Iterative Closest Point Algorithm Research Articles

Real-time limb tracking in single depth images based on circle matching and line fitting

Modern lower limb prostheses neither measure nor incorporate healthy residual leg information for intent recognition or device control. In order to increase robustness and reduce misclassification of devices like these, we propose a vision-based solution for real-time 3D human contralateral limb tracking (CoLiTrack). An inertial measurement unit and a depth camera are placed on the side of the prosthesis. The system is capable of estimating the shank axis of the healthy leg. Initially, the 3D input is transformed into a stabilized coordinate system. By splitting the subsequent shank estimation problem into two less computationally intensive steps, the computation time is significantly reduced: First, an iterative closest point algorithm is applied to fit circular models against 2D projections. Second, the random sample consensus method is used to determine the final shank axis. In our study, three experiments were conducted to validate the static, the dynamic and the real-world performance of our CoLiTrack approach. The shank angle can be tracked at 20 Hz for one sixth of the entire human gait cycle with an angle estimation error below 2.8pm 2.1^{circ }. Our promising results demonstrate the robustness of the novel CoLiTrack approach to make “next-generation prostheses” more user-friendly, functional and safe.

An efficient LiDAR-based localization method for self-driving cars in dynamic environments

AbstractReal-time localization is an important mission for self-driving cars and it is difficult to achieve precise pose information in dynamic environments. In this paper, a novel localization method is proposed to estimate the pose of self-driving cars using a 3D-LiDAR sensor. First, the multi-frame curb features and laser intensity features are extracted. Meanwhile, based on the high-precision curb map generated offline, obstacles on road are detected using region segmentation methods and their features are removed. Furthermore, a map-matching method is proposed to match the features to the map, a robust iterative closest point algorithm is utilized to deal with curb features along with a probability search method dealing with intensity features. Finally, two separate Kalman filters are used to fuse the low-cost global positioning systems and map-matching results. Both offline and online experiments are carried out in dynamic environments and the results demonstrate the accuracy and robustness of the proposed method.

ROBUST SURFACE-MATCHING REGISTRATION BASED ON THE STRUCTURE INFORMATION FOR IMAGE-GUIDED NEUROSURGERY SYSTEM

Image-to-patient space registration is to make the accurate alignment between the actual operating space and the image space. Although the image-to-patient space registration using paired-point is used in some image-guided neurosurgery systems, the current paired-point registration method has some drawbacks and usually cannot achieve the best registration result. Therefore, surface-matching registration is proposed to solve this problem. This paper proposes a surface-matching method that accomplishes image-to-patient space registration automatically. We represent the surface point clouds by the Gaussian Mixture Model (GMM), which can smoothly approximate the probability density distribution of an arbitrary point set. We also use mutual information as the similarity measure between the point clouds and take into account the structure information of the points. To analyze the registration error, we introduce a method for the estimation of Target Registration Error (TRE) by generating simulated data. In the experiments, we used the point sets of the cranium surface and the model of the human head determined by a CT and laser scanner. The TRE was less than 2[Formula: see text]mm, and the TRE had better accuracy in the front and the posterior region. Compared to the Iterative Closest Point algorithm, the surface registration based on GMM and the structure information of the points proved superior in registration robustness and accurate implementation of image-to-patient registration.

Path Planning With Automatic Seam Extraction Over Point Cloud Models for Robotic Arc Welding

This letter presents a point cloud based robotic system for arc welding. Using hand gesture controls, the system scans partial point cloud views of workpiece and reconstructs them into a complete 3D model by a linear iterative closest point algorithm. Then, a bilateral filter is extended to denoise the workpiece model and preserve important geometrical information. To extract the welding seam from the model, a novel intensity-based algorithm is proposed that detects edge points and generates a smooth 6-DOF welding path. The methods are tested on multiple workpieces with different joint types and poses. Experimental results prove the robustness and efficiency of this robotic system on automatic path planning for welding applications.

Part point cloud segmentation method based on model registration

In order to analyze the machining errors of parts more accurately, a point cloud segmentation method based on model registration was proposed for mechanical parts. First, the surface information of the standard model of the part is extracted from the Initial Graphics Exchange Specification (IGES) file; then, the part point cloud is registered to the standard model using the method of the moment principal axis method and the Iterative Closest Point algorithm (ICP); then, by calculating the distance between each point in the point cloud and each surface in the standard model, it is used to determine the corresponding relationship between the model surface and the point cloud, and then the point cloud is segmented; finally, the segmentation results are surface-fitted and benchmarked to obtain a segmentation with better alignment quality. The experimental results show that this method can automatically segment the part point cloud according to the surface features of the part when only the IGES model and the point cloud model are input, without setting any empirical parameters, and obtain the segmentation result with clear boundaries.

Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor

To overcome the drawbacks of pairwise registration for mobile laser scanner (MLS) point clouds, such as difficulty in searching the corresponding points and inaccuracy registration matrix, a robust coarse-to-fine registration method is proposed to align different frames of MLS point clouds into a common coordinate system. The method identifies the correct corresponding point pairs from the source and target point clouds, and then calculates the transform matrix. First, the performance of a multiscale eigenvalue statistic-based descriptor with different combinations of parameters is evaluated to identify the optimal combination. Second, based on the geometric distribution of points in the neighborhood of the keypoint, a weighted covariance matrix is constructed, by which the multiscale eigenvalues are calculated as the feature description language. Third, the corresponding points between the source and target point clouds are estimated in the feature space, and the incorrect ones are eliminated via a geometric consistency constraint. Finally, the estimated corresponding point pairs are used for coarse registration. The value of coarse registration is regarded as the initial value for the iterative closest point algorithm. Subsequently, the final fine registration result is obtained. The results of the registration experiments with Autonomous Systems Lab (ASL) Datasets show that the proposed method can accurately align MLS point clouds in different frames and outperform the comparative methods.

An Experimental Study of a New Keypoint Matching Algorithm for Automatic Point Cloud Registration

Light detection and ranging (LiDAR) data systems mounted on a moving or stationary platform provide 3D point cloud data for various purposes. In applications where the interested area or object needs to be measured twice or more with a shift, precise registration of the obtained point clouds is crucial for generating a healthy model with the combination of the overlapped point clouds. Automatic registration of the point clouds in the common coordinate system using the iterative closest point (ICP) algorithm or its variants is one of the frequently applied methods in the literature, and a number of studies focus on improving the registration process algorithms for achieving better results. This study proposed and tested a different approach for automatic keypoint detecting and matching in coarse registration of the point clouds before fine registration using the ICP algorithm. In the suggested algorithm, the keypoints were matched considering their geometrical relations expressed by means of the angles and distances among them. Hence, contributing the quality improvement of the 3D model obtained through the fine registration process, which is carried out using the ICP method, was our aim. The performance of the new algorithm was assessed using the root mean square error (RMSE) of the 3D transformation in the rough alignment stage as well as a-prior and a-posterior RMSE values of the ICP algorithm. The new algorithm was also compared with the point feature histogram (PFH) descriptor and matching algorithm, accompanying two commonly used detectors. In result of the comparisons, the superiorities and disadvantages of the suggested algorithm were discussed. The measurements for the datasets employed in the experiments were carried out using scanned data of a 6 cm × 6 cm × 10 cm Aristotle sculpture in the laboratory environment, and a building facade in the outdoor as well as using the publically available Stanford bunny sculpture data. In each case study, the proposed algorithm provided satisfying performance with superior accuracy and less iteration number in the ICP process compared to the other coarse registration methods. From the point clouds where coarse registration has been made with the proposed method, the fine registration accuracies in terms of RMSE values with ICP iterations are calculated as ~0.29 cm for Aristotle and Stanford bunny sculptures, ~2.0 cm for the building facade, respectively.

Precise grabbing of overlapping objects system based on end-to-end deep neural network

In recent years, robotic arm technology is in dire need of reform because of the remarkable advances in artificial intelligence and computer vision. The traditional robotic arm techniques, e.g., template matching algorithm and iterative closest point algorithm, suffer from the low precision issue, especially when the target objects overlap with each other, resulting in inaccurate estimation of overlapping objects. This paper proposes a precise grabbing of overlapping objects system based on an end-to-end deep neural network. The successful grabbing is realized in the case of overlapping objects. First, the datasets needed for network training were established, utilizing structured light to obtain the point cloud information of the arbitrarily placed target objects. Furthermore, we collect the corresponding postures as data labels via the teaching device of the robotic arm, and train the network models using the datasets and labels. Finally, we can predict the postures of the target objects in real time and transmit the results to a robotic arm to complete the grabbing work. The experiment results indicate that the proposed grabbing system can grab small irregular objects accurately, only using the point cloud information, estimating the posture of multiple target objects in the scene simultaneously, and estimating the posture of overlapping small objects in the scene.

OICP: An Online Fast Registration Algorithm Based on Rigid Translation Applied to Wire Arc Additive Manufacturing of Mold Repair.

