Landmark constrained genus-one surface Teichmüller map applied to surface registration in medical imaging.

In shape analysis, finding an optimal 1-1 correspondence between surfaces within a large class of admissible bijective mappings is of great importance. Such process is called surface registration. The difficulty lies in the fact that the space of all surface diffeomorphisms is a complicated functional space, making exhaustive search for the best mapping challenging. To tackle this problem, we propose a simple representation of bijective surface maps using Beltrami coefficients (BCs), which are complex-valued functions defined on surfaces with supreme norm less than 1. Fixing any 3 points on a pair of surfaces, there is a 1-1 correspondence between the set of surface diffeomorphisms between them and the set of BCs. Hence, every bijective surface map can be represented by a unique BC. Conversely, given a BC, we can reconstruct the unique surface map associated to it using the Beltrami Holomorphic flow (BHF) method. Using BCs to represent surface maps is advantageous because it is a much simpler functional space, which captures many essential features of a surface map. By adjusting BCs, we equivalently adjust surface diffeomorphisms to obtain the optimal map with desired properties. More specifically, BHF gives us the variation of the associated map under the variation of BC. Using this, a variational problem over the space of surface diffeomorphisms can be easily reformulated into a variational problem over the space of BCs. This makes the minimization procedure much easier. More importantly, the diffeomorphic property is always preserved. We test our method on synthetic examples and real medical applications. Experimental results demonstrate the effectiveness of our proposed algorithm for surface registration.

Point set augmentation through fitting for enhanced ICP registration of point clouds in multisensor coordinate metrology

Laser three-dimensional (3D) image is a novel non-cooperative target 3D image acquisition technology, and the improvements in detection capability and imaging accuracy of the system are critically dependent on efficient echo-signal processing technique and 3D reconstruction method. The registration process is an essential step in array 3D imaging laser point cloud data processing. Registration of point clouds is an effective method that solves the problem caused by the target self-occlusion in the laser 3D imaging system. The accurate registration result will help provide better support for subsequent applications, such as object reconstruction and target recognition. In this study, a set of thresholds in the iterative closest point (ICP) algorithm is analysed on the basis of the characteristics of the laser array 3D imaging system and is combined with the range error and visual lateral resolution of the system, which are both important parameters in the imaging system. To improve the accuracy and speed of registration, the stop threshold of the iterative algorithm and the corresponding point-distance threshold in the algorithm are established in a novel way based on the range error and visual lateral resolution of the system. This forms the foundation, based on which an adaptive threshold ICP algorithm is proposed. The principal idea of the algorithm is to improve the threshold set that has a considerable effect on the accuracy and speed of registration. At first, the characteristics of the imaging point clouds of the laser array 3D imaging system are analysed in the algorithm. Based on this analysis, the distance between the two point clouds and corresponding points with ideal registrations are estimated theoretically, according to the range error and visual lateral resolution of the system. The simulation results show that the theoretically estimated results and actual results have the same variation tendency, thus providing a theoretical basis for subsequent improvements. Next, the estimated results are added according to the iterative closest point algorithm. This implies that the registration thresholds are capable of changing and adapting under different iterations and imaging systems, thus improving the speed and accuracy of registrations. This phenomenon is not seen in other algorithms. Experiments involving laser array imaging of a point cloud and laser scanning of depth imaging data show that the algorithm is practical and effective for both imaging types of point clouds and can improve the speed and accuracy of registration notably. The effectiveness and feasibility of the proposed algorithm are thus verified. In addition, for its full consideration of the imaging system, the basic idea of the proposed algorithm can be used for designing future applications as required.

The purpose of this study was to develop a customized framework for evaluating the registration accuracy of four registration techniques and measuring the untouched surface area of canal instrumentation by visually inspecting and calculating the overlapping area of the surfaces. Twenty-one mandibular incisors were scanned by micro-computed tomography before and after instrumentation. Elastix registration, surface registration, manual registration, and DataViewer registration techniques were used to align the pre- and post-operative datasets. The customized MeVisLab framework was created to investigate the registration accuracy by visual inspection and calculating overlapping areas. The canal surfaces were imported into the same framework to measure the untouched surface area and the consistence test was validated. The correlation between registration accuracy and untouched surface area was analyzed. There is a statistically significant difference between manual registration and automatic registration (P < 0.05). There is no statistical difference between the two untouched surface measure methods (P > 0.05). The partial correlation coefficients for the untouched surface area and registration accuracy were 0.45 (P < 0.05). This application framework based on free customizable software, allows a new method to measure registration accuracy and untouched surface area in an efficient and sensitive way. The application of a precise registration method would improve the quality of micro-CT canal instrumentation studies. This study developed a customized framework based on free software for evaluating the registration accuracy of different registration techniques and measuring the untouched surface area of canal instrumentation could help researchers to improve the quality of micro-CT studies of canal instrumentation.

