Global Registration Research Articles

Practical semiautomatic global registration of multiple point clouds based on semidefinite programming

Multiple point clouds registration is a prerequisite step for geometry object observation from multiple viewpoints. Most algorithms depend on pose graph or relative poses, and they make the results ambiguous and inconsistent with the original point clouds. However, the existing algorithms based on original data can almost exclusively be applied to simulated data. In this paper, a practical semiautomatic global registration algorithm is proposed. A objective function is proposed; it utilizes correspondences between point cloud pairs directly to describe this problem, making the algorithm easy to interface with other point cloud matching algorithms. Moreover, it can be effectively approximated by semidefinite programming. Since no automatic algorithm can guarantee the correctness of the correspondences, a manual strategy is proposed to filter the correspondences and find the correlation between point clouds. Based on the correlation, irrelevant point clouds can be removed easily in the point cloud set or divide the set into multiple independent parts. Besides, a postprocessing strategy based on the correlation is proposed for refining the results. The qualitative and quantitative experimental results demonstrate that the approach achieves more accurate and robust performance than previous algorithms.

Solution of Spatial Transformation Relationship of Similar Ruled Surfaces Based on Registration of Divided Regions

Since the geometric transformation relationship of similar surfaces with complex features, such as local deformation and curvature changes, is hard to be solved through global registration, this paper proposes a method for solving the spatial transformation relationship of similar ruled surfaces based on registration of divided regions. First, an adaptive region division algorithm is proposed to divide similar surfaces, and then, an improved registration algorithm is proposed by adding two constraints which are the curvature feature and differential geometric features of point clouds. Through this improved registration algorithm, the geometric transformation relationship of each sub-region can be solved, and then the spatial geometric transformation relationship of the overall similar surface can be established. Moreover, the improved registration algorithm can ensure that the differential geometric properties of corresponding points are similar after registration, which may provide a basis for mapping and reuse of process knowledge between corresponding points on similar surfaces. Finally, two similar ruled surface blades are taken as examples for simulation verification, the results show that the maximum registration error of each sub-region is 0.025 mm, which is within the allowable error range, and the registration speed of the proposed algorithm is better than the S-ICP algorithm. This proves that the method in this paper is feasible and effective.

A High-Resolution Remote Sensing Image Registration Method Combining Object and Point Features

Point feature-based (PFB) remote sensing image registration methods have achieved great accomplishments. However, such methods based on the hand-crafted point features (HCPFs) have encountered limitations of robustness, accuracy, efficiency, and automation for high-resolution remote sensing (HRRS) image registration. A two-stage registration framework specialized for HRRS images, which combines object and point features is introduced in this article. Specifically, in the first stage, we propose to abstract and represent the macroscopic semantic objects in HRRS images as the deep convolutional object features (DCOFs), which is used to implement the global coarse registration. In the second stage, specific local areas are selected according to the DCOF matching, and the PFB method is performed in the local areas to achieve refinement. The salient points of this proposal include that, 1) the proposed DCOF is more discriminative and expressive than the HCPF at the macroscopic scale so as to effectively achieve automatic and robust global preregistration. 2) We implement the object feature extraction in an object detection fashion which is more-or-less plug and play. 3) Our designed two-stage strategy plays to the advantages of the DCOF and HCPF in different scenarios, thereby improving accuracy and efficiency. Finally, experiments demonstrate the effectiveness of our method. Compared with the state-of-the-art PFB methods, it improves the accuracy by about 3$\%$–6$\%$ and the efficiency by about 15$\%$–30$\%$.

Progressive 3D biomedical image registration network based on deep self-calibration.

Three dimensional deformable image registration (DIR) is a key enabling technique in building digital neuronal atlases of the brain, which can model the local non-linear deformation between a pair of biomedical images and align the anatomical structures of different samples into one spatial coordinate system. And thus, the DIR is always conducted following a preprocessing of global linear registration to remove the large global deformations. However, imperfect preprocessing may leave some large non-linear deformations that cannot be handled well by existing DIR methods. The recently proposed cascaded registration network gives a primary solution to deal with such large non-linear deformations, but still suffers from loss of image details caused by continuous interpolation (information loss problem). In this article, a progressive image registration strategy based on deep self-calibration is proposed to deal with the large non-linear deformations without causing information loss and introducing additional parameters. More importantly, we also propose a novel hierarchical registration strategy to quickly achieve accurate multi-scale progressive registration. In addition, our method can implicitly and reasonably implement dynamic dataset augmentation. We have evaluated the proposed method on both optical and MRI image datasets with obtaining promising results, which demonstrate the superior performance of the proposed method over several other state-of-the-art approaches for deformable image registration.

