Search

Most realtime human pose estimation approaches are based on detecting joint positions. Using the detected joint positions, the yaw and pitch of the limbs can be computed. However, the roll along the limb, which is critical for application such as sports analysis and computer animation, cannot be computed as this axis of rotation remains unobserved. In this paper we therefore introduce orientation keypoints, a novel approach for estimating the full position and rotation of skeletal joints, using only single-frame RGB images. Inspired by how motion-capture systems use a set of point markers to estimate full bone rotations, our method uses virtual markers to generate sufficient information to accurately infer rotations with simple post processing. The rotation predictions improve upon the best reported mean error for joint angles by 48% and achieves 93% accuracy across 15 bone rotations. The method also improves the current state-of-the-art results for joint positions by 14% as measured by MPJPE on the principle dataset, and generalizes well to in-the-wild datasets. [ABSTRACT FROM AUTHOR]

This paper reviews the novel concept of a controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offers useful extensions and applications. ControlVAE is a new variational autoencoder (VAE) framework that combines automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value. It leverages a non-linear PI controller, a variant of the proportional-integral-derivative (PID) controller, to dynamically tune the weight of the KL-divergence term in the evidence lower bound (ELBO) using the output KL-divergence as feedback. This allows us to precisely control the KL-divergence to a desired value (set point) that is effective in avoiding posterior collapse and learning disentangled representations. While prior work developed alternative techniques for controlling the KL divergence, we show that our PI controller has better stability properties and thus better convergence, thereby producing better disentangled representations from finite training data. In order to improve the ELBO of ControlVAE over that of the regular VAE, we provide a simplified theoretical analysis to inform the choice of set point for the KL-divergence of ControlVAE. We evaluate the proposed method on three tasks: image generation, language modeling, and disentangled representation learning. The results show that ControlVAE can achieve much better reconstruction quality than the other methods for comparable disentanglement. On the language modeling task, our method can avoid posterior collapse (KL vanishing) and improve the diversity of generated text. Moreover, it can change the optimization trajectory, improving the ELBO and the reconstruction quality for image generation. [ABSTRACT FROM AUTHOR]

Most realtime human pose estimation approaches are based on detecting joint positions. Using the detected joint positions, the yaw and pitch of the limbs can be computed. However, the roll along the limb, which is critical for application such as sports analysis and computer animation, cannot be computed as this axis of rotation remains unobserved. In this paper we therefore introduce orientation keypoints, a novel approach for estimating the full position and rotation of skeletal joints, using only single-frame RGB images. Inspired by how motion-capture systems use a set of point markers to estimate full bone rotations, our method uses virtual markers to generate sufficient information to accurately infer rotations with simple post processing. The rotation predictions improve upon the best reported mean error for joint angles by 48% and achieves 93% accuracy across 15 bone rotations. The method also improves the current state-of-the-art results for joint positions by 14% as measured by MPJPE on the principle dataset, and generalizes well to in-the-wild datasets. [ABSTRACT FROM AUTHOR]

This paper reviews the novel concept of a controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offers useful extensions and applications. ControlVAE is a new variational autoencoder (VAE) framework that combines automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value. It leverages a non-linear PI controller, a variant of the proportional-integral-derivative (PID) controller, to dynamically tune the weight of the KL-divergence term in the evidence lower bound (ELBO) using the output KL-divergence as feedback. This allows us to precisely control the KL-divergence to a desired value (set point) that is effective in avoiding posterior collapse and learning disentangled representations. While prior work developed alternative techniques for controlling the KL divergence, we show that our PI controller has better stability properties and thus better convergence, thereby producing better disentangled representations from finite training data. In order to improve the ELBO of ControlVAE over that of the regular VAE, we provide a simplified theoretical analysis to inform the choice of set point for the KL-divergence of ControlVAE. We evaluate the proposed method on three tasks: image generation, language modeling, and disentangled representation learning. The results show that ControlVAE can achieve much better reconstruction quality than the other methods for comparable disentanglement. On the language modeling task, our method can avoid posterior collapse (KL vanishing) and improve the diversity of generated text. Moreover, it can change the optimization trajectory, improving the ELBO and the reconstruction quality for image generation. [ABSTRACT FROM AUTHOR]