As promising technology with low requirements and high depositing efficiency, Wire Arc Additive Manufacturing (WAAM) can significantly reduce the repair cost and improve the formation quality of molds. To further improve the accuracy of WAAM in repairing molds, the point cloud model that expresses the spatial distribution and surface characteristics of the mold is proposed. Since the mold has a large size, it is necessary to be scanned multiple times, resulting in multiple point cloud models. The point cloud registration, such as the Iterative Closest Point (ICP) algorithm, then plays the role of merging multiple point cloud models to reconstruct a complete data model. However, using the ICP algorithm to merge large point clouds with a low-overlap area is inefficient, time-consuming, and unsatisfactory. Therefore, this paper provides the improved Offset Iterative Closest Point (OICP) algorithm, which is an online fast registration algorithm suitable for intelligent WAAM mold repair technology. The practicality and reliability of the algorithm are illustrated by the comparison results with the standard ICP algorithm and the three-coordinate measuring instrument in the Experimental Setup Section. The results are that the OICP algorithm is feasible for registrations with low overlap rates. For an overlap rate lower than 60% in our experiments, the traditional ICP algorithm failed, while the Root Mean Square (RMS) error reached 0.1 mm, and the rotation error was within 0.5 degrees, indicating the improvement of the proposed OICP algorithm.

A Comparison Method for 3D Laser Point Clouds in Displacement Change Detection for Arch Dams

Dam deformation monitoring can directly identify the safe operation state of a dam in advance, which plays an important role in dam safety management. Three-dimensional (3D) terrestrial laser scanning technology is widely used in the field of deformation monitoring due to its fast, complete, and high-density 3D data acquisition capabilities. However, 3D point clouds are characterized by rough surfaces, discrete distributions, which affect the accuracy of deformation analysis of two states data. In addition, it is impossible to directly extract the correspondence points from an irregularly distributed point cloud to unify the coordinates of the two states’ data, and the correspondence lines and planes are often difficult to obtain in the natural environment. To solve the above problems, this paper studies a displacement change detection method for arch dams based on two-step point cloud registration and contour model comparison method. In the environment around a dam, the stable rock is used as the correspondence element to improve the registration accuracy, and a two-step registration method from rough to fine using the iterative closest point algorithm is present to describe the coordinate unification of the two states’ data without control network and target. Then, to analyze the displacement variation of an arch dam surface in two states and improve the accuracy of comparing the two surfaces without being affected by the roughness of the point cloud, the contour model fitting the point clouds is used to compare the change in distance between models. Finally, the method of this paper is applied to the Xiahuikeng Arch Dam, and the displacement changes of the entire dam in different periods are visualized by comparing with the existing methods. The results show that the displacement change in the middle area of the dam is generally greater than that of the two banks, increasing with the increase in elevation, which is consistent with the displacement change behavior of the arch dam during operation and can reach millimeter-level accuracy.

Current Measurement Strategies of Coronal Tibiofemoral Subluxation: A Systematic Review of Literature.

OBJECTIVE. Coronal tibiofemoral (TF) subluxation has generated interest in the last several years due to newfound clinical implications of its presence. However, controversy within the literature concerning how to measure and calculate coronal TF subluxation on radiographic imaging remains. The purpose of this study was to describe how coronal TF subluxation is being measured and calculated in the literature with the goal of describing a reproducible and validated technique for clinical adoption. MATERIALS AND METHODS. A PubMed literature search was performed in March 2020 according to PRISMA guidelines. The terms "tibiofemoral subluxation" and "tibial femoral subluxation" were included in the search. Criteria of interest included radiographic view and evaluation, anatomic landmarks used, and measurement validity. RESULTS. Review of relevant literature resulted in 744 articles, 16 of which met our inclusion criteria. A wide range of measuring techniques, anatomic landmarks, and radiographic views were used with varying validity. Full-limb radiographic views were the most common. Six studies measured the translation of the mechanical axes of the tibia and femur. Eight studies measured the translation of either femoral condyle in reference to the tibial plateau. Coordinate-based software with the iterative closest point algorithm was used in two studies. Whether coronal TF subluxation should be divided by tibial plateau width to account for knee size was controversial. CONCLUSION. A variety of approaches exist for diagnosing and quantifying coronal TF subluxation because of the lack of clear anatomic landmarks within the TF joint that can be used to measure coronal TF subluxation in the horizontal plane. Even when using the same anatomic landmarks, studies varied on how to measure coronal TF subluxation radiographically and whether knee size should be accounted for. Further studies are necessary to standardize (via inter- and intraobserver validation with a control group) an easy, reproducible, and minimally biased approach to measuring coronal TF subluxation on radiographic imaging. We believe our systematic review succinctly provides the necessary information to either develop such a tool or encourage future studies to compare existing techniques to find the most reliable and clinically useful approach for evaluating coronal TF subluxation.

