基于计算机视觉技术的结构表面裂缝检测方法研究

计算机视觉技术用于混凝土结构表面裂缝检测,具有现场检测方便、效率高、客观性强的特点,但图像数据分析是该技术的核心,其中裂缝提取与定量测量较为复杂。为提高裂缝图像处理效率和准确率,将深度学习和数字图像处理技术相结合,提出一种裂缝检测方法。建立基于深度卷积神经网络的裂缝识别模型,在图像上自动定位裂缝并结合图像局域阈值分割方法提取裂缝。在裂缝宽度定量测量方面,采用双边滤波算法和三段线性变换对裂缝图像进行预处理,提高了裂缝边缘识别的精确度。通过改进边缘梯度法,实现裂缝最大宽度的定位和裂缝最大宽度的自动获取。该研究为全自动识别裂缝图像及高精度测量裂缝宽度提供了一种解决方法。     

盾构隧道管片裂缝图像识别及宽度计算优化方法

针对盾构隧道管片结构裂损的图像,基于数字图像处理技术,运用软件MATLAB的图像处理功能进行裂缝图像灰度变换及均衡化、图像分割及裂缝识别、边缘提取和宽度计算。在宽度计算中,采用霍夫变换对曲线裂缝进行拟合,细化裂缝图像的宽度,得到更精确信息。     

基于数字图像处理的裂缝检测方法

为保证图像质量,提出一种基于阈值判断的自适应中值滤波(TAMF)新算法。通过扩充图像边界,将噪声图像与对其进行中值滤波后的图像相减得到的灰度值均值T作为判断条件,对搜索窗口内的噪声像素点采用中值滤波处理后输出结果,信号点则不做处理。使用几种滤波算法进行试验分析,结果表明,不同浓度的椒盐噪声均可采用TAMF算法进行滤除,该算法能有效保护图像边缘细节,在PSNR和MSE等图像性能指标上维持较高的水平,为后续裂缝宽度测量提供良好环境。数字图像处理通过获取图像(裂缝)灰度信息,对图像(裂缝)特征进行提取;然后,基于TAMF算法与改进的切线垂线法,将数字图像处理中的图像预处理、裂缝骨架提取、裂缝宽度计算等方法进行集成,提出一套基于数字图像处理的混凝土裂缝图像宽度测量流程,该测量流程所需设备单一,可大幅提高检测精度和效率,满足工程应用要求。     

基于图像处理技术的房屋裂缝宽度变化实时监测研究

基于MATLAB数字图像处理技术,对房屋裂缝宽度变化进行实时监测,依次对采集裂缝图像进行灰度化、图像滤波、二值化、目标区域分割标记和像素标定等处理,计算获得图像裂缝最大宽度值及单次变化值、人工标志间距离变化值。通过与实测数据相比,运用本文提出的计算方法获得房屋裂缝检测数据的识别精度为99.19%。利用MATLAB图像处理技术获得人工标志间距离变化值与最大裂缝宽度变化值累计相对误差为0.16%,人工标志间距离变化能够反映裂缝宽度变化情况。对于实际情况中无法寻找裂缝最大宽度处,而进行裂缝宽度变化实时监测时,可用人工标志间距离变化反映裂缝宽度变化情况。     

基于计算机视觉技术的裂缝特征参数提取方法研究与裂缝检测系统设计

目前国内外学者针对混凝土结构所提出的裂缝图像处理算法可移植性较差,还未有较为通用的算法。对目前常用的图像预处理算法及特征参数提取算法在混凝土裂缝图像识别方面的适用性进行了研究,从相机的拍摄和校正、图像预处理、裂缝特征参数提取等方面对比了不同的算法处理效果,并自主开发了一套混凝土裂缝检测系统。     

基于全卷积神经网络的桥梁裂缝分割和测量方法

为了提高桥梁病害检测自动化水平,解决当前人工检测耗时费力和传统图像分割方法存在去噪效果不明显、分割后裂缝连续性较差等问题,提出了一种基于全卷积神经网络的BCI-AS(Bridge Crack Image-Automatic Segmentation)桥梁裂缝自动分割模型和一种基于投影技术的最小二乘拟合中心线的裂缝宽度测量算法。基于BCI-AS的模型对桥梁裂缝图像数据集进行了精确的像素级分割,分割准确率达到94.45%。基于投影技术最小二乘拟合中心线的算法对分割的裂缝二值图进行了宽度测量,结果表明相对误差在7%以下,证明了所提出具体算法对裂缝分割和裂缝宽度计算的可行性。     

