Robust Alignment Research Articles

A Fast Robust In-Motion Alignment Method for SINS With DVL Aided

In this paper, a fast robust in-motion alignment method is proposed for the strapdown inertial navigation system (SINS) with DVL aided. The proposed method is divided into two procedures, which are coarse alignment procedure and fine alignment procedure. In the coarse alignment procedure, an apparent velocity modeling method is investigated. Building upon this model, a robust Kalman filter (RKF) is designed for parameter estimation, then an optimal observation vector, in which the outliers of the Doppler Velocity Log (DVL) outputs are eliminated, is reconstructed. As compared with the existing method, in the proposed method, the robustness of coarse alignment procedure is enhanced. To improve the accuracy of the coarse alignment method, a fine alignment method is designed. Different from the traditional fine alignment method, the error model of the proposed fine alignment method is constructed in n 0-frame. With this advantage, the time-varying error attitude estimation for the traditional method has transformed into a time-invariant error attitude estimation. Thus, the raw data and intermediate data, which are collected in the coarse alignment procedure, can be reused in the fine alignment procedure. Take advantage of the high performance of the navigational computer, the forward-forward data processing can be carried on repeatedly, the one cycle of the forward-forward procedure consumes about 0.3 s in the real-time system. Simulation and field tests showed that the proposed method can obtain a high-accuracy initial alignment results and suppress the interference of the outliers of the DVL outputs.

Robust Initial Alignment for SINS/DVL Based on Reconstructed Observation Vectors

Misalignment angle will result in a considerable error for the integration of Doppler velocity log (DVL) and of Strapdown Inertial Navigation System (SINS). In this article, a robust initial alignment method for SINS/DVL is proposed to solve a practical applicable issue, which is that the outputs of DVL are often corrupted by the outliers. First, the alignment principle for SINS/DVL is summarized. Second, based on the principle of this alignment method, the apparent velocity model is investigated, and the parameters expression of the apparent velocity model are derived detailed. Using the apparent velocity model, the unknown parameters of the apparent velocity model are estimated by the developed robust Kalman filter, then the reconstructed observation vector, where the outliers are detected and isolated, is reconstructed by the estimated parameters. Based on the reconstructed observation vectors, the initial attitude is determined. Finally, the simulation and field tests are carried out to verify the performance of the proposed method. The test results are shown that the proposed method can detect and isolate the outliers effectively and get better performance than the previous work.

A within-coil optical prospective motion-correction system for brain imaging at 7T.

Motion artifact limits the clinical translation of high-field MR. We present an optical prospective motion correction system for 7 Tesla MRI using a custom-built, within-coil camera to track an optical marker mounted on a subject. The camera was constructed to fit between the transmit-receive coils with direct line of sight to a forehead-mounted marker, improving upon prior mouthpiece work at 7 Tesla MRI. We validated the system by acquiring a 3D-IR-FSPGR on a phantom with deliberate motion applied. The same 3D-IR-FSPGR and a 2D gradient echo were then acquired on 7 volunteers, with/without deliberate motion and with/without motion correction. Three neuroradiologists blindly assessed image quality. In 1 subject, an ultrahigh-resolution 2D gradient echo with 4 averages was acquired with motion correction. Four single-average acquisitions were then acquired serially, with the subject allowed to move between acquisitions. A fifth single-average 2D gradient echo was acquired following subject removal and reentry. In both the phantom and human subjects, deliberate and involuntary motion were well corrected. Despite marked levels of motion, high-quality images were produced without spurious artifacts. The quantitative ratings confirmed significant improvements in image quality in the absence and presence of deliberate motion across both acquisitions (P < .001). The system enabled ultrahigh-resolution visualization of the hippocampus during a long scan and robust alignment of serially acquired scans with interspersed movement. We demonstrate the use of a within-coil camera to perform optical prospective motion correction and ultrahigh-resolution imaging at 7 Tesla MRI. The setup does not require a mouthpiece, which could improve accessibility of motion correction during 7 Tesla MRI exams.

