基于差分盒维数的井下电视图像裂缝分割识别方法研究  

Research on Crack Segmentation and Identification Method for Downhole TV Images Based on Differential Box Dimension Algorithm

作　　者：田成富 耿德祥 曹建伟 王明明 Tian Chengfu;Geng Dexiang;Cao Jianwei;Wang Mingming(Hubei Geological Bureau Geophysical Exploration Brigade,Wuhan Hubei 430056,China;Hubei Shenlong Geological Engineering Investigation Limited Company,Wuhan Hubei 430056,China;School of Resources and Civil Engineering,Suzhou University,Suzhou Anhui 234000,China)

机构地区：[1]湖北省地质局地球物理勘探大队,湖北武汉430056 [2]湖北省神龙地质工程勘察院有限公司,湖北武汉430056 [3]宿州学院资源与土木工程学院,安徽宿州234000

出　　处：《工程地球物理学报》2024年第5期909-917,共9页Chinese Journal of Engineering Geophysics

基　　金：安徽省高校自然科学研究项目(编号:2023AH052232);宿州学院博士后科研启动基金(编号:2022BSH002);综合地球物理研究所校级平台项目(编号:2021XJPT54)。

摘　　要：利用井下电视图像对岩心完整性进行识别、分割及裂缝宽度提取是解释岩性、裂隙的关键。目前,井下电视成像结果主要是通过人工方法进行识别解释,工作量大且易受主观因素影响。基于此,针对井下电视图像分割识别,提出从分形理论出发,采用差分盒维数(Differential Box-counting,DBC)算法来提取井下电视图像的岩性变化,以及裂缝、裂隙等岩层纹理特征,进一步通过基于最佳聚类数选择的K-均值聚类算法对井下电视图像进行纹理分割,实现对井下电视图像的岩层自动化分区。结果表明:结合Canny边缘检测算法提取裂缝宽度信息,裂缝识别准确率达到94.2%,实现了岩性的准确分层、裂缝的精细识别。与2D Log-Gabor算法相比,差分盒维数算法对井下电视图像分割效果好、速度快。The key to interpreting lithology and fractures is to identify,segment,and extract crack width from downhole TV images of rock core integrity.At present,the imaging results of downhole television are mainly identified and interpreted through manual methods,which requires a large workload and is easily influenced by subjective factors.This paper focuses on the segmentation and recognition of downhole television images.Starting from fractal theory,this paper proposes to extract the lithological changes by the differential box counting(DBC)algorithm and rock texture features such as cracks and fissures from downhole television images.Then,the K-means clustering algorithm based on the optimal number of clusters is used to perform texture segmentation on downhole television images,achieving automatic rock layer partitioning of downhole television images.The results show that by combining the Canny edge detection algorithm to extract crack width information,the accuracy of crack recognition reaches 94.2%,achieving accurate layering of lithology and fine identification of cracks.Compared with the 2D Log-Gabor algorithm,the differential box dimension algorithm has better segmentation performance and faster speed for downhole TV images.

关 键 词：差分盒维数 井下电视 图像裂缝分割识别 

分 类 号：P631.8[天文地球—地质矿产勘探]