广东工业大学学报 ›› 2022, Vol. 39 ›› Issue (06): 73-79.doi: 10.12052/gdutxb.210038

• 综合研究 • 上一篇    下一篇

高分辨率桥梁裂缝图像实时检测

刘信宏, 苏成悦, 陈静, 徐胜, 罗文骏, 李艺洪, 刘拔   

  1. 广东工业大学 物理与光电工程学院, 广东 广州 510006
  • 收稿日期:2021-03-10 出版日期:2022-11-10 发布日期:2022-11-25
  • 通信作者: 苏成悦(1961-),男,教授,博士,主要研究方向为应用物理、图像识别,E-mail:cysu@gdut.edu.cn
  • 作者简介:刘信宏(1995-),男,硕士研究生,主要研究方向为图像处理、模式识别,E-mail:liuxinhong@mail2.gdut.edu.cn
  • 基金资助:
    广东省科技计划项目(2017A020208063);广州市科技计划项目(201804010384)

Real Time Detection of High Resolution Bridge Crack Image

Liu Xin-hong, Su Cheng-yue, Chen Jing, Xu Sheng, Luo Wen-jun, Li Yi-hong, Liu Ba   

  1. School of Physics and Optoelectronic Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2021-03-10 Online:2022-11-10 Published:2022-11-25

摘要: 针对现有桥梁裂缝检测算法实时性弱、可靠性差等问题,提出一种嵌入式平台上的实时检测算法。使用移动平均法粗分割,依据几何特征和区域生长法再分割,定位候选裂缝片段;基于裂缝先验条件,建立双判别准则的裂缝聚合模型,递归合并裂缝片段并抑制干扰。实验表明,算法能有效提取细小裂缝,抑制不均匀光照和污渍等复杂背景干扰,识别性能与数种现有算法相比提高115%以上;在嵌入式开发板上处理1500万像素的图像仅耗时1.73 s。

关键词: 图像处理, 桥梁裂缝, 高分辨率, 实时检测, 嵌入式平台

Abstract: The problem of current algorithms is lack of timeliness and reliability in bridge crack detection. In this paper, a real-time algorithm on embedded platform is proposed. Firstly, moving average method is used to segment the image coarsely. Then, candidate crack fragments are selected by region growing method using the geometric features of their contours. Finally, a crack merging model with two criteria is built to merge the crack fragments recursively and suppress interference, based on the prior condition of bridge cracks. Experimental results show that the proposed method performs better than several existing methods by 115% at least, especially on extracting hairline cracks and complex cases with uneven illumination and dirty mark. Dealing with an image with 15 megapixel on embedded platform, it costs only 1.73 s.

Key words: image processing, bridge crack, high resolution, real-time detection, embedded platform

中图分类号: 

