Coal rock crack recognition method based on connectivity threshold segmentation
-
摘要: 煤岩裂隙发育形态是影响煤岩渗透性、决定煤岩体力学特征的重要因素。针对煤岩裂隙识别过程中存在的复杂结构处理不当、裂隙边界特征保留不足、噪声干扰等问题，提出了一种基于连通性阈值分割的煤岩裂隙识别方法。首先，采用直方图均衡化增强算法和非局部均值滤波去噪算法对图像进行预处理， 其次，利用自适应Otsu阈值分割确定预处理后图像的阈值，识别出可能的裂隙区域，应用形态学运算对这些区域进行精细化处理，进一步突出裂隙的边界特征。然后，通过Canny边缘计算提取种子点，以识别图像中的关键特征。最后，基于这些种子点进行区域生长操作，从而有效抑制噪声，并在平滑图像裂隙的同时更加清晰地突出裂隙信息。实验结果表明：① 连通性阈值分割的均方误差较自适应Otsu阈值分割和自适应阈值分割分别平均减少了7.20，7.10 dB，连通性阈值分割的峰值信噪比较自适应Otsu阈值分割和自适应阈值分割分别平均提高了0.60，0.59 dB。② 连通性阈值分割不仅有效解决了裂隙提取不明显、末端提取效果差及连接处特征消失的问题，而且显著减少了噪声的干扰，使裂隙特征变得更加突出，从而极大地提高了裂隙识别的准确性和完整性。③ 连通性阈值分割在自适应Otsu阈值分割的基础上，强化了裂隙特征并有效消除了噪声点，平均准确率较自适应阈值分割算法和自适应Otsu阈值分割分别提高了8%和0.8%，达98.9%。Abstract: The development morphology of coal rock cracks is an important factor affecting the permeability of coal rock and determining the mechanical features of coal rock mass. A coal rock crack recognition method based on connectivity threshold segmentation is proposed to address issues such as improper handling of complex structures, insufficient preservation of crack boundary features, and noise interference in the process of recognizing coal rock cracks. Firstly, histogram equalization enhancement algorithm and non local mean filtering denoising algorithm are used to preprocess the image. Secondly, adaptive Otsu threshold segmentation is used to determine the threshold of the preprocessed image, recognize possible crack areas, and apply morphological operations to refine these areas, further highlighting the boundary features of cracks. Thirdly, seed points are extracted by Canny edge computing to recognize key features in the image. Finally, based on these seed points, regional growth operations are performed to effectively suppress noise and highlight crack information more clearly while smoothing image cracks. The experimental results show the following points. ① The mean square error of connectivity threshold segmentation is reduced by an average of 7.20 and 7.10 dB compared to adaptive Otsu threshold segmentation and adaptive threshold segmentation, respectively. The peak signal-to-noise ratio of connectivity threshold segmentation is improved by an average of 0.60 and 0.59 dB compared to adaptive Otsu threshold segmentation and adaptive threshold segmentation, respectively. ② Connectivity threshold segmentation not only effectively solves the problems of unclear crack extraction, poor end extraction performance, and disappearance of connection features, but also significantly reduces the interference of noise, making crack features more prominent, thereby greatly improving the accuracy and completeness of crack recognition. ③ On the basis of adaptive Otsu threshold segmentation, connectivity threshold segmentation enhances crack features and effectively eliminates noise points. The average accuracy is improved by 8% and 0.8% respectively compared to adaptive threshold segmentation algorithm and adaptive Otsu threshold segmentation, reaching 98.9%.
-
图 2 工业CT扫描实验装置及原理
Figure 2. Experimental device and principle of industrial CT scanning
图 8 开运算叠加底帽运算效果
Figure 8. The effect of the open operation superimposed on the effect of the bottom hat transformation
图 13 各阈值分割算法的降噪效果和失真情况对比
Figure 13. Comparison of the noise reduction effect and distortion of each threshold segmentation algorithms
图 14 本文算法与自适应 Otsu 阈值分割及自适应阈值分割对比
Figure 14. Comparison of the algorithm in this paper with adaptive Otsu threshold segmentation and adaptive threshold segmentation.