Craniofacial Reconstruction Based on Geodesic Regression Model

<p indent=0mm>Craniofacial reconstruction refers to predicting the corresponding appearance based on the characteristics of an unknown skull. In order to solve the problem of large amount of data, manual work of calibrating feature points and difficulty in defining craniofacial feature points in the process of craniofacial reconstruction, for the three-dimensional skull and skin model represented by a triangular mesh, the craniofacial model is represented by a set of geodesics which are starting from the tip of a nose, thereby craniofacial reconstruction method based on geodesic regression is proposed. First, a set of geodesics is extracted from the nose tip point of the 3D face model; then the skull and the geodesics extracted from the corresponding face model are used as training samples, and the partial least square regression statistical model is used to reconstruct geodesics corresponding to the unknown skull; Finally, the iterative closest point algorithm is used to match the geodesics generated by the geodesic regression method with the facial statistical model to reconstruct the face of the test skull. Craniofacial reconstruction experiments have been conducted on 192 sets of craniofacial data. The reconstruction results based on geodesic regression were compared with the reconstruction results of principal component analysis and partial least squares regression. The experimental results showed that our method can improve the reconstruction accuracy, reduce the reconstruction time, and achieve a good reconstruction effect.

Assessment of reference areas for superimposition of serial 3D models of patients with advanced periodontitis for volumetric soft tissue evaluation

This study aimed to determine the optimal reference area for superimposition of serial 3D dental models of patients with advanced periodontitis. Ten pre- and post-periodontal treatment 3D models (median time lapse: 13.1months) of patients with advanced periodontitis were acquired by intraoral scanning. Superimposition was performed with the iterative closest point algorithm using four reference areas: (A) all stable teeth, (B) all teeth, (C) third palatal rugae and (D) the whole model. The superimposition accuracy was evaluated at two stable evaluation regions using the mean absolute distance and evaluated with two-way ANOVA and post-hoc multivariate model. The intra- and inter-operator reproducibility was calculated by intraclass correlation coefficient (ICC). Superimposition accuracy evaluated at stable tooth evaluation region were 71±29μm, 73±21μm, 127±52μm and 113±53μm for areas A, B, C and D, respectively. All reference areas showed similarly high ICC values >0.990, except for reference area C showing ICC of 0.821 (intra-operator) and 0.767 (inter-operator) for tooth evaluation area. Area A and B provide the highest accuracy for superimposition of serial 3D dental models acquired by intraoral scanning of patients with advanced periodontitis.

Surgical navigation system for brachytherapy based on mixed reality using a novel stereo registration method

In this study, we present a novel mixed reality navigation system to facilitate brachytherapy, which is an effective method for curing cancer. The accuracy of needle positioning is a vital problem in brachytherapy that can influence the treatment effect. The purpose of the developed system is to help doctors more quickly and easily position the needles and improve seed accuracy in brachytherapy surgery. Based on mixed reality and a multi-information fusion method, a successful fusion of medical images and a preoperative plan for real patients was achieved, allowing doctors to gain an intuitive understanding of the tumor. Image recognition and pose estimation were used to track the needle punctures in real time and perform registration processes. After global registration using an iterative closest-point algorithm with a pattern tracker, medical images and volume renderings of organs, needles and seeds were aligned with the patient. Based on a phantom experiment, the average needle location error was 0.961 mm, and the angle error was 1.861°. The accuracy of needle insertion was 1.586 mm, and the angle error was 2.429°. This research presents the design and validation of a surgical navigation system for thoracoabdominal brachytherapy based on mixed reality. The proposed system was validated through both phantom and animal experiments. The results indicated that the proposed system achieves clinically acceptable accuracy and can aid doctors in performing surgery based on a visualized plan.

Robust wavefront segment registration based on a parallel approach.

This paper presents a robust registration algorithm for wavefront reconstruction from multiple partial measurements. Wavefronts exceeding the dynamic range or size of the Shack-Hartmann sensor can be measured as a set of segments. The wavefront is reconstructed by parallel registration of these wavefront segments, enabling compensation for sensor misalignment as well as for phase differences. For registration, a global mismatch metric is minimized by rigid body transformations and propagation of the wavefront segments. Apart from the description of the algorithm, a simulation-based evaluation and comparison to the iterative closest point (ICP) algorithm is performed. It is shown that in the case of a noisy data set, the parallel approach enables reconstruction errors that are a factor of 10 smaller than the result obtained with the ICP algorithm.

