Geometric Matching Research Articles

An accurate novel circular hole inspection method for sheet metal parts using edge-guided robust multi-view stereo

Sheet metal parts are frequently used in the industrial field, and the circular holes on these parts are commonly employed as assembly references. Therefore, precise measurement of these circular holes is essential. Because of the scratches, rust, and complex reflection around the edges, the measurement of circular holes on sheet metal parts is a challenging task. In this research, an accurate circular hole inspection method for sheet metal parts is proposed to realize online inspection using a multi-camera system. After capturing images in a single shot, edge detection is adopted to obtain sub-pixel circular hole contours. A new adaptive matching cost based on the descriptor of binary robust independent elementary features and bilinear normalized cross-correlation is introduced to the PatchMatch-based multi-view stereo method to obtain dense and accurate point clouds. To improve the accuracy and integrity of circular hole measurement, a new edge-guided multi-scale geometric consistency matching strategy is proposed accompanied by depth detail restoration. Finally, the points around the circular hole in a spherical range are sampled using the trinocular constraint principle and fitted with the circular equation. The experimental results show that the proposed algorithm performs well, with an error of approximately 0.04 mm, and improves the measurement accuracy compared with the state-of-the-art algorithms.

Influence of Synthesis Conditions on the Crystal, Local Atomic, Electronic Structure, and Catalytic Properties of (Pr1−xYbx)2Zr2O7 (0 ≤ x ≤ 1) Powders

The influence of Yb3+ cations substitution for Pr3+ on the structure and catalytic activity of (Pr1−xYbx)2Zr2O7 powders synthesized via coprecipitation followed by calcination is studied using a combination of long- (s-XRD), medium- (Raman, FT-IR, and SEM-EDS) and short-range (XAFS) sensitive methods, as well as adsorption and catalytic techniques. It is established that chemical composition and calcination temperature are the two major factors that govern the phase composition, crystallographic, and local-structure parameters of these polycrystalline materials. The crystallographic and local-structure parameters of (Pr1−xYbx)2Zr2O7 samples prepared at 1400 °C/3 h demonstrate a tight correlation with their catalytic activity towards propane cracking. The progressive replacement of Pr3+ with Yb3+ cations gives rise to an increase in the catalytic activity. A mechanism of the catalytic cracking of propane is proposed, which considers the geometrical match between the metal–oxygen (Pr–O, Yb–O, and Zr–O) bond lengths within the active sites and the size of adsorbed propane molecule to be the decisive factor governing the reaction route.

Robust shape-based template matching algorithm for target localization under SEM.

A novel acceleration algorithm for geometric template matching is proposed based on the Cauchy-Schwartz inequality (C-S inequality) in this paper. The proposed approach is validated under a scanning electron microscope (SEM), and its effectiveness is demonstrated. In this approach, the object shape features are represented as column vectors with complex elements. Then, a threshold is determined to exclude the sliding windows without any matched objects. Finally, surface fitting is employed to obtain the subpixel positions of the targets, and least squares adjustment is utilized to fine-tune the obtained results. The experimental results demonstrate that the proposed method can significantly reduce the matching time by 59% - 96% compared with the traditional shape-based method. Furthermore, the strong robustness and high accuracy are verified under different disturbances. Additionally, the approach is shown to be robust and accurate under different types of disturbances, thus confirming its suitability for real-time targets tracking on SEM with high accuracy.

Precise plane registration with multiple geometric feature matching and weighted least squares estimation

Point cloud registration is a fundamental problem for 3D laser scanning technology, which is extensively applied in geographic entity modelling such as 3D reconstruction of urban roads and buildings. Registration accuracy is one of the main focuses for these applications. However, noisy points, limited overlap, varying data sources, and differing measuring accuracy may cause changes between point cloud sets and reduce registration accuracy. This paper introduces an automatic plane registration method for urban roads and building scenes, which does not need manual on-site deployment. Firstly, plane primitives are extracted using voxel-based filtering region growth. Next, corresponding planes for the extracted primitives are identified by leveraging saliency features and constructing adjacency matrices. Finally, plane registration is achieved using a weighted plane coordinate conversion model. Through real-world scene experimentation, an overall accuracy of 10 cm and a segmental registration accuracy of 5–6 cm is achieved with our method, outperforming both feature point-based and global point cloud registration approaches in terms of efficiency and accuracy.