表 1 3种算法的准确率统计
Table 1. Accuracy statistics of the three algorithms
% 算法 准确率 第1组 第2组 第3组 自适应阈值分割 0.939 0.943 0.849 自适应Otsu阈值分割 0.983 0.981 0.981 连通性阈值分割 0.990 0.986 0.991 
下载: 导出CSV
-
[1] 张青成,王万富,左建民,等. 煤岩CT图像二值化阀值选取及三维重构技术研究[J]. CT理论与应用研究,2014,23(1):45-51.ZHANG Qingcheng,WANG Wanfu,ZUO Jianmin,et al. CT image binarization threshold selection of coal and 3D reconstruction technology research[J]. Computerized Tomography Theory and Applications,2014,23(1):45-51. [2] 郝晨光,郭晓阳,邓存宝,等. 基于Bi−PTI模型的CT数字煤岩孔裂隙精准识别及阈值反演[J]. 煤炭学报,2023,48(4):1516-1526.HAO Chenguang,GUO Xiaoyang,DENG Cunbao,et al. Precise identification and threshold inversion of poresand fissures in CT digital coal rock based on Bi-PTI model[J]. Journal of China Coal Society,2023,48(4):1516-1526. [3] LOU Quan,JIA Bing,WAN Xiangyun,et al. Discrete characteristics of instantaneous frequency of EMR induced by coal and rock fracture[J]. Measurement Science and Technology,2023,34(12). DOI: 10.1088/1361-6501/ACED5C. [4] 宫伟力,李晨. 煤岩结构多尺度各向异性特征的SEM图像分析[J]. 岩石力学与工程学报,2010,29(增刊1):2681-2689.GONG Weili,LI Chen. Multi-scale and anisotropic characterization of coal structure based on SEM imageanalysis[J]. Chinese Journal of Rock Mechanics and Engineering,2010,29(S1):2681-2689. [5] XU Duo,ZHAO Yixin,JIANG Yaodong,et al. Using improved edge detection method to detect mining- induced ground fissures identified by unmanned aerial vehicle remote sensing[J]. Remote Sensing,2021,13(18). DOI: 10.3390/rs13183652. [6] 毛义坪,马茂源. 基于高斯拉普拉斯算子的多聚焦图像融合[J]. 计算机应用与软件,2019,36(10):216-221.MAO Yiping,MA Maoyuan. Multifocal image fusion based on goslav procedure operator[J]. Computer Applications and Software,2019,36(10):216-221. [7] LIU Chunsheng,REN Chunping. Research on coal-rock fracture image edge detection based on Tikhonov regularization and fractional order differential operator[J]. Journal of Electrical and Computer Engineering,2019,2019(1). DOI: 10.1155/2019/9594301. [8] 苏钰桐,杨炜毅,李俊霖. 基于YOLOv3的煤岩钻孔图像裂隙智能识别方法[J]. 煤矿安全,2021,52(4):156-161.SU Yutong,YANG Weiyi,LI Junlin. Intelligent recognition method of borehole image fractures for coal and rock based on YOLOv3[J]. Safety in Coal Mines,2021,52(4):156-161. [9] 郝天轩,徐新革,赵立桢. 煤岩裂隙图像识别方法研究[J]. 工矿自动化,2023,49(10):68-74.HAO Tianxuan,XU Xinge,ZHAO Lizhen. Research on image recognition methods for coal rock fractures[J]. Journal of Mine Automation,2023,49(10):68-74. [10] 王登科,房禹,魏建平,等. 基于深度学习的煤岩Micro−CT裂隙智能提取与应用[J/OL]. 煤炭学报:1-15[2024-04-23]. https://doi.org/10.13225/j.cnki.jccs.2023.0992.WANG Dengke,FANG Yu,WEI Jianping,et al. Intelligent extraction of Micro-CT fissures in coal based on deep learning and its application[J/OL]. Journal of China Coal Society:1-15[2024-04-23]. https://doi.org/10.13225/j.cnki.jccs.2023.0992. [11] LU Fengli,FU Chengcai,SHI Jie,et al. Attention based deep neural network for micro-fracture extraction of sequential coal rock CT images[J]. Multimedia Tools and Applications,2022,81(18):26463-26482. doi: 10.1007/s11042-022-12033-9 [12] 冯雪健,沈永星,周动,等. 基于CT数字岩心深度学习的煤裂隙分布识别研究[J]. 煤炭科学技术,2023,51(8):97-104.FENG Xuejian,SHEN Yongxing,ZHOU Dong,et al. Multi-scale distribution of coal fractures based on CT digital core deep learning[J]. Coal Science and Technology,2023,51(8):97-104. [13] 汪海洋,潘德炉,夏德深. 二维Otsu自适应阈值选取算法的快速实现[J]. 自动化学报,2007(9):968-971.WANG Haiyang,PAN Delu,XIA Deshen. A fast algorithm for two-dimensional Otsu adaptive threshold algorithm[J]. Acta Automatica Sinica,2007(9):968-971. [14] BAI Lijuan,DU Yirou,LONG Chao. CT image reconstruction via industrial CT fast scanning[J]. Journal of Instrumentation,2024,19(3). DOI:10.1088/1748-022 1/19/03/P03009. [15] JIANG Jiachen,MA Yifei. Computed tomography parameter calibration and imaging principle[J]. IOP Conference Series:Materials Science and Engineering,2018,452. DOI: 10.1088/1757-899X/452/4/042152. [16] 马群,赵美蓉,郑叶龙,等. 基于自适应条件直方图均衡的红外图像细节增强算法[J]. 红外技术,2024,46(1):52-60.MA Qun,ZHAO Meirong,ZHENG Yelong,et al. Infraredimage detail enhancement based on adaptive conditional histogram equalization[J]. Infrared Technology,2024,46(1):52-60. [17] KAUR A,SINGH C. Contrast enhancement for cephalometric images using wavelet-based modified adaptive histogram equalization[J]. Applied Soft Computing,2017,51:180-191. doi: 10.1016/j.asoc.2016.11.046 [18] 战欣茹. 低剂量CT图像域去噪关键技术研究[D]. 北京:北方工业大学,2024.ZHAN Xinru. Research on key technologies for low dose CT image domain denoising[D]. Beijing:North China University of Technology,2024. [19] LIU Xiangyuan,WU Zhongke,WANG Xingce. Validity of non-local mean filter and novel denoising method[J]. Virtual Reality & Intelligent Hardware,2023,5(4):338-350. [20] 张月圆,曾庆化,刘建业,等. 基于Canny的改进图像边缘检测算法[J]. 导航与控制,2019,18(1):84-90.ZHANG Yueyuan,ZENG Qinghua,LIU Jianye,et al. An improved image edge detection algorithm based on Canny algorithm[J]. Navigation and Control,2019,18(1):84-90. -
点击查看大图
图(14) / 表(1)
计量
- 文章访问数: 90
- HTML全文浏览量: 27
- PDF下载量: 8
- 被引次数: 0
