基于正交偏光序列消光特征的岩石薄片颗粒分割与孔隙提取

在岩石薄片正交偏光显微镜下角度域序列图像采集的基础上,分析了不同岩石组分在消光角度域上的光学特征及其差异性,并据此提出一种新的岩石颗粒分割和孔隙分析的方法。充分利用岩石颗粒赋存状态及其晶体光轴产状的复杂性、岩石颗粒空间排列及其接触关系的多样性,对岩石薄片在消光角维度上进行像素尺度的相关分析,并提出相关系数均值、相关系数标准差以及相关系数均差比等敏感参数,实现了岩石颗粒的分割和孔隙的提取。研究表明岩石颗粒内部的像素点灰度和RGB值在角度域上的相关性较强,在颗粒边缘及孔隙内部填隙物分布区域,其相关系数较低,且相关系数标准差要明显高于岩石颗粒内部。该方法从消光特征出发论证了角度域信息完整性的意义,提取的颗粒边缘较为清晰,孔隙结构骨架得以刻画,颗粒分割的效果好于Sobel和Canny等方法。     

基于Manhattan距离的相干体技术的应用

地震相干体技术可以有效地压制连续性,突出不连续性,比地震切片的地质解释更直观,能更细致地进行断层解释。基于Manhattan 距离的相干体技术,与传统的C1 相干算法进行比较,该技术不仅在断层识别能力方面要强于C1 相干算法,而且当利用两种算法获取断层信息的效果相当时,该技术的相关时窗长度要比C1 相干算法所用的相关时窗长度小,这恰能提高程序的运行速度,提高了地震相干体技术的运行效率。此外,该相干体技术也能近似计算出每道在纵横测线方向上的视时间倾角。     

基于多尺度分割的岩石图像矿物特征提取及分析

针对传统岩石薄片鉴定以肉眼观察和描述为主,存在主观性强、定量困难等问题,将数字图像处理方法引入岩石矿物研究,提出了基于多尺度分割的岩石图像矿物特征信息提取方法。以铁质石英砂岩薄片显微镜下单偏光图像为实验对象,获取了石英颗粒的边界及其体积分数、大小、周长、长轴长度和方位、长轴和短轴比、圆度和形态指数等信息。其中：石英颗粒的体积分数为47.07%,小于基质的体积分数,在基质中呈漂浮状,为杂基支撑结构, 表明形成于沉积同生期;长轴的范围为50～604像素,表明石英颗粒大小不均、分选性差;颗粒的圆度为0.27～1.82,形态指数值为1.19～2.46,圆度和形态指数值较小,表明石英颗粒有一定的磨圆度。这种信息的获取和定量分析方法有助于对岩石图像的地学理解。     

基于多聚类中心的加权聚类铸体薄片图像分割方法

针对人工利用显微镜对岩石铸体薄片进行鉴定的低效和普通聚类分割算法对图像边缘分割效果差的问题，本文从岩石特征出发，提出了一种基于聚类分割算法的多聚类中心加权分割新方法，并使用该方法训练了一个适用于岩石铸体薄片的分割模型。使用该模型可以快速地完成对大量薄片的鉴定任务。该方法通过构建新的聚类距离提升了对薄片各组分边缘和内部的分割效果，将多聚类中心的方法和加权的聚类方法相结合，进一步增强了对薄片边缘部分的分割。利用来自疏松岩心的铸体薄片图像进行分割实验，并将本文提出的聚类分割新方法与普通的聚类分割算法的结果进行比较，发现本文方法的分割误差比普通分割方法的误差最高降幅达37.2%。与现有深度学习分割算法对数据量和数据类型的高要求相比，多聚类中心的加权聚类分割算法更适合地质领域中的分割任务，具有较高的应用价值。     

应用改进的相干算法提高三维地震资料解释精度

作者在文中详细探讨了C1、C2和C3三种相干算法及其。根据三维地震数据体的特点提出了实用的相干算法，并编制了相应的软件。我们对三种相干算法对应相干数据体的解释结果进行了细致的分析，C2相干算法基本能够平衡提高横向分辨率和信噪比之间的矛盾，而C3相干算法则取得了更精确的效果。     

相干算法提取嫦娥数据月表地质特征

经典的边缘提取算法可从月球影像数据中提取出月表的构造特征, 但难以提取出与月貌有关的特征信息.本文提出的相干法月球影像地质特征提取技术, 其基本思想是基于相干运算来考察图像上像素或像素组之间的相似性, 以获取月表的构造特征和月貌特征.该方法已经应用在嫦娥一号月球探测器获取的部分影像数据上, 相比于几种常规的边缘提取方法, 本方法优势明显, 不仅能有效地提取环形构造和线性构造等地质特征, 还可以很好地提取月貌特征, 对具有一定规模的小直径撞击坑的识别也有不错的效果.该方法可以用于计算机自动识别或辅助手工解译月表构造, 划分月貌单元等研究.      