Enhancing Occlusion Handling in Real-Time Tracking Systems through Geometric Mapping and 3D Reconstruction Validation

Object detection is a classic research problem in the area of Computer Vision. Many smart world applications, like, video surveillance or autonomous navigation systems require a high accuracy in pose detection of objects. One of the main challenges in Object detection is the problem of detecting occluded objects and its respective 3D reconstruction. The focus of this paper is inter-object occlusion where two or more objects being tracked occlude each other. A novel algorithm has been proposed for handling object occlusion by using the technique of geometric matching and its 3D projection obtained. The developed algorithm has been tested using sample data and the results are presented.

Research on a short-sleeper type ballastless-track that can adapt to large foundation deformation

Settlement and arch deformation on the ballastless-track foundation during rail transit operations pose challenges to the existing track structure, which can only accommodate up to 30 mm of foundation deformation through the replacement of fastener adjusting pads. These limitations result in prolonged remediation cycles, increased expenses, and disruptions to train runs. To address these issues, a height-adjustable short-sleeper ballastless-track structure is proposed. Using the vehicle-track coupled dynamics theory and FEM, this study investigates the geometric matching characteristics, modal behavior of the track structure and their impact on the dynamics performance of the vehicle and track system when the HSBS structure is adjusted to 200 mm. Findings demonstrate that the ballastless-track can easily adjust the height by modifying the thickness of pads or replacing the short sleepers, enabling effective adaptation to substantial track foundation deformation with an adjustment capacity exceeding 200 mm. Importantly, the vibration mode and natural frequency of the short sleeper remain unchanged before and after lifting the track structure. Under the condition of unchanged support stiffness, the stability of the track structure, as well as the safety and smooth performance of the vehicle, are maintained at the same level as before the height adjustment.

PDC-Net+: Enhanced Probabilistic Dense Correspondence Network

Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling alternative paradigm that avoids the keypoint detection step. However, dense flow estimation is often inaccurate in the case of large displacements, occlusions, or homogeneous regions. In order to apply dense methods to real-world applications, such as pose estimation, image manipulation, or 3D reconstruction, it is therefore crucial to estimate the confidence of the predicted matches. We propose the Enhanced Probabilistic Dense Correspondence Network, PDC-Net+, capable of estimating accurate dense correspondences along with a reliable confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. In particular, we parametrize the predictive distribution as a constrained mixture model, ensuring better modelling of both accurate flow predictions and outliers. Moreover, we develop an architecture and an enhanced training strategy tailored for robust and generalizable uncertainty prediction in the context of self-supervised training. Our approach obtains state-of-the-art results on multiple challenging geometric matching and optical flow datasets. We further validate the usefulness of our probabilistic confidence estimation for the tasks of pose estimation, 3D reconstruction, image-based localization, and image retrieval. Code and models are available at https://github.com/PruneTruong/DenseMatching.

A General Layout Pattern Clustering Using Geometric Matching Based Clip Relocation and Lower-Bound Aided Optimization

With the continuous shrinking of feature size, detection of lithography hotspots has been raised as one of the major concerns in Design-for-Manufacturability (DFM) of semiconductor processing. Hotspot detection, along with other DFM measures, trades off turn-around time for the yield of IC manufacturing, thus a simplified but wide-range-covered pattern definition is a key essential to the problem. Layout pattern clustering methods, which group geometrically similar layout clips into clusters, have been vastly proposed to identify layout patterns efficiently. To minimize the clustering number for subsequent DFM processing, in this paper, we propose a geometric-matching-based clip relocation technique to increase the opportunity of pattern clustering. Particularly, we formulate the lower-bound of the clustering number as a maximum-clique problem, and we have also proved that the clustering problem can be solved by the result of the maximum-clique very efficiently. Compared with the experimental results of the state-of-the-art approaches on ICCAD 2016 Contest benchmarks, the proposed method can achieve the optimal solutions for all benchmarks with very competitive run-time. To evaluate the scalability, the ICCAD 2016 Contest benchmarks are extended and evaluated. And experimental results on the extended benchmarks demonstrate that our method can reduce the cluster number by 16.59% on average, while the run-time is 74.11% faster on large-scale benchmarks compared with previous works.

