Fast Registration Research Articles

Application of Monocular Direct Vision Odometry in Augmented Reality

In recent years, the unlabeled augmented reality system has been gradually applied to various mobile devices, among which stable, accurate, and fast registration is the key to realizing this function. For this technique, this paper introduces camera exposure parameters and puts the data association and pose estimation into a unified nonlinear optimization problem. Moreover, the direct monocular vision odometer is transplanted into the augmented reality system through the position adjustment module. We compare it with the traditional visual odometry method that matches the feature points. The results show that this improved method can be used to track more quickly and build a more visual semi-dense point cloud map, which can be used to support the registration and tracking of virtual objects in augmented reality.

Online 3-D Modeling of Complex Workpieces for the Robotic Spray Painting With Low-Cost RGB-D Cameras

The 3-D model of workpieces plays a significant role in robotic spray painting, which needs the geometry and shape information for painting-path planning or pose estimation. However, the models are rarely provided beforehand, even if they are available, random pose changes during workpiece conveying on the spray-painting pipeline also necessitates the usage of real-time 3-D reconstruction. In this case, we propose an online modeling approach for automatic spray-painting applications. Specifically, with two consumer RGB-D cameras mounted on the two sides of the pipeline, the data streams of the moving workpiece are continuously collected. Then, incorporating the 3-D contour feature and approximate linear motion characteristics of the workpiece, a modified iterative closest point (ICP) algorithm is proposed for fast registration of multiple workpiece point clouds with varying positions. Finally, based on the spatial distribution and point cloud quality evaluation, a joint weighted algorithm for fusing point clouds from different perspectives is proposed, which is effective for the issues of self-occlusion and has superior noise resistance. To estimate the system performance, an experimental platform was established to simulate the spray-painting production line. According to our experiments, the proposed method can completely model the complex workpieces with irregular polyhedral structure within 1500 ms, and the modeled geometry accuracy can reach less than 8 mm, which has a significant improvement compared with the conventional methods.

Visualization and co-registration of correlative microscopy data with the ImageJ plug-in Correlia.

Correlative microscopy experiments require the co-registration of the image data acquired by different micro-analytical techniques. Major challenges are the potentially very different fields-of-view and resolutions as well as the multi-modality of the data. To provide microscopists with an easy-to-use software for two-dimensional image co-registration we have developed Correlia, an open source software based on ImageJa/Fiji,b which is fully tailored for the registration of multi-modal microscopy data. It can handle data-sets of in principle arbitrary extent and uses classical approaches, i.e., rigid registration tools or B-spline based deformation models for the correction of both, global and local misalignments, such that a fast registration output is provided. Here we describe some of the basics of Correlia focusing on its application: firstly, registration workflows are outlined on artificial data. In the second part these recipes are applied to register correlative data acquired on an algal biofilm and a soil sample.

MROM Scheme to Improve Handoff Performance in Mobile Networks

Mobile Router (MR) mobility supported by Network Mobility Basic Support Protocol (NEMO BS) is a Mobile IPv6 (MIPv6) extension that supports Host Mobility. Proposed Multihoming and Route Optimization for MANEMO (MROM) scheme is designed to provide Route Optimization (RO) and Multihomed in NEMO architectures. This paper proposes two novel schemes; MANEMO routing scheme and Multihoming-based scheme. These are to provide support for next generation networks. The proposed MROM scheme differs from other schemes for NEMO environment because it considers the requirements of more application flows parameters as packet lost delivery, handoff delay as well as throughput). Another difference is that not only the network infrastructure can begin the functionality of flow routing, but also an Edge Mobile Router (EMR) can do this flow for routing. Moreover, it utilizes the state of the art and presently active access network to perform the separation of each flow in mobile network. Thus, proposed MROM exhibits multihoming features and improves handoff performance by initiating flow-based fast registration process in NEMO environment. A handoff method is proposed with enhanced functionalities of the Local Mobility Anchors (LMA), Mobile Routers (MRs) and signaling messages with a view to achieve continuous connectivity through handoff in NEMO. Both analytical and simulation approaches are used. Analytical evaluation is carried out to analyze packet delivery lost and handoff delay of our proposed scheme. It was also shown that cost of signaling messages and packet delivery are contributing to total handoff cost. At the simulation part, network simulator 3 (NS 3) has been used as the tool to get performance metrics that have been considered like packet delivery ratio, handoff delay, and packet loss. Our proposed scheme (MROM) has been benchmarking to the standard NEMO BS Protocol and P-NEMO. In this paper, we discuss proposed MROM for next generation networks, providing detailed analysis with a numerical model, proposed MROM, by maximizing the handoff performance, has been justified to have better mobility support than the ordinary NEMO BS Protocol and PNEMO.

