Strain field measurements around notches using SIFT features and meshless methods

Abstract

This work proposes a hybrid experimental-numerical technique with the aim to improve strain measurements at stress concentration regions. The novel technique is performed employing the computer vision scale invariant feature transform (SIFT) algorithm and meshless methods, here termed SIFT-meshless. The SIFT is applied to perform feature points matching in two images of the specimen surface at different stages of mechanical deformation. The output data are provided as a set of displacement measurements by tracking matched feature points. This information is then used to model displacement and strain field on the surface by means of a meshless formulation based on the moving least squares approximation. By applying the proposed SIFT-meshless method, the strain distribution around a semicircular notch in a plate under bending load was investigated. The experimental results were compared with those obtained by a digital image correlation technique based on a subset approach and to simulations from finite element analysis software. The experimental results demonstrated that the present method is capable of performing reliable strain measurements at distances close to the notch where the peak strain value is expected, even in the presence of high strain gradients.

Machine vision system for high-temperature wind tunnel: Principle, design and application

“…这些 特征在图像发生变换时仍能保持较好的稳定性和可识 别性, 对于变形前后尤其是散斑发生退化前后的图像 图 9 (网络版彩图)紫外双目视觉技术在高温模拟试验中的应用. (a) 高温电弧风洞烧蚀试验 [51] ; (b) 石英灯加热试验 间的匹配精度较高, 其中尺度不变变换特征对于图像 尺度变化及旋转具有较好的稳定性, 已被成功应用于 应变集中区域变形的测量 [73] . 将上述图像区域特征方 法应用到高温图像的识别和处理中, 具有广阔的应用 前景.…”

Accurate Measurements of High Strain Gradients near Notches Using a Feature-Based DIC Algorithm

“…Thus, the differences between the measured and imposed strains can be used in order to predict the expected AL (amplitude loss) for each DIC algorithm evaluated. For that, the following model was used: (13) where, n is the number of evaluation points.…”

“…Another recently proposed algorithm is the SIFT-Meshless method [13] which uses a feature-based matching approach for correlating images. Features are points or small patches on the image that differ from their immediate surrounding region and can easily be extracted by means of efficient algorithms.…”

Vision‐based displacement measurement enhanced by super‐resolution using generative adversarial networks

“…Meanwhile, modern cities are equipped with a large number of surveillance video cameras that can record images and videos of urban buildings and infrastructures without additional installation efforts, which has the potential to support SHM applications. 5 In terms of the structural displacement measurement problem, there are three main types of commonly-used methods: (1) template matching: this method searches for the most similar patch in the target with a predefined template based on certain correlation metrics and then calculates the structural displacement [6][7][8][9] ; (2) key point matching: this method detects sparse points with significant and stable features in the images and computes the feature description operators to match the set of points before and after structural displacement or directly defines key points based on the geometric features of the targets for specific problems and tracks the position change of the points [10][11][12][13][14][15][16][17][18][19] ; (3) optical flow tracking: optical flow is a method used to describe the motion of pixels in sequential images, where the motion of certain pixels or the full scene is calculated based on differential or phase equations. [20][21][22][23][24] Other research has developed full-field measurement techniques for specific problems, utilizing the advantage of the vision-based system.…”