Surface structured light sensor with simultaneous color mapping

To obtain geometric information and color texture simultaneously, a surface structured light sensor consisting of a monochrome camera, a color camera, and a projector is proposed. The sensor uses a color camera to acquire surface color information while using it as a geometric measurement unit and matching with the monochrome camera to obtain geometric information. Due to the Bayer array and demosaicing algorithm of the color camera, pixel RGB components are always coupled with interference from other channels. However, existing color de-crosstalk in reconstruction is merely applied to the decoupling of color composite patterns, ignoring the intensity errors present in color fringe patterns under monochrome illumination. In our sensor, de-crosstalk of monochromatic patterns is considered to guarantee the reconstruction accuracy. The high-accuracy measurement of the sensor is validated by reconstructing standard steps, yielding a mean absolute error of 0.008 mm for distance measurements. In addition, the reconstruction experiment of a terracotta warrior verifies that the proposed sensor has potential application in the digital preservation of cultural relics.

Small target location algorithm based on optimized template matching

At present, few published template matching algorithms can achieve the performance of commercial software. This paper studies and optimizes the existing geometric feature template matching algorithm, and combines it with the improved Fourier Merlin transform registration algorithm, and finally obtains a fast small target location algorithm. The matching time of the algorithm is 1-4ms, its positioning accuracy is sub-pixel level, the angle accuracy is less than 1 °, and it has good robustness to illumination. The experimental data show that the algorithm meets the requirements of real-time and accurate industrial automation production.

Paintable Bioactive Extracellular Vesicle Ink for Wound Healing

The treatment of cutaneous wounds involving complex biological processes has become a significant public health concern worldwide. Here, we developed an efficient extracellular vesicle (EV) ink to regulate the inflammatory microenvironment and promote vascular regeneration for wound healing. The technology, termed portable bioactive ink for tissue healing (PAINT), leverages bioactive M2 macrophage-derived EVs (EVM2) and a sodium alginate precursor, forming a biocompatible EV-Gel within 3 min after mixing, enabling it to be smeared on wounds in situ to meet diverse morphologies. The bioactive EVM2 reprogram macrophage polarization and promote the proliferation and migration of endothelial cells, thereby effectively regulating inflammation and enhancing angiogenesis in wounds. Through integration with a 3D printing pen, the platform enables EV-Gel to be applied to wound sites having arbitrary shapes and sizes with geometric matches for tissue repairment. When evaluated using a mouse wound model, PAINT technology accelerates cutaneous wound healing by promoting the angiogenesis of endothelial cells and the polarization of macrophages to M2 phenotype in vivo, demonstrating the high potential of bioactive EV ink as a portable biomedical platform for healthcare.

Joint estimation of position and attitude for intelligent vehicles by fusing delayed visual measurements

Accurate position and attitude information is an important basis for normal driving of intelligent vehicles. In this paper, we investigate the estimation of position and attitude states for intelligent vehicles with low cost scheme. The low cost GNSS, camera, and proprioceptive sensors equipped by mass-produced vehicle are fused to estimate the states. The visual measurements adopted in this paper are based on the lateral distance and deflection angle to road features such as lane lines or curbs, which are generated more frequently than some other semantic features such as traffic lights, and leads to broader application scenario. Moreover, it is easier to implement compared with geometrical feature matching methods, since it only needs a simple prior map while latter needs large maps containing many high precision features. The visual measurements is often with large time delay due to negligible processing time. In order to fuse delayed measurements, a state-augmentation technique is adopted for the estimator design. The performance of the proposed method is evaluated by professional simulation software CarMaker, and shows that the incorporation of road features based visual measurement can effectively improve the position and attitude estimation accuracy by reducing the lateral position and yaw angle estimation error.

Investigation on geometric throat matching characteristics of variable geometry rocket-based combined cycle combustor

One of the most effective ways to realize multi-mode and high-performance matching operation of rocket-based combined cycle (RBCC) engine is to adopt a variable geometry combustor. In this study, direct-connect experiments and three-dimensional numerical simulations were used to investigate the matching characteristics between the isolator and the geometric throat of the variable geometry rocket-based combined cycle combustor under Ma 6 condition. The influences of equivalence ratio and geometric throat height variations on the combustor matching characteristics were obtained. The study results show that: (1) The pressure in the combustor and the outlet pressure of the isolator increase gradually with the increase of equivalence ratio, which causes the pre-combustion shock train position in the isolator to move forward gradually. Meanwhile, the combined injection of secondary fuel with the isolator and the pylon is beneficial to the improvement of combustor pressure, thus further improving the engine performance. (2) Different geometric throat heights have a substantial impact on the isolator and combustor matching when the equivalent ratio of the combustor is fixed. Under the conditions of Ma 6 operating at an altitude of 24 km inflow, the starting position of the pre-combustion shock train in the isolator is precisely at the isolator entrance, and the corresponding geometric throat height is 2.10H. The isolator and the combustor can complete matching operation at this point which the geometric throat height is the minimal throat height for Equivalent ratio = 1.0. (3) The reduction in geometric throat height can result in an increase in combustor pressure but a loss in combustor heat release and combustion efficiency of fuel combustion, which are reduced by 21.1% and 7.2% respectively. (4) The heat release and combustion efficiency in the combustor will decrease with a decrease in equivalent ratio at the minimal throat height condition where the isolator and the combustor can complete matching operation. This happens when the equivalent ratio and the geometric throat height change synergistically.

