leveraging multiple frames of varying illumination[C]//2017 IEEE Winter Conference on Applications of Computer Vision (WACV). Santa Rosa : IEEE, 2017: 1045-1053.
[11] 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.
[12] CHENG J R, XIONG W, CHEN W Y, et al. Pixel-level crack detection using U-Net[C]//TENCON 2018-2018 IEEE Region 10 Conference. Jeju: IEEE, 2018: 462-466.
[13] WU Z H, LU T, ZHANG Y D, et al. Crack detecting by recursive attention U-Net[C]//2020 3rd International Conference on Robotics, Control and Automation Engineering (RCAE). Chongqing: IEEE, 2020: 103-107.
[14] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention. Cham: Springer, 2015: 234-241.
[15] HU Y, ZHAO C X. A novel LBP nased methods for pavement crack detection[J]. Journal of Pattern Recognition Research, 2010,5(1): 140-147.
[16] 郭香蓉,李鸿.一种基于集成学习的路面裂缝检测仿真算法[J].计算机仿真,2022,39(2):121-125.
[17] OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention U-Net: learning where to look for the pancreas. arXiv[J]. arXiv preprint arXiv:2018,1804.03999.
[18] SU Z, LIU W Z, YU Z T, et al. Pixel difference networks for efficient edge detection[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal: IEEE, 2021: 5097-5107.
[19] YU Z T, ZHAO C Y, WANG Z Z, et al. Searching central difference convolutional networks for face anti-spoofing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 5295-5305.
[20] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 3431-3440.
[21] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[22] 瞿中,陈雯.基于空洞卷积和多特征融合的混凝土路面裂缝检测[J]. 计算机科学,2022,49(3):192-196.

相似文献/References:

[1]闫晖,鲁统伟.图论在路面裂缝分割中的应用研究[J].武汉工程大学学报,2012,(1):53.
 YAN Hui,LU Tong wei.Method for segmentation of pavement crack based on graph theory[J].Journal of Wuhan Institute of Technology,2012,(01):53.

备注/Memo

备注/Memo:
收稿日期:2022-09-17
基金项目:国家自然科学基金面上项目(52174085)
作者简介:陈 娟,硕士研究生。E-mail:176028224@qq.com
*通讯作者:张彦铎,博士,教授。E-mail:zhangyanduo@hotmail.com
引文格式:陈娟,张彦铎,卢涛. 基于像素差分卷积神经网络的类岩石裂缝检测[J]. 武汉工程大学学报,2023,45(1):81-86,100.

更新日期/Last Update: 2023-03-14