Heatmap regression has become the mainstream methodology for deep learning-based semantic landmark localization, including in facial landmark localization and human pose estimation. Though heatmap regression is robust to large variations in pose, illumination, and occlusion in unconstrained settings, it usually suffers from a sub-pixel localization problem. Specifically, considering that the activation point indices in heatmaps are always integers, quantization error thus appears when using heatmaps as the representation of numerical coordinates. Previous methods to overcome the sub-pixel localization problem usually rely on high-resolution heatmaps. As a result, there is always a trade-off between achieving localization accuracy and computational cost, where the computational complexity of heatmap regression depends on the heatmap resolution in a quadratic manner. In this paper, we formally analyze the quantization error of vanilla heatmap regression and propose a simple yet effective quantization system to address the sub-pixel localization problem. The proposed quantization system induced by the randomized rounding operation 1) encodes the fractional part of numerical coordinates into the ground truth heatmap using a probabilistic approach during training; and 2) decodes the predicted numerical coordinates from a set of activation points during testing. We prove that the proposed quantization system for heatmap regression is unbiased and lossless. Experimental results on popular facial landmark localization datasets (WFLW, 300W, COFW, and AFLW) and human pose estimation datasets (MPII and COCO) demonstrate the effectiveness of the proposed method for efficient and accurate semantic landmark localization. Code is available at http://github.com/baoshengyu/H3R. [ABSTRACT FROM AUTHOR]

The article presents the analytical derivation of the minimum dc link capacitance in single-phase front ends with active power factor correction (PFC) without hold-up time requirements. Such systems typically employ boost-type rectifiers; operate under restricted total harmonic distortion (THD) of the grid-side current. Moreover, PFC rectifiers must be capable of tolerating step-like zero-to-rated load power variations. It is well known that these two constraints contradict each other, posing nontrivial design challenges. The revealed value of minimum capacitance is expressed by an explicit function of grid voltage and frequency, converter rated power, dc link voltage reference, and grid current THD and voltage loop phase margin set points. Experimental results validate the proposed methodology, closely matching corresponding analytical predictions. [ABSTRACT FROM AUTHOR]

Estimating the pose of a calibrated camera relative to a 3D point set from one image is an important task in computer vision. Perspective-n-Point algorithms are often used if perfect 2D-3D correspondences are known. However, it is difficult to determine 2D-3D correspondences perfectly, and then the simultaneous pose and correspondence determination problem is needed to be solved. Early methods aimed to solve this problem by local optimization. Recently, several new methods are proposed to globally solve this problem by using branch-and-bound (BnB) method, but they tend to be slow because the time complexity of the BnB-based methods is exponential to the dimensionality of the parameter space, and they directly search the 6D parameter space. In this paper, we propose to decompose the joint searching into two separate searching processes by introducing a rotation invariant feature (RIF). Specifically, we construct RIFs from the original 3D and 2D point sets and search for the globally optimal translation to match these two RIFs first. Then, the original 3D point set is translated and matched with the 2D point set to find a globally optimal rotation. Experiments on challenging data show that the proposed method outperforms state-of-the-art methods in terms of both speed and accuracy. [ABSTRACT FROM AUTHOR]

Nowadays, a model predictive control has gained a lot of attractions for power converter. To overcome the defects of the conventional model predictive control and achieve better performance, this article presents a multivector model predictive power control (MV-MPPC) with low computational burden for the grid-tied quasi-Z-source inverter (qZSI). Compared with the conventional model predictive power control (MPPC) that adopts only one vector in one control period, the proposed MV-MPPC applies several vectors including two active vectors, one null vector, and one shoot-through (ST) vector to fulfill the expected performance for the grid-tied qZSI. By calculating the optimal duty ratios of the ST vector, the inductor current ripple can be greatly reduced. To eliminate the weighting factor, a modified sliding-mode control method for simultaneously controlling the capacitor voltage and the inductor current to their setting points is proposed. Furthermore, a quick and effective optimal sector selection method is given, which chooses the optimal sector through a look-up table instead of a bunch of complex calculations. Hence, the computational burden of the proposed MV-MPPC is decreased with significance. Both simulation and experimental results are shown to validate the effectiveness and the advantages of the proposed method. [ABSTRACT FROM AUTHOR]