Joint Stacked Hourglass Network and Salient Region Attention Refinement for Robust Face Alignment

Facial landmark detection aims to locate keypoints for facial images, which typically suffer from variations caused by arbitrary pose, diverse facial expressions, and partial occlusion. In this article, we propose a coarse-to-fine framework that joins a stacked hourglass network and salient region attention refinement for robust face alignment. To achieve this goal, we first present a multi-scale region learning module to analyze the structure information at a different facial region and extract a strong discriminative deep feature. Then we employ a stacked hourglass network for heatmap regression and initial facial landmarks prediction. Specifically, the stacked hourglass network introduces an improved Inception-ResNet unit as a basic building block, which can effectively improve the receptive field and learn contextual feature representations. Meanwhile, a novel loss function takes into account global weights and local weights to make the heatmap regression more accurate. Different from existing heatmap regression models, we present a salient region attention refinement module to extract a precise feature based on the heatmap regression, and utilize the filtered feature for landmarks refinement to achieve accurate prediction. Extensive experimental results of several challenging datasets (including 300 Faces in the Wild, Caltech Occluded Faces in the Wild, and Annotated Facial Landmarks Faces in the Wild) confirm that our approach can achieve more competitive performance than the most advanced algorithms.

Factorization of the translation kernel for fast rigid image alignment

An important component of many image alignment methods is the calculation of inner products (correlations) between an image of pixels and another image translated by some shift and rotated by some angle. For robust alignment of an image pair, the number of considered shifts and angles is typically high, thus the inner product calculation becomes a bottleneck. Existing methods, based on fast Fourier transforms (FFTs), compute all such inner products with computational complexity per image pair, which is reduced to if only distinct shifts are needed. We propose to use a factorization of the translation kernel (FTK), an optimal interpolation method which represents images in a Fourier–Bessel basis and uses a rank-H approximation of the translation kernel via an operator singular value decomposition (SVD). Its complexity is per image pair. We prove that , where 2W is the magnitude of the maximum desired shift in pixels and is the desired accuracy. For fixed W this leads to an acceleration when is large, such as when sub-pixel shift grids are considered. Finally, we present numerical results in an electron cryomicroscopy application showing speedup factors of 3–10 with respect to the state of the art.

Memory Attention: Robust Alignment Using Gating Mechanism for End-to-End Speech Synthesis

Recent end-to-end (e2e) speech synthesis systems usually employ attention techniques to align an input text sequence against a mel-spectrogram sequence. Attention-based e2e approach has shown state-of-the-art performance in speech synthesis. However, generating stable and robust attention alignment to avoid some serious failures such as repeating, missing, and mumbling phones is still an ongoing challenge. In order to mitigate these alignment failures, we propose a novel attention method called memory attention for e2e speech synthesis, which is inspired by the gating mechanism of the long-short term memory (LSTM). Leveraging the sequence modeling power of the gating techniques, memory attention can produce a stable alignment by controlling the amount of content-based and location-based information. For performance evaluation, we compared our proposed memory attention algorithm with various conventional attention techniques in single speaker and emotional speech synthesis scenarios. From the experimental results, we conclude that memory attention can robustly generate various stylish speech.

Caretta – A multiple protein structure alignment and feature extraction suite

The vast number of protein structures currently available opens exciting opportunities for machine learning on proteins, aimed at predicting and understanding functional properties. In particular, in combination with homology modelling, it is now possible to not only use sequence features as input for machine learning, but also structure features. However, in order to do so, robust multiple structure alignments are imperative.Here we present Caretta, a multiple structure alignment suite meant for homologous but sequentially divergent protein families which consistently returns accurate alignments with a higher coverage than current state-of-the-art tools. Caretta is available as a GUI and command-line application and additionally outputs an aligned structure feature matrix for a given set of input structures, which can readily be used in downstream steps for supervised or unsupervised machine learning. We show Caretta’s performance on two benchmark datasets, and present an example application of Caretta in predicting the conformational state of cyclin-dependent kinases.

A Novel Deep Learning Pipeline for Retinal Vessel Detection In Fluorescein Angiography.

While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluorescein angiography (FA) has been stymied due to the lack of labeled ground truth datasets. We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks (DNNs) that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning. The cross-modality transfer exploits concurrently captured CF and fundus FA images. Binary vessels maps are first detected from CF images with a pre-trained neural network and then are geometrically registered with and transferred to FA images via robust parametric chamfer alignment to a preliminary FA vessel detection obtained with an unsupervised technique. Using the transferred vessels as initial ground truth labels for deep learning, the human-in-the-loop approach progressively improves the quality of the ground truth labeling by iterating between deep-learning and labeling. The approach significantly reduces manual labeling effort while increasing engagement. We highlight several important considerations for the proposed methodology and validate the performance on three datasets. Experimental results demonstrate that the proposed pipeline significantly reduces the annotation effort and the resulting deep learning methods outperform prior existing FA vessel detection methods by a significant margin. A new public dataset, RECOVERY-FA19, is introduced that includes high-resolution ultra-widefield images and accurately labeled ground truth binary vessel maps.