  • TP391
[1] 张国旗. 基于图像处理的混凝土桥梁底面裂缝检测方法的研究[D]. 北京: 北京交通大学, 2010.
[2] 王德方, 曾卫明, 王倪传. 基于改进K-means算法的不均匀光照下道路裂缝检测[J]. 计算机应用与软件, 2015, 32(7): 244-247.
WANG D F, ZENG W M, WANG N C. Road crack detection under uneven illumination using improved k-means algorithm [J]. Computer Application and Software, 2015, 32(7): 244-247.
[3] 张德津, 李清泉, 陈颖, 等. 基于空间聚集特征的沥青路面裂缝检测方法[J]. 自动化学报, 2016, 42(3): 443-454.
ZHANG D J, LI Q Q, CHEN Y, et al. Asphalt pavement crack detection based on spatial clustering feature [J]. Acta Automatic Sinica, 2016, 42(3): 443-454.
[4] 王耀东, 朱力强, 史红梅, 等. 基于局部图像纹理计算的隧道裂缝视觉检测技术[J]. 铁道学报, 2018, 40(2): 82-90.
WANG Y D, ZHU L Q, SHI H M, et al. Vision detection of tunnel cracks based on local image texture calculation [J]. Journal of the China Railway Society, 2018, 40(2): 82-90.
[5] 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.
[6] ZOU Q, CAO Y, LI Q, et al. CrackTree: automatic crack detection from pavement images [J]. Pattern Recognition Letters, 2012, 33(3): 227-238.
[7] 贺福强, 平安, 罗红, 等. 局部特征聚类联合区域增长的桥梁裂缝检测[J]. 科学技术与工程, 2019, 19(34): 272-277.
HE F Q, PING A, LUO H, et al. Bridge crack detection based on local feature clustering combined with regional growth [J]. Science Technology and Engineering, 2019, 19(34): 272-277.
[8] 周飘, 李强, 曾曙光, 等. 基于多尺度Hessian矩阵滤波的陶瓷瓦表面裂纹检测方法[J]. 激光与光电子学进展, 2020, 57(10): 222-228.
ZHOU P, LI Q, ZENG S G, et al. Surface crack detection method for ceramic tile based on hessian matrix multi-scale filtering [J]. Laser & Optoelectronics Progress, 2020, 57(10): 222-228.
[9] CHEN H, ZHAO H, HAN D, et al. Accurate and robust crack detection using steerable evidence filtering in electroluminescence images of solar cells [J]. Optics and Lasers in Engineering, 2019, 118: 22-33.
[10] TIAN Q, LUO Q, GE B, et al. A methodology framework for retrieval of concrete surface crack's image properties based on hybrid model [J]. Optik, 2019, 180: 199-214.
[11] LIU Z, CAO Y, WANG Y, et al. Computer vision-based concrete crack detection using U-net fully convolutional networks [J]. Automation in Construction, 2019, 104: 129-139.
[12] CHEN F C, JAHANSHAHI M R. NB-FCN: real-time accurate crack detection in inspection videos using deep fully convolutional network and parametric data fusion [J]. IEEE Transactions on Instrumentation and Measurement, 2019, 69(8): 5325-5334.
[13] ZHANG L, YANG F, ZHANG Y D, et al. Road crack detection using deep convolutional neural network[C]//2016 IEEE international conference on image processing (ICIP) . Phoenix: IEEE, 2016: 3708-3712.
[14] CHAIYASARN K, SHARMA M, ALI L, et al. Crack detection in historical structures based on Convolutional Neural Network [J]. International Journal of GEOMATE, 2018, 15(51): 240-251.
[15] KIM B, YUVARAJ N, PREETHAA K R S, et al. Surface crack detection using deep learning with shallow CNN architecture for enhanced computation [J]. Neural Computing and Applications, 2021, 33(15): 9289-9305.
[16] SHI W, ZOU R, WANG F, et al. A new image segmentation method based on multifractal detrended moving average analysis [J]. Physica A:Statistical Mechanics and its Applications, 2015, 432: 197-205.
[17] 赵玲玲, 汪烨, 刘俊. 基于无人机与HSV空间的光伏电池板检测分析[J]. 红外技术, 2020, 42(10): 978-982.
ZHAO L L, WANG Y, LIU J. Detection and analysis of photovoltaic panels based on UAV and HSV space [J]. Infrared Technology, 2020, 42(10): 978-982.
[18] 揭云飞, 王峰, 钟有东, 等. 基于地面特征的单目视觉机器人室内定位方法[J]. 广东工业大学学报, 2020, 37(5): 31-37.
JIE Y F, EVERETT W, ZHONG Y D, et al. An indoor positioning method of monocular vision robot based on floor features [J]. Journal of Guangdong University of Technology, 2020, 37(5): 31-37.
[19] 姒绍辉, 胡伏原, 顾亚军, 等. 一种基于不规则区域的高斯滤波去噪算法[J]. 计算机科学, 2014, 41(11): 313-316.
SI S H, HU F Y, Gu Y J, et al. Improved denoising algorithm based on non-regular area gaussian filtering [J]. Computer Science, 2014, 41(11): 313-316.
[20] SKLANSKY J. Finding the convex hull of a simple polygon [J]. Pattern Recognition Letters, 1982, 1(2): 79-83.
[21] TOUSSAINT G. Solving geometric problems with the rotating calipers[C]//Proceedings of the IEEE Melecon. Athens: IEEE, 1983.
[1] 邹恒, 高军礼, 张树文, 宋海涛. 围棋机器人落子指引装置的设计与实现[J]. 广东工业大学学报, 2023, 40(01): 77-82,91.
[2] 丘展春, 费伦科, 滕少华, 张巍. 余弦相似度保持的掌纹识别算法[J]. 广东工业大学学报, 2022, 39(03): 55-62.
[3] 杨运龙, 梁路, 滕少华. 一种双路网络语义分割模型[J]. 广东工业大学学报, 2022, 39(01): 63-70.
[4] 揭云飞, 王峰, 钟有东, 智凯旋, 熊超伟. 基于地面特征的单目视觉机器人室内定位方法[J]. 广东工业大学学报, 2020, 37(05): 31-37.
[5] 钟映春, 吕帅, 罗鹏, 简裕涛, 褚千琨. 烤瓷牙内部缺陷的图像检测及其特征统计分析[J]. 广东工业大学学报, 2018, 35(01): 1-5.
[6] 邹庆胜, 汪仁煌, 明俊峰. 基于机器视觉的瓷砖多参数分类系统的设计[J]. 广东工业大学学报, 2010, 27(4): 46-49.
[7] 袁西霞; 岳建华; 赵贤任; . MATLAB在中值滤波改进算法中的应用[J]. 广东工业大学学报, 2007, 24(1): 33-35.
[8] 薛岚燕; 郑胜林; 潘保昌; 陈箫枫; . 基于神经网络的灰度图像阈值分割方法[J]. 广东工业大学学报, 2005, 22(4): 67-72.
[9] 苏成悦; 郑光昭; . 利用光折变晶体实现多灰度级图像的区域分割[J]. 广东工业大学学报, 2000, 17(4): 89-92.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!