花岗岩矿物正交偏光镜下图像人工智能识别研究

人工智能在地球科学领域中的应用是近年来研究的热点,对地球科学的发展有着重要意义,其应用之一就是使用计算机视觉技术实现岩石或矿物的自动化识别分类。然而,目前大多研究直接对岩石薄片图像进行分类,不能够精细定位并识别薄片中多且复杂的矿物目标。虽然现已有许多学者将目标检测技术应用于岩石矿物的图像识别分类中,但这些方法识别的对象大多是岩石手标本图像,只能对图像中的单一对象检测。在识别分类研究领域中,缺少对岩石薄片镜下图像识别的算法及质量较好的相关数据集。为了解决这些问题,本文首先采集了3000张正交偏光镜下花岗岩薄片图像,标注矿物样本10000余个,并通过数据增广方式对数据集进行增强,建立了一个质量较好、具有多样性的数据集。其次本文提出基于Yolov5x的改进算法RDB-Yolov5x。这种方法在特征提取过程中添加了密集连接方式,使用密集连接残差模块（RDB）替代传统的残差结构,有效地保留了图像的语义和位置信息细节。实验结果表明该方法泛化能力较好,在对图像中小尺寸、特征模糊的矿物颗粒的识别中表现出优秀的性能,可以准确有效地对花岗岩中的五类目标矿物（石英、黑云母、白云母、斜长石、钾长石）进行识别,...     

局部结构熵算法在地震数据不连续性检测中的应用

自从相干地震数据体概念被提出以来,许多学者提出了不同的基于相干性检测地质结构不连续性的算法。例如,基于特征结构的相干算法,局部结构熵算法以及第二与第一特征值比值算法等。本文基于小波变换具有多尺度多分辨率分析的优点,提出了在特定的小波变换分频瞬时属性上,利用局部结构熵算法来检测地震数据的局部不连续性。实际地震资料检测结果表明,基于分频瞬时相位的局部结构熵算法更能有效地检测到地震数据的细微变化,对于油气藏的精细刻画有重要意义。      

构造弱变形区自动有限应变测量-以石英砂岩为例

有限应变测量是研究岩石变形特征的重要研究内容。为了提高岩石有限应变测量的精度与速度,改变手工测量岩石有限应变耗时、枯燥的状况,应用多重图像限制的自动种子区域生长算法,以大青山地区为例,对如变形区内的石英砂岩有限应变进行了自动测量。该算法综合多个图像、利用色彩信息,不需要特殊设备即可对颗粒进行自动识别。算法还在叠加后的图像中,应用了修改的Canny边缘检测算法增强颗粒边界与内部的对比度。识别结果与手工测量的颗粒,在质心坐标、面积、长轴、短轴、有限应变测量方面具有很大的相似性。      

相干体与图像锐化联合在地震解释中的应用

详细讨论了第三代相干算法的基本原理,并将图像锐化处理与相干体相结合应用到地震解释中,发现将图像锐化处理与相干体技术相结合,更能充分利用三维地震数据体中的信息,清楚地展示断层的空间走向等属性信息,更好地识别岩性体边界等,提高地震解释的精度。     

基于钻孔图像的岩体结构面几何信息智能测量

针对钻孔图像中岩体结构面形态特征,提出了一种基于Canny检测的岩体结构面几何信息智能测量方法。该方法首先采用灰度共生矩阵特征参数,在长幅钻孔图像中定位结构面区域;然后,对识别的结构面区域,采用Canny检测算法识别出结构面边缘,并通过边缘连接和合适的阈值筛选边缘,提取出结构面上下边缘;最后,对结构面边缘进行三角函数拟合,得到结构面上下边缘的正弦曲线,结合立体空间几何理论,从而计算出岩体结构面的倾向、倾角、隙宽等参数。以如美水电站坝址区两钻孔为例,基于本算法提取结构面几何信息,并与已有成功算法进行对比得到了较为一致的结果,证明了算法的可行性。     