Accuracy Analysis of Alignment Methods based on Reference Features for Robot-Based Optical Inspection Systems

In recent years, optical 3D sensors have reached a high level of accuracy suitable for many applications involved in the geometric quality assurance in modern production sites. In order to circumvent the tradeoff between the size of the field of view and the accuracy, a fusion of multiple point clouds is often performed by means of data-driven registration algorithms, such as the well-known ICP. These methods require a coarse alignment of point clouds, which also influences the accuracy and robustness of the actual 3D matching process. In the context of robot-based inspection systems, additional reference features are often applied. The references are well detectable and provide key points. This gives rise to the question of whether or not better initial alignments are obtainable from the measurement data, in contrast to the alignment obtained by the robot kinematic. Therefore, we investigated the accuracy of calculated transformations for translational and rotational modifications based on measured data. The results indicate that for mainly translational relative transformations high accuracies are obtainable. An improvement of the coarse alignment for subsequent fine registration processes promises a contribution towards having more accurate and robust alignments of point clouds, and therefore benefits geometric quality assurance applications in manufacturing industries.

A guided approach for subtomogram averaging of challenging macromolecular assemblies

Cryo-electron tomography is a powerful biophysical technique enabling three-dimensional visualization of complex biological systems. Macromolecular targets of interest identified within cryo-tomograms can be computationally extracted, aligned, and averaged to produce a better-resolved structure through a process called subtomogram averaging (STA). However, accurate alignment of macromolecular machines that exhibit extreme structural heterogeneity and conformational flexibility remains a significant challenge with conventional STA approaches. To expand the applicability of STA to a broader range of pleomorphic complexes, we developed a user-guided, focused refinement approach that can be incorporated into the standard STA workflow to facilitate the robust alignment of particularly challenging samples. We demonstrate that it is possible to align visually recognizable portions of multi-subunit complexes by providing a priori information regarding their relative orientations within cryo-tomograms, and describe how this strategy was applied to successfully elucidate the first three-dimensional structure of the dynein-dynactin motor protein complex bound to microtubules. Our approach expands the application of STA for solving a more diverse range of heterogeneous biological structures, and establishes a conceptual framework for the development of automated strategies to deconvolve the complexity of crowded cellular environments and improve in situ structure determination technologies.

Robust Alignment of Multi-Exposed Images With Saturated Regions

It is challenging to align multi-exposed images due to large illumination variations, especially in presence of saturated regions. In this paper, a novel image alignment algorithm is proposed to cope with the multi-exposed images with saturated regions. Specifically, the multi-exposed images are first normalized by using intensity mapping functions (IMFs) in consideration of saturated pixels. Then, the normalized images are coded by using the local binary pattern (LBP). Finally, the coded images are aligned by formulating an optimization problem by using a differentiable Hamming distance. Experimental results show that the proposed algorithm outperforms state-of-the-art alignment methods for multi-exposed images in terms of alignment accuracy and robustness to exposure values.

ACCELERATING THE EMERGENCE OF ORDER IN SWARMING SYSTEMS

Our ability to understand and control the emergence of order in swarming systems is a fundamental challenge in contemporary science. The standard Vicsek model (SVM) — a minimal model for swarming systems of self-propelled particles — describes a large population of agents reaching global alignment without the need of central control. Yet, the emergence of order in this model takes time and is not robust to noise. In many real-world scenarios, we need a decentralized protocol to guide a swarming system (e.g., unmanned vehicles or nanorobots) to reach an ordered state in a prompt and noise-robust manner. Here, we find that introducing a simple adaptive rule based on the heading differences of neighboring particles in the Vicsek model can effectively speed up their global alignment, mitigate the disturbance of noise to alignment, and maintain a robust alignment under predation. This simple adaptive model of swarming systems could offer new insights in understanding the prompt and flexible formation of animals and help us design better protocols to achieve fast and robust alignment for multi-agent systems.