It is required to use a stereotactic frame on a patient's crainial surface to access an intracerebral hematoma in conventional ICH (Intracerebral Hemorrhage) removal surgery. Since ICH using a stereotactic frame is an invasive procedure and also takes a long time, we attempt to develop a robotic ICH removal procedure with a markerless registration system using an optical 3-D scanner. Preoperative planning is performed using a patient's CT (Computed Tomography) images, which include the patient's 3-D geometrical information on the hematoma and internal structures of brain. To register the preplanned data and the intraoperative patient's data, the patient's facial surface is scanned by an optical 3-D scanner on the bed in the operating room. The intraoperatively scanned facial surface is registered to the pose of the patient's preoperative facial surface. The conventional ICP (Iterative Closest Point) algorithm can be used for the registration. In this paper, we propose a weighted ICP in order to improve the accuracy of the registration results. We investigated facial regions that can be used as anatomical landmarks. The facial regions for the landmarks in the preoperative 3-D model are weighted for more accurate registration. We increase weights at the relatively undeformed facial regions, and decrease weights at the other regions. As a result, more accurate and robust registration can be achieved from the preoperative data even with local facial shape changes.

The registration of point clouds in a three-dimensional space is an important task in many areas of computer vision, including robotics and autonomous driving. The purpose of registration is to find a rigid geometric transformation to align two point clouds. The registration problem can be affected by noise and partiality (two point clouds only have a partial overlap). The Iterative Closed Point (ICP) algorithm is a common method for solving the registration problem. Recently, artificial neural networks have begun to be used in the registration of point clouds. The drawback of ICP and other registration algorithms is the possible convergence to a local minimum. Thus, an important characteristic of a registration algorithm is the ability to avoid local minima. In this paper, we propose an ICP-type registration algorithm (λ-ICP) that uses a multiparameter functional (λ-functional). The proposed λ-ICP algorithm generalizes the NICP algorithm (normal ICP). The application of the λ-functional requires a consistent choice of the eigenvectors of the covariance matrix of two point clouds. The paper also proposes an algorithm for choosing the directions of eigenvectors. The performance of the proposed λ-ICP algorithm is compared with that of a standard point-to-point ICP and neural network Deep Closest Points (DCP).

This paper proposes a new iterative closest point approach based on correntropy with feature guided. Iterative Closest Point (ICP) algorithm can deal with most rigid registration problems, but for point sets with lots of noise and outliers, ICP cannot achieve high precision. We introduce correntropy into ICP to handle this problem by suppressing the influence of the noise and outliers. In terms of point sets contain a large proportion of planes or a curved surface, and have single structure, such as a three-dimensional model of upper jaw, we propose a feature-guided model to solve the oral data registration problem, which uses both the feature and the original data to participate in the registration, but with different weights. Our method mainly deals with the point set registration which has single structure and contains outliers. Experimental results demonstrate that the proposed algorithm is precise and robust.