Numerical Approach to Facial Palsy Using a Novel Registration Method with 3D Facial Landmark.

Treatment of facial palsy is essential because neglecting this disorder can lead to serious sequelae and further damage. For an objective evaluation and consistent rehabilitation training program of facial palsy patients, a clinician’s evaluation must be simultaneously performed alongside quantitative evaluation. Recent research has evaluated facial palsy using 68 facial landmarks as features. However, facial palsy has numerous features, whereas existing studies use relatively few landmarks; moreover, they do not confirm the degree of improvement in the patient. In addition, as the face of a normal person is not perfectly symmetrical, it must be compared with previous images taken at a different time. Therefore, we introduce three methods to numerically approach measuring the degree of facial palsy after extracting 478 3D facial landmarks from 2D RGB images taken at different times. The proposed numerical approach performs registration to compare the same facial palsy patients at different times. We scale landmarks by performing scale matching before global registration. After scale matching, coarse registration is performed with global registration. Point-to-plane ICP is performed using the transformation matrix obtained from global registration as the initial matrix. After registration, the distance symmetry, angular symmetry, and amount of landmark movement are calculated for the left and right sides of the face. The degree of facial palsy at a certain point in time can be approached numerically and can be compared with the degree of palsy at other times. For the same facial expressions, the degree of facial palsy at different times can be measured through distance and angle symmetry. For different facial expressions, the simultaneous degree of facial palsy in the left and right sides can be compared through the amount of landmark movement. Through experiments, the proposed method was tested using the facial palsy patient database at different times. The experiments involved clinicians and confirmed that using the proposed numerical approach can help assess the progression of facial palsy.

Purchase intention in the Italian e-mobility market

The low diffusion of EVs, which account for only 4.2% of the global registrations, has pushed scholars’ interest in uncovering the factors involved when purchasing these vehicles. Based on the theory of planned behavior (TPB), this study performs an exploratory analysis of the factors influencing EV purchase intention of a representative sample of the Italian population (N = 1100). Data are collected through an online questionnaire composed as of the following: 33 items are derived from TPB, 20 concern mobility habits, 8 EV knowledge, and the remaining are socio-demographic variables. The last item measures the EV purchase intention. Data concerning TPB and mobility habits are reduced through two factor analyses. The first analysis reveals four components: pleasantness, traditional driving habits, environmental concern, and perceived purchase control. The second reveals three components: autonomous transport, non-autonomous transport, and walking versus driving the car. For EV knowledge, the mean score is calculated. Then a hierarchical multiple regression analysis shows that EV purchase intention is widely predicted by pleasantness, followed by environmental concern, perceived purchase control, and, to a less extent, autonomous transport, while it is negatively affected by traditional driving habits and EV knowledge. These findings reveal that EV purchase intention in the Italian e-mobility market is essentially driven by beliefs and attitudes, but is hindered by a reluctance to leave traditional driving habits and an increasing knowledge of EVs, entailing presumably that of their unresolved problems, such as the high purchase cost, the limited range, and the poor infrastructure. Demographic variables do not affect the EV purchase intention. Suggestions are provided to policy makers and car manufacturers to sustain the EV uptake.

A landmark-free approach for automatic, dense and robust correspondence of 3D faces

Global dense registration of 3D faces commonly prioritizes correspondences of facial landmarks which are fiducial points for the anatomical structures. However, it is not always easy to pre-annotate the landmarks accurately in raw scans of 3D faces. Contrary to the current state-of-the-art in dense 3D face correspondence, we propose a general framework without pre-annotated landmarks, which promotes its robustness and allows the meshes to deform in a uniform manner. The proposed framework includes two stages: first the correspondences are established using a template face; and then we select some well-reconstructed samples to build a prior model and leverage it into the correspondence process of other samples. In both stages, the dense registration is revisited in two perspectives: semantic and topological correspondence. In the latter stage, we further incorporate shape and normal statistics of 3D faces to regularize the correspondence process for more robust results. This provides a feasible way to handle data with noises and occlusions, as well as large deformation caused by facial expressions. Our basic idea is to gradually refine the correspondence of individual points in a way global-to-local. At the same time, we solve the local-to-global deformation based on the refined correspondences. The two processes are alternated, and aided by some confidence checks for each individual points. In the experiments, the proposed method is evaluated both qualitatively and quantitatively on three datasets including two publicly available ones: FRGC v2.0 and BU-3DFE datasets, demonstrating its effectiveness.