In medical image analysis (MIA) and computer-assisted surgery (CAS), aligning two multiple point sets (PSs) together is an essential but also a challenging problem. For example, rigidly aligning multiple point sets into one common coordinate frame is a prerequisite for statistical shape modelling (SSM). Accurately aligning the pre-operative space with the intra-operative space in CAS is very crucial to successful interventions. In this article, we formally formulate the multiple generalized point set registration problem (MGPSR) in a probabilistic manner, where both the positional and the normal vectors are used. The six-dimensional vectors consisting of both positional and normal vectors are called as generalized points. In the formulated model, all the generalized PSs to be registered are considered to be the realizations of underlying unknown hybrid mixture models (HMMs). By assuming the independence of the positional and orientational vectors (i.e., the normal vectors), the probability density function (PDF) of an observed generalized point is computed as the product of Gaussian and Fisher distributions. Furthermore, to consider the anisotropic noise in surgical navigation, the positional error is assumed to obey a multi-variate Gaussian distribution. Finally, registering PSs is formulated as a maximum likelihood (ML) problem, and solved under the expectation maximization (EM) technique. By using more enriched information (i.e., the normal vectors), our algorithm is more robust to outliers. By treating all PSs equally, our algorithm does not bias towards any PS. To validate the proposed approach, extensive experiments have been conducted on surface points extracted from CT images of (i) a human femur bone model; (ii) a human pelvis bone model. Results demonstrate our algorithm’s high accuracy, robustness to noise and outliers. Note to Practitioners—This paper was motivated by solving the problem of registering two or more PSs. Most existing registration approaches use only the positional information associated with each point, and thus lacks robustness to noise and outliers. Three significant improvements are brought by our proposed approach. First, the normal vectors that can be extracted from the point sets are utilized in the registration. Second, the positional error distribution is assumed to be anisotropic and inhomogeneous. Third, all the PSs to be registered are treated equally that means no PS is considered as the model one. The registration problem is cast into a maximum likelihood (ML) problem and solved under the expectation maximization (EM) framework. We have demonstrated through extensive experiments that the proposed registration approach achieves significantly improved accuracy, robustness to noise and outliers. The algorithm is particularly suitable for biomedical applications involving the registration procedures, such as image-guided surgery. [ABSTRACT FROM AUTHOR]

In order to retain more feature information of local areas on a point cloud, local grouping and subsampling are the necessary data structuring steps in most hierarchical deep learning models. Due to the disorder nature of the points in a point cloud, the significant time cost may be consumed when grouping and subsampling the points, which consequently results in poor scalability. This paper proposes a fast data structuring method called PSNet (Point Structuring Net). PSNet transforms the spatial features of the points and matches them to the features of local areas in a point cloud. PSNet achieves grouping and sampling at the same time while the existing methods process sampling and grouping in two separate steps (such as using FPS plus kNN). PSNet performs feature transformation pointwise while the existing methods uses the spatial relationship among the points as the reference for grouping. Thanks to these features, PSNet has two important advantages: 1) the grouping and sampling results obtained by PSNet is stable and permutation invariant; and 2) PSNet can be easily parallelized. PSNet can replace the data structuring methods in the mainstream point cloud deep learning models in a plug-and-play manner. We have conducted extensive experiments. The results show that PSNet can improve the training and inference speed significantly while maintaining the model accuracy. [ABSTRACT FROM AUTHOR]