PurposeA fast and accurate intraoperative registration method is important for Computer-Aided Orthopedic Surgery (CAOS). A-mode ultrasound (US) is able to acquire bone surface data in a non-invasive manner. To utilize A-mode US in CAOS, a suitable registration algorithm is necessary with a small number of registration points and the presence of measurement errors. Therefore, we investigated the effects of (1) the number of registration points and (2) the Ultrasound Point Localization Error (UPLE) on the overall registration accuracy.MethodsWe proposed a new registration method (ICP-PS), including the Iterative Closest Points (ICP) algorithm and a Perturbation Search algorithm. This method enables to avoid getting stuck in the local minimum of ICP iterations and to find the adjacent global minimum. This registration method was subsequently validated in a numerical simulation and a cadaveric experiment using a 3D-tracked A-mode US system.ResultsThe results showed that ICP-PS outperformed the standard ICP algorithm. The registration accuracy improved with the addition of ultrasound registration points. In the numerical simulation, for 25 sample points with zero UPLE, the averaged registration error of ICP-PS reached 0.25 mm, while 1.71 mm for ICP, decreasing by 85.38%. In the cadaver experiment, using 25 registration points, ICP-PS achieved an RMSE of 2.81 mm relative to 5.84 mm for the ICP, decreasing by 51.88%.ConclusionsThe simulation approach provided a well-defined framework for estimating the necessary number of ultrasound registration points and acceptable level of UPLE for a given required level of accuracy for intraoperative registration in CAOS. ICP-PS method is suitable for A-mode US based intraoperative registration. This study would facilitate the application of A-mode US probe in registering the point cloud to a known shape model, which also has the potential for accurately estimating bone position and orientation for skeletal motion tracking and surgical navigation.

Localization and mapping are key requirements for autonomous mobile systems to perform navigation and interaction tasks. Iterative Closest Point (ICP) is widely applied for LiDAR scan-matching in the robotic community. In addition, the standard ICP algorithm only considers geometric information when iteratively searching for the nearest point. However, ICP individually cannot achieve accurate point-cloud registration performance in challenging environments such as dynamic environments and highways. Moreover, the computation of searching for the closest points is an expensive step in the ICP algorithm, which is limited to meet real-time requirements, especially when dealing with large-scale point-cloud data. In this paper, we propose a segment-based scan-matching framework for six degree-of-freedom pose estimation and mapping. The LiDAR generates a large number of ground points when scanning, but many of these points are useless and increase the burden of subsequent processing. To address this problem, we first apply an image-based ground-point extraction method to filter out noise and ground points. The point cloud after removing the ground points is then segmented into disjoint sets. After this step, a standard point-to-point ICP is applied into to calculate the six degree-of-freedom transformation between consecutive scans. Furthermore, once closed loops are detected in the environment, a 6D graph-optimization algorithm for global relaxation (6D simultaneous localization and mapping (SLAM)) is employed. Experiments based on publicly available KITTI datasets show that our method requires less runtime while at the same time achieves higher pose estimation accuracy compared with the standard ICP method and its variants.

Advances in 3D imaging have recently made 3D surface scanners, capable of capturing textured surfaces at video rate, affordable and common in computer vision. This is a relatively new source of data, the potential of which has not yet been fully exploited as the problem of non-rigid registration of surfaces is difficult. While registration based on shape alone has been an active research area for some time, the problem of registering surfaces based on texture information has not been addressed in a principled way. We propose a novel, efficient and reliable, fully automatic method for performing groupwise non-rigid registration of textured surfaces, such as those obtained with 3D scanners. We demonstrate the robustness of our approach on 3D scans of human faces, including the notoriously difficult case of inter-subject registration. We show how our method can be used to build high-quality 3D models of appearance fully automatically.

With the rapid development of binocular reconstruction, fringe projection profilometry, and time of flight, 3D imaging technology has been widely applied in the field of 3D measurement. However, due to limited measurement range and self-occlusion, point cloud registration methods are often used to obtain larger or more complete 3D contours. Although many scholars have proposed various point cloud registration methods, the accuracy and efficiency of point cloud registration still need to be further improved, especially for point clouds with different density or non-rigid transformation. Image registration technology based on image correlation has been developed for many years and has achieved great success in fields such as computer vision, photomechanics, and photogrammetry. Therefore, a simple and direct idea in this paper is to transform the point cloud registration problem into volume image correlation problem. By this, an efficient image registration method based on fast Fourier transform and an inverse compositional Gaussian Newton optimization method that only needs to calculate the Hessian matrix once can be introduced into the point cloud registration field, which can greatly improve the speed and accuracy of point cloud registration. Comparative experiments have shown that our method has doubled the accuracy and efficiency compared to the iterative closest point (ICP) method, and its practicality has also been verified in impeller reconstruction experiments.