基于无人飞机成像的桥梁裂缝宽度识别可行性研究

基于传统桥梁检测车裂缝宽度检测存在阻碍交通、受到桥型限制、使用维护费用高等问题。该文以旋翼无人飞机为工作平台,为满足0.2mm以上桥梁裂缝宽度识别要求,采用IMETRUM非接触式测量仪验证无人机悬停状态下机载成像质量具有可靠性;通过加装机载三点激光测距仪,测量物距并推导成像平面与被测平面夹角,计算并修正裂缝图像像素解析度;设计适于无人机成像的图像预处理程序、构建基于支持向量机（SVM）裂缝形态智能提取训练模型、裂缝法向实际宽度计算方法。以湘潭市湘江二大桥为研究对象,通过对实桥进行无人机裂缝宽度识别,并与传统人工测试进行比较,表明机载成像识别裂缝宽度满足工程精度要求,以无人飞机为工作平台替代桥检车或支架工作平台,实现结构表面裂缝形状与宽度识别具有可行性和广泛应用前景。     

超长钢筋混凝土池壁结构裂缝控制技术的研究

多年来,超长钢筋混凝土结构裂缝宽度的预测与控制一直是研究的热门课题。然而,对于边缘约束墙体的裂缝控制的加固设计仍然缺乏共识。本文以某体育中心游泳跳水馆为工程实例,介绍了一种超长钢筋混凝土池壁结构裂缝控制新技术,讨论了新型超长钢筋砼池壁"止水带"在超长钢筋混凝土池壁中的施工工艺和可行性,并通过与传统技术的对比分析发现,该技术具有施工速度快、裂缝控制效果好等优势。     

边缘检测算子及其在裂缝图像中的应用

简要介绍了几种经典的边缘检测技术,并在MATALB中利用这些算子对约束收缩引起的混凝土裂缝进行裂缝图像的边缘检测,通过对比几种算子的分析结果,总结出相对有效的裂缝图像边缘检测算子,为进一步施行裂缝表征参数的提取提供依据。     

基于数字图像处理的混凝土微裂纹定量分析技术

在应用真空荧光环氧浸渍技术得到含微裂纹的混凝土显微图像的基础上,基于MATLAB搭建开发了由二值化、形状分析、骨架化和自动测量4个模块组成的混凝土微裂纹定量分析软件QUANSIMIC(quantitative analysis system of microcracks in concrete),可实现微裂纹区域的识别、提取以及面积、长度及宽度等二维结构特征参数的测量分析.其中二值化模块中采用Intermodes法确定灰度阈值进行微裂纹区域的识别和提取;形状分析模块中分别采用开操作去除噪声,采用长宽比为20的判别准则区分孔隙与裂纹;在自动测量模块中的长度计算时考虑了微裂纹骨架的宏观倾角,相对误差很低.     

Monitoring Crack Changes in Concrete Structures

Abstract:   This study proposes a crack-monitoring system to quantify the change of cracks from multitemporal images during the monitoring period. A series of images were taken from an off-the-shelf digital camera. Concrete cracks were extracted from the digital images by employing a series of image-processing techniques. The image coordinates and orientation of same cracks can be changed since the position and direction of the portable camera vary at every exposure time. To monitor the crack changes (width and length), it is critical to transform the image coordinates of cracks extracted from each image into the same object coordinates of the concrete surface. In this study, such a geometric relationship was automatically recovered using the two-dimensional (2D) projective transformation based on the modified iterated Hough transform (MIHT) algorithm, the result of which solved the transformation parameters. To improve the computational operation of MIHT, regions of parameter estimation were also investigated. The developed algorithms were applied to monitor the crack of the concrete specimen. As a result, the change of cracks on the concrete specimen was successfully detected and accurately quantified.     