Operability, Usefulness, and Task-Technology Fit of an mHealth App for Delivering Primary Health Care Services by Community Health Workers in Underserved Areas of Pakistan and Afghanistan: Qualitative Study.

BackgroundThe recent proliferation of digital health technology in low- and middle-income countries has made it possible for community health workers (CHWs) to use mobile health (mHealth) to perform tasks such as data collection and training. Although most studies focus on the prospect of digital apps to motivate and connect CHW, only a few have captured end-user experiences with mobile-based apps. We examined the experience of frontline health workers with a move towards digitalized real-time data to record maternal and childcare services in remote areas of Afghanistan and Pakistan.ObjectiveOur study aimed to explore CHW perceptions on the operability of the mHealth app in a community setting, usefulness of the app in the delivery of assigned maternal and childcare functions, and the task-technology fit with monitoring information systems.MethodsThe Hayat app, designed to digitalize and facilitate electronic record keeping, was evaluated to be embedded into mainstream health systems. The app had 2 components: smartphone app for data entry and web dashboard for visualization of the maternal, newborn, and child health reports. Using a qualitative exploratory study design, we conducted a total of 8 focus group discussions with purposively selected lady health workers (LHWs) and CHWs in 3 districts of Pakistan and 3 hamlets of Afghanistan, respectively. Focus group discussions were conducted in the local language, audio recorded, and converted into expanded notes for thematic analysis.ResultsAlthough a majority of LHWs used the app with ease, some initially faced difficulties in operating it and requested a longer duration of training. Contrary to LHWs, the CHWs were able to use the app without difficulty, as they were using it only to register clients. Overall, use of the mHealth app in both countries resulted in a positive impact on health education sessions, easier communication with parents or clients, tracking of routine immunization defaulters and follow-ups, improved data validity, easily accessible vaccination schedules, and faster registration. In addition to building up their image in the community and personal development, the improved reporting and monitoring mechanisms also set the stage for the LHWs to get recognized for their hard work. CHWs in Afghanistan also reported the app provided immediate access to information when requested by their supervisor. Although the Hayat app eliminates the need to carry multiple registers and helps in recalling client information at the touch of a button, technical issues around connectivity and data inputting tabs were highlighted by the participants.ConclusionsThe digitization of records not only provided CHWs support in their daily routine but also strengthened monitoring mechanisms and improved motivation. We recommend conducting end user experience studies before embedding apps into mainstream health systems as high acceptability does not always result in high uptake of digital technology.