In this article, a coordinated control architecture is proposed that utilizes inverter-based distributed energy resources (DERs) and legacy controllers such as voltage regulators in a power distribution system and coordinates the reactive power support such that the voltage balance at a particular node of interest can be achieved. The approach is developed based on the alternating direction method of multipliers and the optimal control framework, where a primary control loop is used to provide the necessary reactive power set point to mitigate the voltage deviation and a secondary control loop is used to balance the reactive power from multiple devices such as DERs. The methodology is tested on the IEEE 123-bus distribution feeder with multiple three-phase DERs in coordination with a voltage regulator. It has been observed that the proposed architecture can reduce regulator tap operation, improve the voltage deviation (at least by 20%), and, at the same time, mitigate the negative effect of the reverse operation of the regulators. [ABSTRACT FROM AUTHOR]

The service of grid voltage regulation is required nowadays from inverter-based resources (IBRs) particularly at the lower voltage level. In the transmission network, this is easily managed by leveraging solely the reactive power (Q) capability of the IBR, but in distribution networks that are mix of $L$ and $r$ the voltage magnitude is coupled with both active (P) and reactive power injection. There are methods in the literature designed for these cases that utilize both P and Q in voltage regulation, but they usually require network and load data, which may not be readily available. Furthermore, they often disregard an apparent nonmonotonic relation between the inverter terminal voltage and the P/Q ratio risking instability. To fill this gap, this article introduces a network-agnostic P–Q adjustment technique for photovoltaic (PV) systems or other IBRs. The proposed technique tracks in a step-like manner the reference voltage set point if it is feasible, or the maximum grid voltage otherwise. This allows identification of the critical P/Q ratio without any prior information at the cost of limited voltage ripple due to a variable step-size strategy implemented. The superior performance of the proposed scheme is validated through simulations in MATLAB-Simulink in a reduced UKGDS 95-bus system and through lab experiments on a scaled down laboratory grade prototype. [ABSTRACT FROM AUTHOR]

3D point cloud registration is fragile to outliers, which are labeled as the points without corresponding points. To handle this problem, a widely adopted strategy is to estimate the relative pose based only on some accurate correspondences, which is achieved by building correspondences on the identified inliers or by selecting reliable ones. However, these approaches are usually complicated and time-consuming. By contrast, the virtual point-based methods learn the virtual corresponding points (VCPs) for all source points uniformly without distinguishing the outliers and the inliers. Although this strategy is time-efficient, the learned VCPs usually exhibit serious collapse degeneration due to insufficient supervision and the inherent distribution limitation. In this paper, we propose to exploit the best of both worlds and present a novel robust 3D point cloud registration framework. We follow the idea of the virtual point-based methods but learn a new type of virtual points called rectified virtual corresponding points (RCPs), which are defined as the point set with the same shape as the source and with the same pose as the target. Hence, a pair of consistent point clouds, i.e. source and RCPs, is formed by rectifying VCPs to RCPs (VRNet), through which reliable correspondences between source and RCPs can be accurately obtained. Since the relative pose between source and RCPs is the same as the relative pose between source and target, the input point clouds can be registered naturally. Specifically, we first construct the initial VCPs by using an estimated soft matching matrix to perform a weighted average on the target points. Then, we design a correction-walk module to learn an offset to rectify VCPs to RCPs, which effectively breaks the distribution limitation of VCPs. Finally, we develop a hybrid loss function to enforce the shape and geometry structure consistency of the learned RCPs and the source to provide sufficient supervision. Extensive experiments on several benchmark datasets demonstrate that our method achieves advanced registration performance and time-efficiency simultaneously. The code will be made public. [ABSTRACT FROM AUTHOR]