General access to cubanes as benzene bioisosteres.

The replacement of benzene rings with sp3-hybridized bioisosteres in drug candidates generally improves pharmacokinetic properties while retaining biological activity1-5. Rigid, strained frameworks such as bicyclo[1.1.1]pentane and cubane are particularly well suited as the ring strain imparts high bond strength and thus metabolic stability on their C-H bonds. Cubane is the ideal bioisostere as it provides the closest geometric match to benzene6,7. At present, however, all cubanes in drug design, like almost all benzene bioisosteres, act solely as substitutes for mono- or para-substituted benzene rings1-7. This is owing to the difficulty of accessing 1,3- and 1,2-disubstituted cubane precursors. The adoption of cubane in drug design has been further hindered by the poor compatibility of cross-coupling reactions with the cubane scaffold, owing to a competing metal-catalysed valence isomerization8-11. Here we report expedient routes to 1,3- and 1,2-disubstituted cubane building blocks using a convenient cyclobutadiene precursor and a photolytic C-H carboxylation reaction, respectively. Moreover, we leverage the slow oxidative addition and rapid reductive elimination of copper to develop C-N, C-C(sp3), C-C(sp2) and C-CF3 cross-coupling protocols12,13. Our research enables facile elaboration of all cubane isomers into drug candidates, thus enabling ideal bioisosteric replacement of ortho-, meta- and para-substituted benzenes.

The Study and Application of Facial Recognition Models

Facial recognition technology is a biometric application that uniquely identifies or authenticates a person by comparing and analyzing facial features based on the width of a person's face. Face recognition technology has gained popularity recently thanks to the development and invention of artificial intelligence and other technologies. The traditional methods of face recognition technology development—the method based on geometric features and the method based on 3D models—as well as the deep learning Convolutional Neural Network (CNN) model VGG-Face for face recognition—are analyzed, compared, and described in this paper. It also provides a detailed description of face recognition technology. In this work, accuracy and TAR values are employed for geometric feature matching by comparing the metric results of each method on a dataset for better comparison. Our results show that while both traditional geometric feature modeling methods and 3D modeling methods can achieve good accuracy, however, they do not perform as well as humans in terms of accuracy. The Vgg-Face based on the deep learning model completely exceeds the 3D model method in terms of accuracy and TAR value, and is even more accurate than humans.

PR-Alignment: Multidimensional Adaptive Registration Algorithm Based on Practical Application Scenarios

In the present day, 3D point clouds are considered to be an important form of representing the 3D world. In computer vision, mobile robotics, and computer graphics, point cloud registration is a basic task, and it is widely used in 3D reconstruction, reverse engineering, among other applications. However, the mainstream method of point cloud registration is subject to the problems of a long registration time as well as a poor modeling effect, and these two factors cannot be balanced. To address this issue, we propose an adaptive registration mechanism based on a multi-dimensional analysis of practical application scenarios. Through the use of laser point clouds and RGB images, we are able to obtain geometric and photometric information, thus improving the data dimension. By adding target scene classification information to the RANSAC algorithm, combined with geometric matching and photometric matching, we are able to complete the adaptive estimation of the transformation matrix. We demonstrate via extensive experiments that our method achieves a state-of-the-art performance in terms of point cloud registration accuracy and time compared with other mainstream algorithms, striking a balance between expected performance and time cost.