A NEW METHOD OF FAST REGISTRATION OF UNMANNED AERIAL VEHICLE REMOTE SENSING IMAGES BASED-ON AN IMPROVED SURF ALGORITHM

Abstract. Remote sensing system fitted on UAV (Unmanned Aerial Vehicle) can obtain clear images and high-resolution aerial photographs. It has advantages of flexibility, convenience and ability to work full-time. However, there are some problems of UAV image such as small coverage area, large number, irregular overlap, etc. How to obtain a large regional map quickly becomes a major obstacle to UAV remote sensing application. In this paper, a new method of fast registration of UAV remote sensing images was proposed to meet the needs of practical application. This paper used Progressive Sample Consensus (PROSAC) algorithm to improve the matching accuracy by removed a large number of mismatching point pairs of remote sensing image registration based-on SURF (Speed Up Robust Feature) algorithm, and GPU (Graphic Processing Unit) was also used to accelerate the speed of improved SURF algorithm. Finally, geometric verification was used to achieve mosaic accuracy in survey area. The number of feature points obtained by using improved SURF based-on PROSAC algorithm was only 9.5% than that of SURF algorithm. Moreover, the accuracy rate of improved method was about 99.7%, while the accuracy rate of improved SURF algorithm was increased by 8% than SURF algorithm. Moreover, the improved running time of SURFGPU algorithm for UAV remote sensing image registration was a speed of around 16 times than SURF algorithm, and the image matching time had reached millisecond level. Thus, improved SURF algorithm had better matching accuracy and executing speed to meet the requirements of real-time and robustness in UAV remote sensing image registration.

Multi-View Point-Based Registration for Native Knee Kinematics Measurement with Feature Transfer Learning

Deep-learning methods provide a promising approach for measuring in-vivo knee joint motion from fast registration of two-dimensional (2D) to three-dimensional (3D) data with a broad range of capture. However, if there are insufficient data for training, the data-driven approach will fail. We propose a feature-based transfer-learning method to extract features from fluoroscopic images. With three subjects and fewer than 100 pairs of real fluoroscopic images, we achieved a mean registration success rate of up to 40%. The proposed method provides a promising solution, using a learning-based registration method when only a limited number of real fluoroscopic images is available.

Medical Image Registration Based on Renyi’s Quadratic Mutual Information

In this paper, a medical image registration based on Renyi’s quadratic mutual information is proposed. Firstly, the initial values (i.e. the translation and rotation parameters) for aligning the floating image with the reference image are obtained by computing the medical image centroids and moments. Then, when exploring the optimal geometric transformation parameters, the Renyi’s quadratic mutual information is taken as the similarity criterion between the reference and floating images. Finally, the Simplex method, as multi-parameter optimization one, is used to search the optimal registering values in the experiments. The experimental results reveal that, the proposed method has a lower computational load, faster registration and better registration accuracy compared with the registration method based on the Shannon mutual information. It can cater to both mono-modality and multi-modality image registrations.

Limited Liability Companies in Poland

This study discusses the construction of a limited liability company (LLC) under Polish law. Due to the short length of the article and the large scale of the issue, this study is limited to the presentation of basic concepts. The construction of an LLC under Polish law is flexible and has been modernised, as a result of a number of amendments, including a fast registration path.

Fast registration of forest terrestrial laser scans using key points detected from crowns and stems

ABSTRACT Registration of TLS data is an important prerequisite to overcome the limitations of occlusion. Most existing registration methods rely on stems to determine the transformation parameters. However, the complexity of the registration problem increases dramatically as the number of stems grows. It is tricky to reduce the stems and determine the valid ones that can provide reliable registration transformation without a knowledge of the two scans. This paper presents an automatic and fast registration of TLS point clouds in forest areas. It reduces stems by selecting from the overlap areas, which are recovered from the mode-based key points that are detected from crowns. The proposed method was tested in a managed forest in Finland, and was compared with the stem-based registration method without reducing stems. The experiments demonstrated that the mean rotation error was 2.09′, and the mean errors in horizontal and vertical translation were 1.13 and 7.21 cm, respectively. Compared with the stem-based method, the proposed method improves the registration efficiency significantly (818 s vs 96 s) and achieves similar results in terms of the mean registration errors (1.94′ for rotation error, 0.83 and 7.38 cm for horizontal and vertical translation error, respectively).