No proper norm exists to measure the distance between two object poses essentially because a general pose is defined by a rotation and a translation, and thus, it involves magnitudes with different units. As a means to solve this dimensional-inhomogeneity problem, the concept of characteristic length has been put forward in the area of kinematics. The idea consists of scaling translations according to this characteristic length and then approximating the corresponding displacement defining the object pose in ${\mathbb {R}}^3$ by a rotation in ${\mathbb {R}}^4$ , for which a norm exists. This article sheds new light on this kind of approximations which permits simplifying optimization problem whose cost functions involve translations and rotations simultaneously. A good example of this kind of problems is the pointcloud registration problem in which the optimal rotation and translation between two sets of corresponding 3-D point data, so that they are aligned/registered, have to be found. As a result, a simple closed-form formula for solving this problem is presented which is shown to be an attractive alternative to the previous approaches. [ABSTRACT FROM AUTHOR]

This article studies the fuzzy cluster-based point set registration (FuzzyPSReg). First, we propose a new metric based on Gustafson–Kessel (GK) fuzzy clustering to measure the alignment of two point clouds. Unlike the metric based on fuzzy c-means (FCM) clustering in our previous work, the GK-based metric includes orientation properties of the point clouds, thereby providing more information for registration. We then develop the registration quality assessment of the GK-based metric, which is more sensitive to small misalignments than that of the FCM-based metric. Next, by effectively combining the two metrics, we design two FuzzyPSReg strategies with global optimization. 1) FuzzyPSReg-SS, which extends our previous work and aligns two similar-sized point clouds with greatly improved efficiency. 2) FuzzyPSReg-O2S, which aligns two point clouds with a relatively large difference in size and can be used to estimate the pose of an object in a scene. In the experiment, we use different point clouds to test and compare the proposed method with state-of-the-art registration approaches. The results demonstrate the advantages and effectiveness of our method. [ABSTRACT FROM AUTHOR]

In this article, an incremental quantities distance protection using Park's transformation is proposed to increase the operation speed of distance protection. Based on the instantaneous voltage in abc frame approximate linear distribution along the AC transmission lines, this article proves that instantaneous voltage in dq frame still satisfies the approximate linear distribution along the AC transmission line. Then, the d-axis voltage components of fault point and setting point are used to determine the internal and external faults. In order to ensure that the presented distance protection can be applied to all fault types, a virtual three-phase system construction method is also presented. The fault point voltage construction method and low-pass filter design method are also discussed. Finally, a typical AC transmission system is developed in PSCAD/EMTDC to verify the performance of the proposed distance protection under different fault conditions. Simulation results indicate that the proposed incremental quantities distance protection has fast operation speed under internal metallic fault conditions and high security under external fault conditions. [ABSTRACT FROM AUTHOR]

The iterative closest point (ICP) algorithm and its variants are a fundamental technique for rigid registration between two point sets, with wide applications in different areas from robotics to 3D reconstruction. The main drawbacks for ICP are its slow convergence, as well as its sensitivity to outliers, missing data, and partial overlaps. Recent work such as Sparse ICP achieves robustness via sparsity optimization at the cost of computational speed. In this paper, we propose a new method for robust registration with fast convergence. First, we show that the classical point-to-point ICP can be treated as a majorization-minimization (MM) algorithm, and propose an Anderson acceleration approach to speed up its convergence. In addition, we introduce a robust error metric based on the Welsch’s function, which is minimized efficiently using the MM algorithm with Anderson acceleration. On challenging datasets with noises and partial overlaps, we achieve similar or better accuracy than Sparse ICP while being at least an order of magnitude faster. Finally, we extend the robust formulation to point-to-plane ICP, and solve the resulting problem using a similar Anderson-accelerated MM strategy. Our robust ICP methods improve the registration accuracy on benchmark datasets while being competitive in computational time. [ABSTRACT FROM AUTHOR]