基于蚁群和Canny边缘检测算子混合算法的二维岩石图像裂隙特征提取与修复研究

岩石中常含有裂缝、岩脉等细小而重要的微观结构,需要高分辨率的成像技术来提取其特征。在岩石图像处理中,特征提取可以提取出岩石的主要结构信息从而极大降低数据量,然而某些细线状岩石特征(如裂缝、裂隙等)往往无法被完整识别出来而存在间断现象。本文在采用蚁群算法修复岩石细线状特征的基础上,综合利用蚁群算法、DBSCAN聚类算法和Canny算子提出一种新的岩石图像修复算法。根据设定的阈值,对提取的图像间断部分进行搜索并连接,以修复在图像特征提取过程中缺失的部分重要信息,同时去除修复过程产生的多余特征。实际结果表明,利用混合算法处理的岩石特征提取图像得到了较好的修复,能够提高岩石裂隙特征提取的准确性。     

成像雷达干涉测量数据相关性与干旱-半干旱地区地表类型特征的关系

利用欧洲资源卫星1号和2号获取的重轨干涉测量雷达数据，首先进行干涉测量数据相关性估测，并结合干涉测量数据的振幅信息，开展新疆喀什试验区地表土地类型的识别与分类，区分和识别出裸土、盐碱地、灌丛、裸岩/戈壁、沼泽和水体 6类土地类型。最后通过对不同土地类型的后向散射特性和相关性的分析，探讨了干涉测量数据相关性与干旱-半干旱地区地表特征的关系。     

A new algorithm using image colour system transformation for rock grain segmentation

Summary The present paper is concerned with the development and application of an effective automatic algorithm of image analysis in order to detect grain boundaries on microscope images of Redziny dolostone and Wisniowka quartzite. The algorithm utilises sets of 6 colour images for each measurement field on thin sections, which are recorded using an optical polarizing microscope in different polarization set-ups. The proposed method is based on an image pre-processing procedure that is focused on colour system transformation, followed by rock grain boundaries segmentation using the image analysis methods for each colour image. For the image pre-processing procedure, several colour system transformations were selected and compared. By using the alternative colour systems that concentrate on colour information we are able to minimise the effects of internal micro-structures in the grain boundaries segmentation procedure. The grain boundary maps obtained confirm that the use of an approximately perceptually uniform colour system as an image pre-processing procedure can significantly improve the rock grain segmentation. This newly-developed method may facilitate petrographical and stereological studies of rock structures.     

砂样图像岩屑自动分割提取方法

通过将砂样图像进行单颗粒分割,识别砂样成分,可显著提高砂样岩性分析的准确性和效率。现有的砂样图像分割方法主要以传统分水岭算法和卷积神经网络为主,但由于对单颗粒岩屑轮廓细节提取不足,误分割率高。本文提出一种以图像融合算法为桥梁,将卷积神经网络和分水岭算法相结合的单颗粒图像分割提取方法。首先利用改进的Mask R-CNN网络快速分割砂样原图,获得其初分割图像;然后,将初分割图像与砂样原图进行融合,再使用改进的分水岭算法对融合结果进行分割;最后,利用砂样原图坐标点匹配方法,将分水岭分割得到的结果图像进行修正,完成单颗粒岩屑图像提取。实验结果表明,本文的单颗粒自动分割提取方法准确率高达96.77%,且模型更轻量和精准,为岩屑图像分割提供了一种可行且有效的方法,可满足有效测算油藏层构造变化、查找潜在沉积物源及储层动态变化的需求。     

A novel random discrete element analysis of rock fragmentation

This paper presents a novel probabilistic approach of random discrete element analysis (RDEA) to investigate the mechanism of rock fragmentation under uniaxial compression. This model combines the advantages of both random field theory and discrete element method in characterizing the spatial variation and uncertainty of microscopic material properties. The numerical results reveal that the stress-strain curves of a group of tests can match well the general trend of the experimental data, with the mean uniaxial compressive strength (UCS) of 10.18 MPa and the mean Young modulus of 1.73 GPa. The coefficient of variation (COV) for the rock samples is much lower than that of the initial random fields of particles because of the averaging effect of microscopic material property in obtaining the bulk values. The rock fragmentation is initiated by the breakage of weak particles within the rock mass, and it develops rapidly as the vertical loading stress approaches the UCS. The final damage zone resides dominantly in the weak region of the rock sample, and the distribution of material property coefficients follows a similar beta distribution as the corresponding initial random field. Rock samples with persistent “pillar-like” structures of strong particles can effectively resist the normal compression, resulting in high rock strengths. The traditional DEM simulation with a set of constant material properties can only represent one extreme realization of random field, which could significantly overestimate the rock strength. The proposed RDEA approach can effectively capture the uncertainty and complex interactions of rock fragmentation in a more realistic and reliable way.     