Toward a robust and fast real-time point cloud registration with factor analysis and Student’s-t mixture model

Three-dimensional (3D) point cloud registration generally involves in unsatisfied situations like Gaussian white noise, data missing and disorder in affine. This paper proposes a robust and real-time point cloud registration, which combines the Student’s-t mixture model (SMM) with factor analysis. The proposed method extending the point cloud mathematical model to the orthogonal factor model and employs the SMM to fit the point cloud data, because the degree of freedom of Student’s t-distribution makes it more flexible in fitting the probability distribution of data. Since the Expectation Maximization (EM) algorithm has a stable estimation ability for the mixture model, the EM algorithm is used to estimate the factor load matrix. The filed data and experimental results show that the proposed algorithm can achieve accurate registration and fast convergence even in the case of point cloud disorder, data occlusion, incomplete loss and noise.

可见光图像与合成孔径雷达图像的快速配准

可见光图像与合成孔径雷达图像的快速配准

An efficient EM-ICP algorithm for non-linear registration of large 3D point sets

In this paper, we present a new method for non-linear pairwise registration of 3D point sets. In this method, we consider the points of the first set as the draws of a Gaussian mixture model whose centres are the displaced points of the second set. Next we perform a maximum a posteriori estimation of the parameters (which include the unknown transformation) of this model using the expectation–maximisation (EM) algorithm. Compared to other methods using the same “EM-ICP” framework, we propose four key modifications leading to an efficient algorithm allowing for fast registration of large 3D point sets: (1) truncation of the cost function; (2) symmetrisation of the point-to-point correspondences; (3) specification of priors on these correspondences using differential geometry; (4) efficient encoding of deformations using the RKHS theory and the Fourier analysis. We evaluate the added value of these modifications and compare our method to the state-of-the-art CPD algorithm on real and simulated data.

Hubless keypoint-based 3D deformable groupwise registration.

We present a novel algorithm for Fast Registration Of image Groups (FROG), applied to large 3D image groups. Our approach extracts 3D SURF keypoints from images, computes matched pairs of keypoints and registers the group by minimizing pair distances in a hubless way i.e. without computing any central mean image. Using keypoints significantly reduces the problem complexity compared to voxel-based approaches, and enables us to provide an in-core global optimization, similar to the Bundle Adjustment for 3D reconstruction. As we aim to register images of different patients, the matching step yields many outliers. Then we propose a new EM-weighting algorithm which efficiently discards outliers. Global optimization is carried out with a fast gradient descent algorithm. This allows our approach to robustly register large datasets. The result is a set of diffeomorphic half transforms which link the volumes together and can be subsequently exploited for computational anatomy and landmark detection. We show experimental results on whole-body CT scans, with groups of up to 103 volumes. On a benchmark based on anatomical landmarks, our algorithm compares favorably with the star-groupwise voxel-based ANTs and NiftyReg approaches while being much faster. We also discuss the limitations of our approach for lower resolution images such as brain MRI.

An Adaptive Real-Time Detection Algorithm for Dim and Small Photoelectric GSO Debris.

Geosynchronous orbit (GSO) is the ideal orbit for communication, navigation, meteorology and other satellites, but the space of GSO is limited, and there are still a large number of space debris threatening the safety of spacecraft. Therefore, real-time detection of GSO debris is necessary to avoid collision accidents. Because radar is limited by transmitting power and operating distance, it is difficult to detect GSO debris, so photoelectric detection becomes the mainstream way to detect GSO debris. This paper presents an adaptive real-time detection algorithm for GSO debris in the charge coupled device (CCD) images. The main work is as follows: An image adaptive fast registration algorithm and an enhanced dilation difference algorithm are proposed. Combining with mathematical morphology, threshold segmentation and global nearest neighbor (GNN) multi-target tracking algorithm, the functions of image background suppression, registration, suspected target extraction and multi-target tracking are realized. The processing results of a large number of measured data show that the algorithm can detect dim geostationary earth orbit (GEO) and non-GEO debris in GSO belt stably and efficiently, and the processing speed meets the real-time requirements, with strong adaptive ability, and has high practical application value.

Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces.

Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we build a connection between classical and learning-based methods. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task for both images and anatomical surfaces, and provide extensive empirical analyses of the algorithm. Our principled approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees. Our implementation is available online at http://voxelmorph.csail.mit.edu.