In this work, we present a family of vector quantization schemes vqSGD (Vector-Quantized Stochastic Gradient Descent) that provide an asymptotic reduction in the communication cost with convergence guarantees in first-order distributed optimization. In the process we derive the following fundamental information theoretic fact: $\Theta \left({\frac {d}{R^{2}}}\right)$ bits are necessary and sufficient (up to an additive $O(\log d)$ term) to describe an unbiased estimator $\hat{\boldsymbol {g}}(\boldsymbol {g})$ for any $\boldsymbol {g}$ in the $d$ -dimensional unit sphere, under the constraint that $\| \hat{\boldsymbol {g}}(\boldsymbol {g})\|_{2}\le R$ almost surely, $R > 1$. In particular, we consider a randomized scheme based on the convex hull of a point set, that returns an unbiased estimator of a $d$ -dimensional gradient vector with almost surely bounded norm. We provide multiple efficient instances of our scheme, that are near optimal, and require $o(d)$ bits of communication at the expense of tolerable increase in error. The instances of our quantization scheme are obtained using well-known families of binary error-correcting codes and provide a smooth tradeoff between the communication and the estimation error of quantization. Furthermore, we show that vqSGD also offers automatic privacy guarantees. [ABSTRACT FROM AUTHOR]

We study generalized covering radii, a fundamental property of linear codes that characterizes the trade-off between storage, latency, and access in linear data-query protocols such as PIR. We prove lower and upper bounds on the generalized covering radii of Reed-Muller codes, as well as finding their exact value in certain extreme cases. With the application to linear data-query protocols in mind, we also construct a covering algorithm that gets as input a set of points in space, and find a corresponding set of codewords from the Reed-Muller code that are jointly not farther away from the input than the upper bound on the generalized covering radius of the code. We prove that the algorithm runs in time that is polynomial in the code parameters. [ABSTRACT FROM AUTHOR]

Multi-object tracking and segmentation (MOTS) is a derivative task of multi-object tracking (MOT). The new setting encourages the learning of more discriminative high-quality embeddings. In this paper, we focus on the problem of exploring the relationship between the segmenter and the tracker, and propose an efficient Object Point set Inductive Tracker (OPITrack) based on it. First, we discover that after a single attention layer, the high-dimensional, key point embedding will show feature averaging. To alleviate this phenomenon, we propose an embedding generalization training strategy for sparse training and dense testing. This strategy allows the network to increase randomness in training and encourages the tracker to learn more discriminative features. In addition, to learn the desired embedding space, we propose a general Trip-hard sample augmentation loss. The loss uses patches that are not distinguishable by the segmenter to join the feature learning and force the embedding network to learn the difference between false positives and true positives. Our method was validated on two MOTS benchmark datasets and achieved promising results. In addition, our OPITrack can achieve better performance for the raw model while costing less video memory (VRAM) at training time. [ABSTRACT FROM AUTHOR]

The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense point sets as the supervision, which makes them limited to be trained under synthetic paired training data and not suitable to be under real-scanned sparse data. However, it is expensive and tedious to obtain large numbers of paired sparse-dense point sets as supervision from real-scanned sparse data. To address this problem, we propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. Specifically, we propose a coarse-to-fine reconstruction framework, which contains two main components: point feature extraction and point feature expansion, respectively. In the point feature extraction, we integrate the self-attention module with the graph convolution network (GCN) to capture context information inside and among local regions simultaneously. In the point feature expansion, we introduce a hierarchically learnable folding strategy to generate upsampled point sets with learnable 2D grids. Moreover, to further optimize the noisy points in the generated point sets, we propose a novel self-projection optimization associated with uniform and reconstruction terms as a joint loss to facilitate the self-supervised point cloud upsampling. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performances to state-of-the-art supervised methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a relative pose estimation algorithm for micro-lens array (MLA)-based conventional light field (LF) cameras. First, by employing the matched LF-point pairs, we establish the LF-point-LF-point correspondence model to represent the correlation between LF features of the same 3D scene point in a pair of LFs. Then, we employ the proposed correspondence model to estimate the relative camera pose, which includes a linear solution and a non-linear optimization on manifold. Unlike prior related algorithms, which estimated relative poses based on the recovered depths of scene points, we adopt the estimated disparities to avoid the inaccuracy in recovering depths due to the ultra-small baseline between sub-aperture images of LF cameras. Experimental results on both simulated and real scene data have demonstrated the effectiveness of the proposed algorithm compared with classical as well as state-of-art relative pose estimation algorithms. [ABSTRACT FROM AUTHOR]