Next Step in Incretin-Based Therapy: From Single to Dual Agonism

The twin epidemics of Type 2 diabetes (T2D) and obesity will continue to bring significant health challenges in the coming decades. Randomised controlled trials of glucagon-like peptide 1 (GLP-1)-based therapies showed high glycaemic efficacy with clinically meaningful weight loss, and have been considered as game-changers in the diabesity population. Emerging evidence has demonstrated that co-administration of glucose-dependent insulinotropic peptide (GIP) and GLP-1 results in enhanced insulinotropic effect in an additive way with significant glucagonostatic response, compared with the administration of each hormone separately. These findings have driven the choice to pursue incretin-based dual agonist therapies, known as ‘twincretin’. Observations from the global registration Phase III trials suggest that tirzepatide (a novel dual GIP/GLP-1 receptor agonist) represent advancement over current GLP-1 analogues, providing enhanced glycaemic and weight benefits with similar gastrointestinal tolerability. However, data are limited from patients with a range of ethnicities, and several questions remain unanswered.

Global optimization point-set registration based on translation/rotation decoupling for image-guided surgery applications.

In image-guided surgery systems, image-to-patient spatial registration is to get the spatial transformation between the image space and the actual operating space. Although the image-to-patient spatial registration methods using paired point or surface matching are used in some image-guided neurosurgery systems, the key problem is that the global optimization registration result cannot be achieved. Therefore, this paper proposes a new rotation invariant feature for decoupling rotation and translation space, based on which global optimization point set registration method is proposed. The new rotation invariant features, constructed based on the edges and the angles, are the rotation invariant, which has high feature resolution. Some of them are not only the rotation invariant, but also the translation invariant. To obtain the global optimal solution, branch and bound search strategy is used to search the parameter space of the translation and the computational cost is reduced simultaneously. The registration accuracy of the spatial registration method is analyzed by comparing the difference between the estimated transform and the standard transform to calculate the registration error. To validate the performance of the spatial registration method proposed, the registration performance was analyzed by comparing the experimental results with the results of the two mainstream registration methods (the iterative closest point [ICP] registration method and the coherent point drift method). In the experiments, the comparison was based on the registration accuracy and the execution time. We show our registration method can obtain higher accuracy in a shorter time in most cases. At the same time, when using ICP to further refine our results, the ICP method can converge in a very short time, which also shows that our method provides a good initial pose for the ICP method and can help the ICP converge to the global optimal solution faster. Our method can achieve an average rotation error of 0.124 degrees and an average translation error of 0.38 mm on 10 clinical data. The results reveal that the surface registration method based on translation rotation decoupling can achieve superior performance regarding both the registration accuracy and the time efficiency in the image-to-patient spatial registration.

Fast cross-staining alignment of gigapixel whole slide images with application to prostate cancer and breast cancer analysis

Joint analysis of multiple protein expressions and tissue morphology patterns is important for disease diagnosis, treatment planning, and drug development, requiring cross-staining alignment of multiple immunohistochemical and histopathological slides. However, cross-staining alignment of enormous gigapixel whole slide images (WSIs) at single cell precision is difficult. Apart from gigantic data dimensions of WSIs, there are large variations on the cell appearance and tissue morphology across different staining together with morphological deformations caused by slide preparation. The goal of this study is to build an image registration framework for cross-staining alignment of gigapixel WSIs of histopathological and immunohistochemical microscopic slides and assess its clinical applicability. To the authors’ best knowledge, this is the first study to perform real time fully automatic cross staining alignment of WSIs with 40× and 20× objective magnification. The proposed WSI registration framework consists of a rapid global image registration module, a real time interactive field of view (FOV) localization model and a real time propagated multi-level image registration module. In this study, the proposed method is evaluated on two kinds of cancer datasets from two hospitals using different digital scanners, including a dual staining breast cancer data set with 43 hematoxylin and eosin (H&E) WSIs and 43 immunohistochemical (IHC) CK(AE1/AE3) WSIs, and a triple staining prostate cancer data set containing 30 H&E WSIs, 30 IHC CK18 WSIs, and 30 IHC HMCK WSIs. In evaluation, the registration performance is measured by not only registration accuracy but also computational time. The results show that the proposed method achieves high accuracy of 0.833 ± 0.0674 for the triple-staining prostate cancer data set and 0.931 ± 0.0455 for the dual-staining breast cancer data set, respectively, and takes only 4.34 s per WSI registration on average. In addition, for 30.23% data, the proposed method takes less than 1 s for WSI registration. In comparison with the benchmark methods, the proposed method demonstrates superior performance in registration accuracy and computational time, which has great potentials for assisting medical doctors to identify cancerous tissues and determine the cancer stage in clinical practice.