Robust face alignment by cascaded regression and de-occlusion

Face alignment is a typical facial behavior analysis task in computer vision. However, the performance of face alignment is degraded greatly when the face image is partially occluded. In order to achieve better mapping between facial appearance features and shape increments, we propose a robust and occlusion-free face alignment algorithm in which a face de-occlusion module and a deep regression module are integrated into a cascaded deep generative regression model. The face de-occlusion module is a disentangled representation learning Generative Adversarial Networks (GANs) which aims to locate occlusions and recover the genuine appearance from partially occluded face image. The deep regression module can enhance facial appearance representation by utilizing the recovered faces to obtain more accurate regressors. Then, by the cascaded deep generative regression model, we recover the partially occluded face image and achieve accurate locating of landmarks gradually. It is interesting to show that the cascaded deep generative regression model can effectively locate occlusions and recover more genuine faces, which can be further used to improve the performance of face alignment. Experimental results conducted on four challenging occluded face datasets demonstrate that our method outperforms state-of-the-art methods.

BeamDelta: simple alignment tool for optical systems

BeamDelta is a tool to help align optical systems. It greatly assists in assembling bespoke optical systems by providing a live view of the current laser beam position and a reference position. Even a simple optical setup has multiple degrees of freedom that affect the alignment of beam paths. These degrees of freedom rise exponentially with the complexity of the system. The process of aligning all the optical components for a specific system is often esoteric and poorly documented, if it is documented at all. Alignment methods used often rely on visual inspection of beams impinging on pinholes in the beam path, typically requiring an experienced operator staring at diffuse reflections for extended periods of time. This can lead to a decline in accuracy due to eye strain, flash blindness as well as symptoms such as headaches and, possibly, more serious retinal damage. Here we present BeamDelta a simple alignment tool and accompanying software interface which allows users to obtain accurate alignment as well as removing the necessity of staring at diffuse laser reflections. BeamDelta is a robust alignment tool as it doesn't require any precise alignment itself.

Alignment methods for nanotomography with deep subpixel accuracy.

As the resolution of X-ray tomography improves, the limited long-term stability and accuracy of nanoimaging tools does not allow computing artifact-free three-dimensional (3D) reconstructions without an additional step of numerical alignment of the measured projections. However, the common iterative alignment methods are significantly more computationally demanding than a simple tomographic reconstruction of the acquired volume. Here, we address this issue and present an alignment toolkit, which exploits methods with deep-subpixel accuracy combined with a multi-resolution scheme. This leads to robust and accurate alignment with significantly reduced computational and memory requirements. The performance of the presented methods is demonstrated on simulated and measured datasets for tomography and also laminography acquisition geometries. A GPU accelerated implementation of our alignment framework is publicly available.

Information technology integration for accelerated knowledge sharing practices: challenges and prospects for small and medium enterprises

This paper argues that business enterprises in this competitive global market cannot compete and remain sustainable without effective knowledge sharing to improve business intelligence processes. The central argument hinges on the deployment and use of information technology (IT) as strategic tools to promote business decision making through quick business data analysis and dissemination of business ideas across business units and locations. The study reiterated the critical role IT plays in facilitating a culture of organizational learning and knowledge sharing practices. The study utilized surveys and questionnaires that were distributed to 230 small and medium enterprises (SMEs), and both descriptive and inferential statistics were used to present the results. Findings showed that firms are still using one-on-one meeting to share knowledge, while knowledge sharing activities are controlled through a rigid and inflexible process at the top management level, thereby hindering knowledge flow that is crucial for real-time decision making. The advances in IT have not been used advantageously to improve knowledge sharing and to advance business management. The paper concludes that without strong positive correlation between IT infrastructure integration, and communication strategies and knowledge sharing, the SMEs may not be able to compete in a highly competitive knowledge economy. Consequently, they may lose leverage to another competitor with more robust and mature IT infrastructure alignment for sharing business analytics and intelligence efficiently. A technologically driven, open, and informal approach to knowledge sharing for productive and innovative engagement is recommended. Furthermore, the use of IT that can promote agile and real-time knowledge sharing is recommended.