High-precision visual localization based on an improved shape-based matching algorithm.

To deal with the requirement of high-precision localization of large-size workpieces in an industrial environment, an improved shape-based matching algorithm is proposed based on the phase stretching transformation and the iterative closest point algorithms. Basler industrial cameras are used to collect images of large-size workpieces, such as glass. The experimental results show that the average localization error is 0.05±0.013mm, which can meet the requirements of practical applications. This algorithm can effectively and accurately achieve high-precision localization of different positions of multi-directionally transformed objects in industrial environments.

An efficient method for reflective surface scanning using Kinect v2

ToF cameras, also identified as range imaging cameras, are a recent generation of sensors. As they are desirable for measuring distances to objects at a high frame rate, such sensors are increasingly used for 3D acquisitions, and more generally for applications in robotics or reverse engineering. In this study, the authors presented an efficient method for reflective surface scanning using Kinect v2. The approach is based on the principles of the ICP (Iterative Closest Point) algorithm. During the Kinect v2 scanning, the obtained point cloud is incomplete and includes flying pixels. The authors solve the flying pixel problem by capturing point clouds as multiple viewpoints. Each point cloud belongs to each coordinate. Then, all of the point clouds must be aligned and combined using the ICP algorithm. The experimental results show that the quality of the method is significantly improved.

A Tracking Registration Method for Augmented Reality Based on Multi-modal Template Matching and Point Clouds

In order to overcome the defects where the surface of the object lacks sufficient texture features and the algorithm cannot meet the real-time requirements of augmented reality, a markerless augmented reality tracking registration method based on multi-modal template matching and point clouds is proposed. The method first adapts the linear parallel multi-modal LineMod template matching method with scale invariance to identify the texture-less target and obtain the reference image as the key frame that is most similar to the current perspective. Then, we can obtain the initial pose of the camera and solve the problem of re-initialization because of tracking registration interruption. A point cloud-based method is used to calculate the precise pose of the camera in real time. In order to solve the problem that the traditional iterative closest point (ICP) algorithm cannot meet the real-time requirements of the system, Kd-tree (k-dimensional tree) is used under the graphics processing unit (GPU) to replace the part of finding the nearest points in the original ICP algorithm to improve the speed of tracking registration. At the same time, the random sample consensus (RANSAC) algorithm is used to remove the error point pairs to improve the accuracy of the algorithm. The results show that the proposed tracking registration method has good real-time performance and robustness.

An automatic method for the measurement of coarse particle movement in a mountain riverbed

In this paper, we propose an automatic approach that is able to recognize the corresponding particles in multi-temporal point clouds and to determine 3D displacement vectors and the rotation parameters between them. The core of this method is a moving window approach combined with the Iterative Closest Point (ICP) algorithm. The particle-wise ICP algorithm is supplemented by initial transformation parameters obtained by key point matching. The routine is designed to be applied to natural objects, which are characterized by their complex geometry. The method’s performance is verified using terrestrial laser scanning data sets representing a mountain riverbed. The experiments performed show that the method enables us to recognize corresponding particles with an effectiveness of 85%. The mean absolute distances between the tile of a point cloud and the particle after alignment are used as the accuracy of the alignment. The median of these values is equal to 2 mm.

The evaluation of profile errors of the leading and trailing edges of a thin-walled blade based on chord length deviation

The shape of leading and trailing edges (LTEs) of a thin-walled blade is one of the key parameters that influence the performance of an aero-engine, and an exact evaluation of the shape is the basis to ensure machining quality. When the chord length of a blade is deviated, the actual position of LTEs deviates from the theoretical curve. However, considering the problem that chord length deviation couples with profile errors of LTEs, the deviation is introduced into the evaluation of profile errors with the standard iterative closest point (ICP) algorithm, which results in an inexact evaluation and affects the performance of the aero-engine. To address this issue, a novel method that exactly evaluates profile errors of LTEs is proposed. Firstly, a data pre-transformation function is introduced into the standard ICP algorithm to separate the relationship between the chord length deviation and profile errors of LTEs. Secondly, a data preprocessing optimization model is established with the constraints of chord length tolerance and camber curve, which can ensure the trend of the blade and the continuity of measuring data. Thirdly, the model is solved by the particle swarm optimization (PSO) algorithm. Finally, this method is applied to the evaluation of profile errors of LTEs of an open blisk using simulation and experimental data to verify its availability. The results show that the proposed method can eliminate the adverse effect of chord length deviation and realize the exact evaluation of the profile errors of LTEs.