Keypoint domain triangular features for fast initial alignment of 3D point clouds

The authors propose a keypoint domain triangular feature-based initial alignment (KDT-IA) method to achieve fast and automatic registration of three-dimensional (3D) point clouds. KDT-IA has two main contributions: a KDT feature and a transformation estimation technique called one point-based sample consensus (1P-SAC). KDT is ultrafast because it encodes the spatial geometry of 3D keypoints over sparse keypoints, as opposed to conventional point cloud domain features. The alignment is additionally accelerated by the 1P-SAC algorithm due to its linear computational complexity. Experiments on real-world scanned point cloud data confirm that KDT-IA achieves competitive accuracy performance with classical methods yet being at least one order of magnitude faster.

Fast predictive simple geodesic regression.

Deformable image registration and regression are important tasks in medical image analysis. However, they are computationally expensive, especially when analyzing large-scale datasets that contain thousands of images. Hence, cluster computing is typically used, making the approaches dependent on such computational infrastructure. Even larger computational resources are required as study sizes increase. This limits the use of deformable image registration and regression for clinical applications and as component algorithms for other image analysis approaches. We therefore propose using a fast predictive approach to perform image registrations. In particular, we employ these fast registration predictions to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting method is orders of magnitude faster than the standard optimization-based regression model and hence facilitates large-scale analysis on a single graphics processing unit (GPU). We evaluate our results on 3D brain magnetic resonance images (MRI) from the ADNI datasets.

Intensity-Assisted ICP for Fast Registration of 2D-LIDAR.

Iterative closest point (ICP) is a method commonly used to perform scan-matching and registration. To be a simple and robust algorithm, it is still computationally expensive, and it has been regarded as having a crucial challenge especially in a real-time application as used for the simultaneous localization and mapping (SLAM) problem. For these reasons, this paper presents a new method for the acceleration of ICP with an assisted intensity. Unlike the conventional ICP, this method is proposed to reduce the computational cost and avoid divergences. An initial transformation guess is computed with an assisted intensity for their relative rigid-body transformation. Moreover, a target function is proposed to determine the best initial transformation guess based on the statistic of their spatial distances and intensity residuals. Additionally, this method is also proposed to reduce the iteration number. The Anderson acceleration is utilized for increasing the iteration speed which has better ability than the Picard iteration procedure. The proposed algorithm is operated in real time with a single core central processing unit (CPU) thread. Hence, it is suitable for the robot which has limited computation resources. To validate the novelty, this proposed method is evaluated on the SEMANTIC3D.NET benchmark dataset. According to comparative results, the proposed method is declared as having better accuracy and robustness than the conventional ICP methods.

Brazilian Legislation Leaning Towards Fast Registration of Biological Control Agents to Benefit Organic Agriculture.

Brazil is one of the main users of chemical pesticides in the world. These products threaten human and environmental health, and many of them are prohibited in countries other than Brazil. This paradigm exists in contrast with worldwide efforts to make the need for food production compatible with biodiversity conservation, preservation of ecosystem services, and human health. In this scenario, the development of sustainable methods for crop production and pest management such as organic agriculture and biological control are necessary. Herein, we describe how the process of registration of natural enemy-based products in organic agriculture is simpler and faster than the conventional route of chemical insecticides and can favor the development of the biological control market in Brazil. Since the regulatory mechanisms have been established in Brazil for organic agriculture, the number of biological control products registered has increased exponentially. Today, 50 companies and associations are marketing 16 species/isolates and 95 natural enemy-based products. Although this scenario presents a series of new opportunities to increase and stimulate a more sustainable agriculture in the country, biological control is not always aligned with the aims and philosophy of organic agriculture and agroecology. Therefore, we also argue that new research efforts are needed on understanding how conservation biological control strategies can be integrated with augmentation biological control to promote a sustainable agriculture under the concepts of organic agriculture and agroecology.