3D Digital protection and representation of burial ruins based on LiDAR and UAV survey

To improve the efficiency and accuracy of digital protection of burial sites, the digital protection of burial sites was studied by the collaborative observation technology of LiDAR and unmanned aerial vehicle (UAV) mapping. Multi-feature constrained iterative global registration algorithm is used to realize fast registration of multi-site cloud, the Structure from motion (SFM)-based algorithm is used to generate dense point cloud from UAV image, and then the Iterative Closest Point(ICP) algorithm is used to realize the fusion of point cloud data on-site and image. According to the fused data, a variety of measurable results, such as high-precision burial model and contour map, are produced, and an orthophoto generation system is written independently, which can fully automatically generate high-precision orthophoto map and realize the digitalization of the burial sites. Taking the protection application of the burial site in Yaoheyuan, Ningxia, one of the top 10 archeological discoveries in China in 2017, with guaranteed data accuracy and integrity, the surveying and mapping data of the tomb site was obtained quickly. The global registration accuracy of the proposed algorithm is within 1 cm, and the registration efficiency was superior to the current mainstream open source algorithm, which verified the feasibility and efficiency of this method. It provides an effective scheme for the digital protection of burial cultural heritage, and is also suitable for the digital protection of other heritage sites in the World Heritage List such as Panlongcheng Site and Sanxingdui.

FLORA-5/GOG3035: Frontline chemo-immunotherapy (paclitaxel-carboplatin-oregovomab [PCO] versus chemotherapy (paclitaxel-carboplatin-placebo [PCP]) in patients with advanced epithelial ovarian cancer (EOC)—Phase III, double-blind, placebo-controlled, global, multinational study.

TPS5619 Background: Oregovomab, a murine IgGκ1 monoclonal antibody, has high affinity binding to tumor associated antigen CA125, thus, rendering the target antigen CA125 more immunogenic or “neoantigen-like” through altered and enhanced antigen processing and presentation to specific T cells. This phenomenon is hypothesized to bypass tumor-associated immune suppression when oregovomab is combined with chemotherapy. In a randomized phase II study, oregovomab in combination with paclitaxel and carboplatin (PC) induced tumor immunity and demonstrated significant improvement in median PFS (41.8 months(m) PCO vs 12.2 m PC, HR 0.46, p=0.0027) and median OS (N.E. PCO vs 43.2 m PC, HR O.35, p=0.043) in patients with previously untreated EOC. Oregovomab combined with PC had a favorable toxicity profile. FLORA-5/GOG3035, the definitive confirmatory global registration trial, is currently recruiting patients in the front-line setting. Methods: The study is a phase 3, multicenter, double-blind, placebo-controlled trial. Optimally debulked patients with FIGO III/IV EOC and serum CA125 ≥ 50 U/ml receiving adjuvant (Cohort 1) or patients receiving neoadjuvant chemotherapy post-interval cytoreductive surgery (Cohort 2) will be randomized to PC + oregovomab or placebo (PCO vs. PCP). Patients with germline BRCA1/2 mutations are excluded. Chemotherapy will be administered every 3 weeks in both cohorts. Oregovomab/placebo is administered simultaneously at cycles 1, 3, and 5 of chemotherapy with an additional dose at 12 weeks following cycle 5 in Cohort 1. Neoadjuvant patients will be administered oregovomab/placebo after debulking surgery at cycles 4 and 6 with two additional doses at 6- and 18-weeks following cycle 6 in Cohort 2. No other front-line maintenance therapy is permitted. The primary objective is PFS determined by RECIST 1.1. Cohort 1 will recruit 372 patients with a 90% power to detect a difference with an alpha of 0.025 and a hazard ratio of 0.65 when 252 PFS events have been observed. Cohort 2 will be analyzed separately recruiting 232 patients with a 90% power to detect a difference with an alpha of 0.025 and a hazard ratio of 0.60 when 165 PFS events have been observed. An interim futility analysis will be performed. Secondary objectives include OS, frequency and severity of AEs, and QoL. Exploratory objectives include iRECIST, TFST, TSST, PFS2, and evaluation of correlative biomarkers. The study is actively enrolling in the US, Canada, Belgium, Italy, Spain, Czech Republic, Hungary, Poland, Korea, Taiwan, Mexico, Argentina, and Chile. 179 patients were enrolled at time of submission. Clinical trial information: NCT04498117.