Image quality evaluation method for surface crack detection based on standard test chart

The use of automated equipment for surface crack detection based on digital image acquisition is becoming increasingly popular in the inspection industry. While researchers typically focus on improving the accuracy of recognition methods, the image quality is essential to the effectiveness of the algorithm. However, evaluating the quality of crack images has received little attention in computer-aided civil and infrastructure engineering. A prominent issue is whether surface cracks are visible and measurable in images. This study proposes an image quality evaluation method using an original standard test chart that simulates cracks of different widths and directions. Geometric transformations and preprocessing techniques are employed in a full-reference strategy to process the acquired crack images. The resulting information provides quantitative scores for crack visibility and measurability. The proposed Crack Structural Similarity Index is more in line with human perception and offers an accurate evaluation of real image quality. The study shows that Gaussian blur disturbance and random noise disturbance primarily affect measurability and visibility, respectively. Furthermore, the study finds that the quality of the crack image improves with increasing sensor pixel size and using a prime lens over a zoom or long zoom lens. This approach enables comparing image quality collected by different devices in the field environment and provides guidance for optimizing field acquisition parameters. In the future, the results of this study can be applied to facilitate the application of automated testing equipment and improve overall performance.     

基于摄影法的红黏土裂隙试验研究

准确提取红黏土裂隙特征,有助于进一步研究裂隙对红黏土工程性质的影响。本文以桂林红黏土试样为试验研究对象,获取红黏土表面裂隙数字图像后,通过比对不同方法,发现直方图阈值法适用于红黏土的裂隙图像分割。通过去除杂点、填充细小孔洞,将裂隙数字图像转化为二值图像,最后进行骨骼化和消刺处理,可得裂隙骨骼图像。研究发现试样在第5次干湿循环后裂隙发育均已趋稳定;初始含水率为25%的试样在干湿循环作用下发育出线状裂隙;初始含水率为28%的试样则发育出网状裂隙;干湿循环次数与裂隙率和裂隙总长度具有良好的相关性,可用二次函数拟合。     

基于图像分析的节理岩体单轴压缩损伤演化研究

 为定量地研究节理岩体的损伤演化规律,对岩体石膏模型试件单轴压缩试验过程中拍摄的表面数字图像进行处理分析。编制Matlab程序,实现单个裂纹的识别、裂纹长度和方位角、总裂纹面积分数和总裂纹分形维数的计算。对节理倾角和节理连通率这2个参数组合变化下的试件表面裂纹图像的分析结果为：(1) 试件表面总裂纹面积分数和总裂纹分形维数变化规律基本相似,在各节理连通率和各节理倾角下,2个参量都随轴向应变的增加而增大;(2) 可将试件分为两大组,节理倾角为0°,15°,75°,90°试件(劈裂破坏为主)和节理倾角为30°,45°,60°的试件(剪切破坏为主),第1组试件表面的总裂纹面积分数和总裂纹分形维数值都高于第2组试件;(3) 具有相同节理连通率的试件,在试验开始点不同节理倾角的总裂纹面积分数基本相同,在峰值荷载点和试验结束点的总裂纹面积分数随节理倾角的变化曲线基本呈V型(最小值在节理倾角为45°处,最大值在节理倾角为0°处);(4) 表面裂纹在试验开始时和加载过程中的各向异性分布特征,可以用裂纹面积分数沿裂纹方位角的分布图来表征。研究结果表明,表面裂纹图像分析可以有效地定量研究节理岩体试件的各向异性损伤演化特征。     

Beamlet Transform‐Based Technique for Pavement Crack Detection and Classification

Abstract: This article presents a Beamlet transform‐based approach to automatically detect and classify pavement cracks in digital images. The proposed method uses a pavement distress image enhancement algorithm to correct the nonuniform background illumination by calculating the multiplicative factors that eliminate the background lighting variation. To extract linear features such as surface cracks from the pavement images, the image is partitioned into small windows and a Beamlet transform‐based algorithm is applied. The crack segments are then linked together and classified into four types: vertical, horizontal, transversal, and block. Simulation results show that the method is effective and robust in the extraction of cracks on a variety of pavement images.     