Airborne light detection and ranging (LiDAR) data are increasingly used in various fields such as topographic mapping, urban planning, and emergency management. A necessary processing step in the application of airborne LiDAR data is the elimination of mismatch errors. This paper proposes a new method for airborne LiDAR strip adjustment based on point clouds with planar neighborhoods; this method is intended to eliminate errors in airborne LiDAR point clouds. Initially, standard pre-processing tasks such as denoising, ground separation, and resampling are performed on the airborne LiDAR point clouds. Subsequently, this paper introduces a unique approach to extract point clouds with planar neighborhoods which is designed to enhance the registration accuracy of the iterative closest point (ICP) algorithm within the context of airborne LiDAR point clouds. Following the registration of the point clouds using the ICP algorithm, tie points are extracted via a point-to-plane projection method. Finally, a strip adjustment calculation is executed using the extracted tie points, in accordance with the strip adjustment equation for airborne LiDAR point clouds that was derived in this study. Three sets of airborne LiDAR point cloud data were utilized in the experiment outlined in this paper. The results indicate that the proposed strip adjustment method can effectively eliminate mismatch errors in airborne LiDAR point clouds, achieving a registration accuracy and absolute accuracy of 0.05 m. Furthermore, this method’s processing efficiency was more than five times higher than that of traditional methods such as ICP and LS3D.

As a fundamental process of three-dimensional lidar point cloud data (3D LPCD) processing, numerous registration methods are time consuming and easily fall into local optimum. A 3D LPCD registration method based on the iterative closest point (ICP) algorithm, which is improved by the Gaussian mixture model (GMM) considering corner features, is proposed in this article to address these limitations. The GMM method is used for coarse registration, and the input original 3D LPCD is replaced by corner features extracted by the improved 3D Harris algorithm to improve the efficiency of coarse registration. In addition, a satisfactory initial position between the reference and the moving 3D LPCD is prepared for ICP fine registration by coarse registration; thus, the accuracy of fine registration can be improved. The registration accuracy and efficiency of the new method is proved to be higher than those of four common ICP-based registration methods (3DSC-RANSACICP, 3DSC-SAC-IAICP, FPFH-RANSACICP, and FPFH-SAC-IAICP), and GMM registration methods, and the local optimum problem is effectively addressed.

<title>Abstract</title> Wheels are critical components of railway vehicles, and the dynamic measurement of wheel parameters is of paramount importance for the safe operation of trains.To enhance the matching accuracy in the existing dynamic measurement processes for train wheel parameters, this paper proposes an improved point cloud registration algorithm based on key point fusion of the Super-4PCS(Super Four-Points Congruent Sets) and ICP (Iterative Closest Point) algorithm. Firstly, point cloud filtering and normal estimation are performed on the wheel point cloud data to obtain source and target point clouds with normal information. Subsequently, the ISS algorithm is employed to extract key points, and the FPFH(Fast Point Feature Histograms) point cloud feature descriptor is utilized to characterize the extracted key points. Then, a two-level registration strategy is used to improve registration accuracy, in which the Super-4PCS algorithm is applied for primary coarse registration and the ICP algorithm is used for the secondary fine registration, respectively. Finally, the experiment is conducted to validate the proposed algorithm and the performance of the algorithm is further comparative analyzed through the listed registration evaluation metrics. Experimental results demonstrate that the proposed algorithm exhibits significant improvements in registration accuracy and robustness for wheel point cloud data compared to the traditional algorithms.

This paper presents a novel method for pair-wise range image registration, a backbone task in world modeling, parts inspection and manufacture, object recognition, pose estimation, robotic navigation, and reverse engineering. The method finds the most suitable homogeneous transformation matrix between two constructed range images to create a more complete 3D view of a scene. The proposed solution integrates a ray casting-based fitness estimation with a global optimization method called improved self-adaptive differential evolution. This method eliminates the fine registration steps of the well-known iterative closest point (ICP) algorithm used in previously proposed methods, and thus, is the first direct global registration algorithm. With its parallel implementation potential, the ray casting-based algorithm speeds up the fitness calculation for the global optimization method, which effectively exploits the search space to find the best transformation solution. The integration was successfully implemented in a parallel paradigm on a multi-core computer processor to solve a simultaneous 3D localization problem. The fast, accurate, and robust results show that the proposed algorithm significantly improves on the registration problem over state-of-the-art algorithms.