Automatic 3D MRI-Ultrasound Registration for Image Guided Arthroscopy

Registration of partial view intra-operative ultrasound (US) to pre-operative MRI is an essential step in image-guided minimally invasive surgery. In this paper, we present an automatic, landmark-free 3D multimodal registration of pre-operative MRI to 4D US (high-refresh-rate 3D-US) for enabling guidance in knee arthroscopy. We focus on the problem of initializing registration in the case of partial views. The proposed method utilizes a pre-initialization step of using the automatically segmented structures from both modalities to achieve a global geometric initialization. This is followed by computing distance maps of the procured segmentations for registration in the distance space. Following that, the final local refinement between the MRI-US volumes is achieved using the LC2 (Linear correlation of linear combination) metric. The method is evaluated on 11 cases spanning six subjects, with four levels of knee flexion. A best-case error of 1.41 mm and 2.34∘ and an average registration error of 3.45 mm and 7.76∘ is achieved in translation and rotation, respectively. An inter-observer variability study is performed, and a mean difference of 4.41 mm and 7.77∘ is reported. The errors obtained through the developed registration algorithm and inter-observer difference values are found to be comparable. We have shown that the proposed algorithm is simple, robust and allows for the automatic global registration of 3D US and MRI that can enable US based image guidance in minimally invasive procedures.

Delay in death registration among adolescents and young adults in England and Wales

Accurate and timely mortality data are vital to informing policy and improving outcomes. Shortcomings in global vital registration quality and coverage are well known. These limitations particularly affect mortality data for adolescents and young people, as efforts to improve measurement systems have focused on other groups.1 However, even in settings with complete death registration such as the UK, obtaining data on deaths in this age group can present unique challenges, particularly related to delay in registration.

FAST CONVERGENCE METHOD FOR GLOBAL OPTIMAL 4DOF REGISTRATION

Abstract. Four degrees of freedom (4DoF) registration is a class of point cloud registration problems for finding a rigid transformation to align two point clouds under the constraint that the rigid transformation is composed of a three-dimensional (3D) translation and 1D rotation. This constraint is suitable to align scan pairs acquired using modern terrestrial Light Detection and Ranging (LiDAR) scanners, the scans of which can share the direction of gravity as the Z-axis due to such scanners using tripods or internal inclinometers. We propose a fast convergence method for global optimal 4DoF registration. The proposed method consists of (i) our newly developed 4DoF registration model formulated as an optimization problem involving the cylindrical norm to measure the distance between two points, and (ii) a fast convergence algorithm to find a global optimal solution of the model. We experimentally demonstrated that the proposed method reduced the number of iterations to convergence and computation time compared with a current 4DoF registration method, especially when the given scan pairs are similar but cannot be aligned, which often appears in registration of multiple point clouds.

MO413: Registration of Image Modalities for Analyses of Tissue Samples Using 3D Image Modelling

Abstract BACKGROUND AND AIMS Biopsies are a diagnostic tool for the diagnosis of histopathological, molecular biological, proteomic and imaging data, to narrow down disease patterns or identify diseases. Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) provides an emerging state-of-the-art technique for molecular imaging of biological tissue. The aim of this study is the registration of MALDI MSI data sets and data acquired from different histological stainings to create a 3D model of biopsies and whole organs. METHOD The registration of the image modalities is achieved by using a variant of our global, deformable Schatten-q-Norm registration approach. Utilizing a connected-component segmentation for background removal followed by a principal-axis-based linear pre-registration, the images are adjusted into a homogeneous alignment. This registration approach is accompanied by the 3D reconstruction of histological and MALDI MSI data. RESULTS With this, a system of automatic registration for cross-process evaluation, as well as for creating 3D models, is developed and established. The registration of MALDI MSI data with different histological image data is evaluated by using the established global image registration system. CONCLUSION In conclusion, this multimodal image approach offers the possibility of molecular analyses of tissue specimens in clinical research and diagnosis.