Automated image processing technique for detecting and analysing concrete surface cracks

In the present work, an image processing technique that automatically detects and analyses cracks in the digital image of concrete surfaces is proposed. The image processing technique automates the measurement of crack characteristics including the width, length, orientation and crack pattern. In the proposed technique, a morphological technique was applied to correct the non-uniform brightness of the background, and enhanced binarisation and shape analysis were used to improve the detection performance; furthermore, detailed algorithms to calculate the crack width, length, orientation and an artificial neural network to recognise crack patterns including horizontal, vertical, diagonal (?45°), diagonal (+45°), and random cracks are proposed. An image processing program was developed for the proposed algorithm and a series of experimental and analytical investigations were performed to assess the validity of the algorithm. Then, the crack characteristics measured using the proposed technique were compared with those obtained using a conventional technique. The test results showed that the crack characteristics can be accurately measured and analysed using the proposed technique.     

隧道衬砌裂缝特征提取方法研究

 衬砌裂缝图像的分割和信息提取是裂缝自动检测系统中的重点。本文在采集图片大量试验的基础上对裂缝信息采集流程进行优化。其中,针对衬砌图像分割,提出结合prewitt算子和otsu的梯度类间阈值法,并用数学形态学对图片进行进一步优化,从而得到裂缝区域完整而杂质区域较少的二值图像;针对裂缝特征提取,通过对试验图片集合特征的分析确定描绘子为集中度、外接矩形长宽比、外接矩形占有率、平均宽度等。应用实例表明,梯度类间阈值法能够更好地实现对图像的分割,较常用的otsu算法更能适应复杂背景的裂缝图片。通过对优化图像的不同区域进行描绘特征提取统计,可形成具有一定代表性的图片库,为实现裂缝自动识别奠定基础。     

Image analysis method for crack distribution and width estimation for reinforced concrete structures

Crack observation is important for evaluating the structural performance and safety of reinforced concrete (RC) structures. Most of the existing image-based crack detection methods are based on edge detection algorithms, which detect cracks that are wide enough to present dark areas in the obtained images. Cracks initiate as thin cracks, generally having width less than the width of a pixel in images; such cracks are generally undetectable by edge detection-based methods.An image analysis method is proposed to observe the development and distribution of thin cracks on RC surfaces; it also allows estimation of crack widths. Image matching based on optical flow and subpixel is employed to analyze slight concrete surface displacements. Camera calibration is included to eliminate perspective effects and lens distortion. Geometric transformation is adopted so that cameras do not need to be perpendicular to the observed surface or specified positions. Formulas are proposed to estimate the width of shear crack opening. The proposed method was then applied to a cyclic test of an RC structure. The crack widths and their development analyzed by the image analysis were verified with human inspection in the test. In addition, concrete surface cracks that appeared at a very early stage of the test could be observed by the proposed method before they could be detected by the naked eye. The results thus demonstrate that the proposed image analysis method offers an efficient way applicable not only for structural tests but also for crack-based structural-health-monitoring applications.     

Digital image analysis of fluid inclusions

Fluid inclusions commonly exist in the cracks of rock masses. From a microscopic point of view, the fluid inclusion plane (FIP) is the crack plane while the fluid inclusion line (FIL) is the intersecting line between a specific plane (horizontal or different) and the FIP. These microscopic compositions or structures not only provide valuable information on the deformations and/or fractures of rocks but also reflect the trend, length and width of cracks. This paper presents the digital image analysis of fluid inclusions in rocks and discusses the characteristics of FILs. For the image analysis, the original digital images photographed by the microscope equipped with a digital camera on a heating–freezing platform were first converted into grayscale images and then broken into blocks using quadtree decomposition and region segmentation. For each block, the inflection point, derivative, frequency and color-based methods were used to detect the edges of fluid inclusions. To better define the boundaries of fluid inclusions, the dilation, erosion, seed filling, boundary connection and smoothing techniques were used to, respectively, extend edges, connect discontinuous points, fill pores in the outlines, eliminate irrelative parts in neighboring positions, smoothen projecting parts around the outlines and aggregate smaller inclusions into larger ones. After the boundaries of fluid inclusions were defined, the blocks were re-assembled and the edge points and lines of fluid inclusions were then defined in a global coordinate system. Based on the geometrical properties of the fluid inclusions, such as the centroid positions, areas and long-axis directions, FILs and their configuration parameters (such as length, mean width and abundance) were obtained with the least-squares method. All of these procedures were coded into a program and could be automatically run. The digital image analyses of fluid inclusions may provide valuable information about the relationships between the FIL networks and the crack properties.