Graphene Formation through Spontaneous Exfoliation of Graphite by Chlorosulfonic Acid: A DFT Study

Using exfoliating agents is one of the most promising ways for large-scale production of liquid dispersed graphenic materials from graphite. Therefore, it is crucial to know the reason why some molecules have a larger exfoliating power than others. The highest reported experimental yield for the liquid phase single-surfactant spontaneous exfoliation of graphite, i.e., without sonication, has been obtained using chlorosulfonic acid. The ability of this acid to disperse graphite is studied within the framework of Density Functional Theory (DFT). Equilibrium configurations, electron transfers, binding energies, and densities of states are presented for two acid concentrations and for two situations: adsorption (on monolayer and bilayer graphene) and intercalation (in between simple hexagonal and Bernal-stacked bilayer graphene). Experimental exfoliation power and dispersion stability are explained in terms of charge transfer—the largest found among several studied exfoliating and surfactant agents—facilitated by the good geometrical matching of chlorosulfonic acid molecules to constituent carbon rings of graphene. This matching is in the origin of the tendency toward adsorption of chlorosulfonic acid molecules on graphene monolayers when they separate, originating the charging of the monolayers that precludes their reaggregation.

DO-VTON: a details-oriented virtual try-on network

PurposeThe paper aims to transfer the item image of a given clothing product to a corresponding area of the user image. Existing classical methods suffer from unconstrained deformation of clothing and occlusion caused by hair or poses, which leads to loss of details in the try-on results. In this paper, the authors present a details-oriented virtual try-on network (DO-VTON), which allows synthesizing high-fidelity try-on images with preserved characteristics of target clothing.Design/methodology/approachThe proposed try-on network consists of three modules. The fashion parsing module (FPM) is designed to generate the parsing map of a reference person image. The geometric matching module (GMM) warps the input clothing and matches it with the torso area of the reference person guided by the parsing map. The try-on module (TOM) generates the final try-on image. In both FPM and TOM, attention mechanism is introduced to obtain sufficient features, which enhances the performance of characteristics preservation. In GMM, a two-stage coarse-to-fine training strategy with a grid regularization loss (GR loss) is employed to optimize the clothing warping.FindingsIn this paper, the authors propose a three-stage image-based virtual try-on network, DO-VTON, that aims to generate realistic try-on images with extensive characteristics preserved.Research limitations/implicationsThe authors’ proposed algorithm can provide a promising tool for image based virtual try-on.Practical implicationsThe authors’ proposed method is a technology for consumers to purchase favored clothes online and to reduce the return rate in e-commerce.Originality/valueTherefore, the authors’ proposed algorithm can provide a promising tool for image based virtual try-on.

Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence.

Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this work we introduce a Hough transform perspective on convolutional matching and propose an effective geometric matching algorithm, dubbed Convolutional Hough Matching (CHM). The method distributes similarities of candidate matches over a geometric transformation space and evaluates them in a convolutional manner. We cast it into a trainable neural layer with a semi-isotropic high-dimensional kernel, which learns non-rigid matching with a small number of interpretable parameters. To further improve the efficiency of high-dimensional voting, we also propose to use an efficient kernel decomposition with center-pivot neighbors, which significantly sparsifies the proposed semi-isotropic kernels without performance degradation. To validate the proposed techniques, we develop the neural network with CHM layers that perform convolutional matching in the space of translation and scaling. Our method sets a new state of the art on standard benchmarks for semantic visual correspondence, proving its strong robustness to challenging intra-class variations.

Hexagonal crystalline Magnus' green salt analogues prepared from hydroxy-functionalised Pt and Pd complexes.

New Magnus' green salt (MGS) analogues, [M(dabdOH)2][MCl4]·2H2O (dabdOH = (2S,3S)-2,3-diaminobutane-1,4-diol; M = Pd (1) and M = Pt(2)), in which [M(dabdOH)2]2+ and [MCl4]2- are stacked alternately to form linear chains, were obtained as hexagonal plate crystals. The hexagonal shape and large crystal size are unprecedented features as MGS analogues. An unusual trigonal grade separation of chain complexes has been revealed by the structural analysis. 1 and 2 exhibited remarkable yellow and pink colours, respectively, which are derived from weak M⋯M interactions. The dabdOH ligand, which has an additional hydrogen donor group (hydroxy group), produces a multiple-hydrogen-bond network. The combination of intrachain and interchain hydrogen bonds gives a two-dimensional (2D) hydrogen-bond sheet, and each 2D sheet is indirectly connected by hydrogen bonds via lattice water molecules. The OH-functionalised ligand greatly increases the hydrophilicity of the MGS analogues and yields the largest single crystals of all MGS analogues reported so far. The trigonal grade-separated chain structure is likely due to the geometric matching between the periodicity of chains and the short axis width of the chain. This strategy opens up new insight for preparing large crystals of MGS analogues and for constructing trigonal grade-separated nanowires in molecular crystals.