Q-Bursts Generated by the Contact of the Interplanetary Shock Wave with the Magnetosphere

The study presents the results of the global registration of a short-term train of damped oscillations in the frequency range 0,5–30,0 Hz (Q-burst), observed at the initial phase of the preliminary impulse of the sudden onset SC on 09.09.2011. The spatial features of the spectrum of train oscillations are studied. We discovered A spectral-resonance structure of bursts, which is observed globally. It is assumed that bursts are generated as a result of powerful lightning discharges that create red sprites in the ionosphere. The electromagnetic radiation of sprites is captured in the earth-ionosphere waveguide and propagates globally. We assumed that one of the reasons for the increase in the power of the Q-signal is the coincidence of the beginning of its generation with the amplification of the ionospheric current system of the preliminary impulse of the sudden onset of SC.

Asia-Inclusive Clinical Research and Development Enabled by Translational Science and Quantitative Clinical Pharmacology: Toward a Culture That Challenges the Status Quo.

Access lag to innovative therapies in Asian populations continues to present a challenge to global health. Recent progressive changes in the global regulatory landscape, including newer guidelines, are enabling simultaneous global drug development and near-simultaneous global drug registration. The International Conference on Harmonization (ICH) E17 guideline outlines general principles for the design and analysis of multiregional clinical trials (MRCTs). We posit that translational research and quantitative clinical pharmacology tools are core enablers for Asia-inclusive global drug development aligned with ICH E17 principles. Assessment of ethnic sensitivity should be initiated early in the development lifecycle to inform the need for, and extent of, Asian phase I ethno-bridging data. Relevant ethno-bridging data may be generated as standalone Asian phase I trials, as part of Western First-In-Human trials, or under accelerated development settings as a lead-in phase in an MRCT. Quantitative understanding of human clearance mechanisms and pharmacogenetic factors is vital to forecasting ethnic sensitivity in drug exposure using physiologically-based pharmacokinetic models. Stratification factors to control heterogeneity in MRCTs can be identified by reverse translational research incorporating pharmacometric disease models and model-based meta-analyses. Because epidemiological variations can extend to the molecular level, quantitative systems pharmacology models may be useful in forecasting how molecular variation in therapeutic targets or pathway proteins across populations might impact treatment outcomes. Through prospective evaluation of conservation in drug- and disease-related intrinsic and extrinsic factors, a pooled East Asian region can be implemented in Asia-inclusive MRCTs to maximize efficiency in substantiating evidence of benefit-risk for the region at-large with a Totality of Evidence approach.

Deep hashing for global registration of untracked 2D laparoscopic ultrasound to CT

PurposeThe registration of Laparoscopic Ultrasound (LUS) to CT can enhance the safety of laparoscopic liver surgery by providing the surgeon with awareness on the relative positioning between critical vessels and a tumour. In an effort to provide a translatable solution for this poorly constrained problem, Content-based Image Retrieval (CBIR) based on vessel information has been suggested as a method for obtaining a global coarse registration without using tracking information. However, the performance of these frameworks is limited by the use of non-generalisable handcrafted vessel features.MethodsWe propose the use of a Deep Hashing (DH) network to directly convert vessel images from both LUS and CT into fixed size hash codes. During training, these codes are learnt from a patient-specific CT scan by supplying the network with triplets of vessel images which include both a registered and a mis-registered pair. Once hash codes have been learnt, they can be used to perform registration with CBIR methods.ResultsWe test a CBIR pipeline on 11 sequences of untracked LUS distributed across 5 clinical cases. Compared to a handcrafted feature approach, our model improves the registration success rate significantly from 48% to 61%, considering a 20 mm error as the threshold for a successful coarse registration.ConclusionsWe present the first DH framework for interventional multi-modal registration tasks. The presented approach is easily generalisable to other registration problems, does not require annotated data for training, and may promote the translation of these techniques.

Benchmark Based Selection Of Point Cloud Registration Algorithms For Cultural Heritage 3D Digitization

Abstract This work aims to address the point cloud global registration algorithm selection problem by proposing a pipeline for testing and evaluating such algorithms. Moreover, this benchmark-based evaluation automates the algorithm selection process by assessing the point cloud registration algorithms under the same universal benchmark, using complete and diverse datasets. We demonstrate its performance by comparing two State-of-the-art global registration algorithms that are tested on a set of problems created by diverse, unstructured datasets, acquired by various types of sensors, and in different environmental conditions. Furthermore, a comprehensive metric is proposed, which serves as a qualitative metric, rather than an absolute result for the evaluation process. Finally, the different outcomes of the algorithms benchmarking performance are thoroughly presented and discussed.