Learning and Uncertainty-Exploited Directional Antenna Control for Robust Long-Distance and Broad-Band Aerial Communication

Aerial communication using directional antennas (ACDA) is a promising solution to enable long-distance and broad-band unmanned aerial vehicle (UAV)-to-UAV networking. The automatic alignment of directional antennas allows the transmission energy to focus in certain direction and significantly extends the communication range and rejects interference. Robust automatic alignment of directional antennas is not easy to achieve, considering practical issues such as the limited on-board sensing devices due to the physical constraints of UAV payload and power supplies, uncertain and varying UAV movement patterns, and unstable GPS and unknown communication environments. In this paper, we develop reinforcement learning (RL)-based online antenna control solutions for the ACDA system to conquer these challenges. The control solution adopts an uncertain UAV mobility modeling and intention estimation framework to capture and predict the uncertain intentions of UAV maneuvers and hence permit robust tracking. To account for an unstable GPS environment, the control solution features a learning of communication channel models to provide additional measurement signals in GPS-denied settings. A novel stochastic optimal control solution for nonlinear random switching dynamics is developed that integrates RL, an effective uncertainty evaluation method called multivariate probabilistic collocation method (MPCM), and unscented Kalman Filter (UKF). Simulation studies are conducted to illustrate and validate the proposed solutions.

Handheld mobile photography in very low light

Taking photographs in low light using a mobile phone is challenging and rarely produces pleasing results. Aside from the physical limits imposed by read noise and photon shot noise, these cameras are typically handheld, have small apertures and sensors, use mass-produced analog electronics that cannot easily be cooled, and are commonly used to photograph subjects that move, like children and pets. In this paper we describe a system for capturing clean, sharp, colorful photographs in light as low as 0.3 lux, where human vision becomes monochromatic and indistinct. To permit handheld photography without flash illumination, we capture, align, and combine multiple frames. Our system employs "motion metering", which uses an estimate of motion magnitudes (whether due to handshake or moving objects) to identify the number of frames and the per-frame exposure times that together minimize both noise and motion blur in a captured burst. We combine these frames using robust alignment and merging techniques that are specialized for high-noise imagery. To ensure accurate colors in such low light, we employ a learning-based auto white balancing algorithm. To prevent the photographs from looking like they were shot in daylight, we use tone mapping techniques inspired by illusionistic painting: increasing contrast, crushing shadows to black, and surrounding the scene with darkness. All of these processes are performed using the limited computational resources of a mobile device. Our system can be used by novice photographers to produce shareable pictures in a few seconds based on a single shutter press, even in environments so dim that humans cannot see clearly.

Face alignment using a 3D deeply-initialized ensemble of regression trees

Face alignment algorithms locate a set of landmark points in images of faces taken in unrestricted situations. State-of-the-art approaches typically fail or lose accuracy in the presence of occlusions, strong deformations, large pose variations and ambiguous configurations. In this paper we present 3DDE, a robust and efficient face alignment algorithm based on a coarse-to-fine cascade of ensembles of regression trees. It is initialized by robustly fitting a 3D face model to the probability maps produced by a convolutional neural network. With this initialization we address self-occlusions and large face rotations. Further, the regressor implicitly imposes a prior face shape on the solution, addressing occlusions and ambiguous face configurations. Its coarse-to-fine structure tackles the combinatorial explosion of parts deformation. In the experiments performed, 3DDE improves the state-of-the-art in 300W, COFW, AFLW and WFLW data sets. Finally, we perform cross-dataset experiments that reveal the existence of a significant data set bias in these benchmarks.

Performance assessment of displacement-field estimation of the human left atrium from 4D-CT images using the coherent point drift algorithm

Background:Cardiac four-dimensional computed tomography (4D-CT) imaging is a standard approach used to visualize left atrium (LA) deformation for clinical diagnosis. However, the quantitative evaluation of LA deformation from 4D-CT images is still a challenging task. We assess the performance of LA displacement-field estimation from 4D-CT images using the coherent point drift (CPD) algorithm, which is a robust point set alignment method based on the expectation–maximization (EM) algorithm. Method:Subject-specific LA surfaces at 20 phases/cardiac cycles were reconstructed from 4D-CT images and expressed as sets of triangular elements. The LA surface at the phase that maximized the LA surface area was assigned as the control LA surface and those at the other 19 phases were assigned as observed LA surfaces. The LA displacement-field was estimated by solving the alignment between the control and observation LA surfaces using CPD. Results:Global correspondences between the estimated and observed LA surfaces were successfully confirmed by quantitative evaluations using the Dice similarity coefficient and differences of surface area for all phases. The surface distances between the estimated and observed LA surfaces ranged within 2 mm, except at the left atrial appendage and boundaries, where incomplete data, such as missing or false detections, were included on the observed LA surface. We confirmed that the estimated LA surface displacement and its spatial distribution were anisotropic, which is consistent with existing clinical observations. Conclusion:These results highlight that the LA displacement field estimated by CPD robustly tracks global LA surface deformation observed in 4D-CT images.