Porous Structure Reconstruction Using Convolutional Neural Networks

The three-dimensional high-resolution imaging of rock samples is the basis for pore-scale characterization of reservoirs. Micro X-ray computed tomography (µ-CT) is considered the most direct means of obtaining the three-dimensional inner structure of porous media without deconstruction. The micrometer resolution of µ-CT, however, limits its application in the detection of small structures such as nanochannels, which are critical for fluid transportation. An effective strategy for solving this problem is applying numerical reconstruction methods to improve the resolution of the µ-CT images. In this paper, a convolutional neural network reconstruction method is introduced to reconstruct high-resolution porous structures based on low-resolution µ-CT images and high-resolution scanning electron microscope (SEM) images. The proposed method involves four steps. First, a three-dimensional low-resolution tomographic image of a rock sample is obtained by µ-CT scanning. Next, one or more sections in the rock sample are selected for scanning by SEM to obtain high-resolution two-dimensional images. The high-resolution segmented SEM images and their corresponding low-resolution µ-CT slices are then applied to train a convolutional neural network (CNN) model. Finally, the trained CNN model is used to reconstruct the entire low-resolution three-dimensional µ-CT image. Because the SEM images are segmented and have a higher resolution than the µ-CT image, this algorithm integrates the super-resolution and segmentation processes. The input data are low-resolution µ-CT images, and the output data are high-resolution segmented porous structures. The experimental results show that the proposed method can achieve state-of-the-art performance.     

一种改进的光滑粒子动力学法在地震条件下岩质边坡中的验证与应用

开发一种改进损伤框架的粒子流算法,被称为核断裂的光滑粒子流法（kernel?broken smoothed particle hydrodynamics,KBSPH）,用于模拟地震条件下岩质边坡的裂纹扩展和变形破坏过程.在KBSPH中,提出一种改进的损伤框架,通过引入断裂标志来改进损伤粒子的核函数,使损伤粒子的虚拟应力键直接断裂,裂纹在断裂的应力键间生成,从而模拟岩石的裂纹扩展过程.在地震边界上采用了双层边界,将动力输入边界与黏滞边界分离.首先通过薄板振动实验验证KBSPH的动力特性.其次以单裂隙岩体单轴压缩试验验证KBSPH的断裂力学特性.最后模拟地震条件下多节理岩质边坡中裂纹扩展过程和动力响应.薄板振动实验验证了KBSPH的动力特性的准确性.单裂隙岩体单轴压缩试验,证明了KBSPH可以正确模拟预制裂隙尖端的翼型裂纹.通过对比以往数值模拟方法和现场案例,表明KBSPH正确揭示了加速度放大效应以及地震条件下岩质边坡的裂纹扩展过程.KBSPH避免了传统算法的网格畸变,损伤粒子应力分量重新分配的问题,降低了编程难度,提高了运行速率,可为SPH在地震条件下岩石力学中的应用和理解岩石断裂机理提供一定的参考.      

Deep learning based classification of rock structure of tunnel face

The automated interpretation of rock structure can improve the efficiency,accuracy,and consistency of the geological risk assessment of tunnel face.Because of the high uncertainties in the geological images as a result of different regional rock types,as well as in-situ conditions(e.g.,temperature,humidity,and construction procedure),previous automated methods have limited performance in classification of rock structure of tunnel face during construction.This paper presents a framework for classifying multiple rock structures based on the geological images of tunnel face using convolutional neural networks(CNN),namely Inception-ResNet-V2(IRV2).A prototype recognition system is implemented to classify 5 types of rock structures including mosaic,granular,layered,block,and fragmentation structures.The proposed IRV2 network is trained by over 35,000 out of 42,400 images extracted from over 150 sections of tunnel faces and tested by the remaining 7400 images.Furthermore,different hyperparameters of the CNN model are introduced to optimize the most efficient algorithm parameter.Among all the discussed models,i.e.,ResNet-50,ResNet-101,and Inception-v4,Inception-ResNet-V2 exhibits the best performance in terms of various indicators,such as precision,recall,F-score,and testing time per image.Meanwhile,the model trained by a large database can obtain the object features more comprehensively,leading to higher accuracy.Compared with the original image classification method,the sub-image method is closer to the reality considering both the accuracy and the perspective of error divergence.The experimental results reveal that the proposed method is optimal and efficient for automated classification of rock structure using the geological images of the tunnel face.