FracDetect: A novel algorithm for 3D fracture detection in digital fractured rocks

被引:12
作者
Ramandi, Hamed Lamei [1 ]
Irtza, Saad [2 ]
Sirojan, Tharmakulasingam [2 ]
Naman, Aous [2 ]
Mathew, Reji [2 ]
Sethu, Vidhyasaharan [2 ]
Roshan, Hamid [1 ]
机构
[1] UNSW Sydney, Sch Minerals & Energy Resources Engn, Sydney, NSW 2052, Australia
[2] UNSW Sydney, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia
基金
澳大利亚研究理事会;
关键词
Fracture detection; Micro-CT image; Computer vision; Fractured media; RAY COMPUTED-TOMOGRAPHY; HIGH-RESOLUTION; IMAGE; SEGMENTATION; ENHANCEMENT; APERTURE; FEATURES; SAMPLES; SHALE;
D O I
10.1016/j.jhydrol.2022.127482
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Fractures have a governing effect on the physical properties of fractured rocks, such as permeability. Accurate representation of 3D fractures is, therefore, required for precise analysis of digital fractured rocks. However, conventional segmentation methods fail to detect and label the fractures with aperture sizes near or below the resolution of 3D micro-computed tomographic (micro-CT) images, which are visible in the greyscale images, and where greyscale intensity convolution between different phases exists. In addition, conventional methods are highly subjective to user interpretation. Herein, a novel algorithm for the automatic detection of fractures from greyscale 3D micro-CT images is proposed. The algorithm involves a low-level early vision stage, which identifies potential fractures, followed by a high-level interpretative stage, which enforces planar continuity to reject false positives and more reliably extract planar fractures from digital rock images. A manually segmented fractured shale sample was used as the groundtruth, with which the efficacy of the algorithm in 3D fracture detection was validated. Following this, the proposed and conventional methods were applied to detect fractures in digital fractured coal and shale samples. Based on these analyses, the impact of fracture detection accuracy on the analysis of fractured rocks' physical properties was inferred.
引用
收藏
页数:12
相关论文
共 68 条
[1]   Representative elementary volume analysis of porous media using X-ray computed tomography [J].
Al-Raoush, Riyadh ;
Papadopoulos, Apostolos .
POWDER TECHNOLOGY, 2010, 200 (1-2) :69-77
[2]   Petrophysical assessment of Australian organic-rich shales: Beetaloo, Cooper and Perth basins [J].
Algazlan, Muath ;
Pinetown, Kaydy ;
Grigore, Mihaela ;
Chen, Zhixi ;
Sarmadivaleh, Mohammad ;
Roshan, Hamid .
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2019, 70
[3]  
[Anonymous], 2018, DIGITAL IMAGE PROCES
[4]  
[Anonymous], 2009, COMPUT TOMOGR
[5]  
[Anonymous], 2005, The ITK Software Guide, DOI DOI 10.1016/j.neuroimage.2012.10.081
[6]   The effect of deformation on two-phase flow through proppant-packed fractured shale samples: A micro-scale experimental investigation [J].
Arshadi, Maziar ;
Zolfaghari, Arsalan ;
Piri, Mohammad ;
Al-Muntasheri, Ghaithan A. ;
Sayed, Mohammed .
ADVANCES IN WATER RESOURCES, 2017, 105 :108-131
[7]   Integrating Machine/Deep Learning Methods and Filtering Techniques for Reliable Mineral Phase Segmentation of 3D X-ray Computed Tomography Images [J].
Asadi, Parisa ;
Beckingham, Lauren E. .
ENERGIES, 2021, 14 (15)
[8]  
Chao Qi, 2018, Petroleum Research, V3, P259, DOI 10.1016/j.ptlrs.2018.08.003
[9]   Image moments: A general and useful set of features for visual servoing [J].
Chaumette, F .
IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 2004, 20 (04) :713-723
[10]   Rock images classification by using deep convolution neural network [J].
Cheng, Guojian ;
Guo, Wenhui .
2ND ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION SYSTEM AND ARTIFICIAL INTELLIGENCE (ISAI2017), 2017, 887