Designing and installing jigs and fixtures for new products are very costly tasks. In order to rapidly respond to frequent product changes in a manufacturing system, we developed a transformable pin array fixture system including reconfiguration planning software that finds the optimal position for mounting an assembly part and automatically generates a pin height control code. We first classified main fixturing quality factors such as type of contact, distance between a pin and a joining point, and part shape. We then formulate the part positioning problem as an alignment problem between the joining point set and the pin point set in the xy plane in consideration of the fixturing quality factors. A car door trim assembly module was used to verify the proposed method. Finite-element analysis results showed that in a car door trim assembly process such as ultrasonic welding and screwing, relocating an assembly part at the optimal position reduces its deformation. Note to Practitioners—Jigs and fixture systems are the fundamental manufacturing elements that are used for ensuring assembly quality. Traditionally, manufacturers have produced a small variety of products in massive quantities using dedicated jig and fixture systems. However, these dedicated workholding systems do not fit for the Today’s rapidly changing market. In order to enhance the reconfigurability of these systems, we propose a transformable pin array-based part fixturing system including part position optimization. Due to the system complexity, the assembly quality can be lower using the transformable fixtures than the conventional fixtures. Therefore, it is further necessary to develop a cost-effective reconfigurable fixture while preserving the assembly quality for the better chance of its industrial implementation. [ABSTRACT FROM AUTHOR]

In this work, we propose a strong two-stream baseline method referred to as GeometryMotion-Net for 3D action recognition. For efficient 3D action recognition, we first represent each point cloud sequence as a limited number of randomly sampled frames with each frame consisting of a sparse set of points. After that, we propose a new two-stream framework for effective 3D action recognition. For the geometry stream, we propose a new module to produce a virtual overall geometry point cloud by first merging all 3D points from these selected frames, and then we exploit local neighborhood information of each point in the feature space. In the motion stream, for any two neighboring point cloud frames, we also propose a new module to generate one virtual forward motion point cloud and one virtual backward motion point cloud. Specifically, for each point in the current frame, we first produce a set of 3D offset features relative to the neighboring points in the reference frame (i.e., the previous/subsequent frame) and then exploit local neighborhood information of this point in the offset feature space. Based on the newly generated virtual overall geometry point cloud and multiple virtual forward/backward motion point clouds, any existing point cloud analysis methods (e.g., PointNet) can be readily adopted for extracting discriminant geometry and bidirectional motion features in the geometry and motion streams, respectively, which are further aggregated to make our two-stream network trainable in an end-to-end fashion. Comprehensive experiments on both large-scale datasets (i.e. NTU RGB+D 60 and NTU RGB+D 120) and small-scale datasets (i.e., N-UCLA and UWA3DII) demonstrate the effectiveness and efficiency of our two-stream network for 3D action recognition. [ABSTRACT FROM AUTHOR]

SRM is one of the most attractive electric machines to be used as a S/G in the future MEA thanks to its special physical characteristics that facilitate its direct coupling to the propulsive unit; however, the controllability of the SRG at different operational points, imposed by the specific application, is critical. In this article, a novel active power control scheme which uses a vector-controlled SAF is proposed, in order to efficiently drive the SRG in a wide set point range. Considering the highly non-linearity of the SRM operational behavior, an adaptive phases’ magnetization regulation is applied, aiming at taking full advantage of the SRG's energy production capability, in compliance with the MEA power system specifications and limitations. The mathematical analysis is verified through simulation results, while the SRG concept under study is validated via a RT CHIL implementation. [ABSTRACT FROM AUTHOR]

A problem of the erroneous duality gap caused by the presence of symmetries is solved in this article utilizing the point group theory. The optimization problems are first divided into two classes based on their predisposition to suffer from this deficiency. Then, the classical problem of Q-factor minimization is shown in an example where the erroneous duality gap is eliminated by combining solutions from orthogonal subspaces. The validity of this treatment is demonstrated in a series of subsequent examples of increasing complexity spanning the wide variety of optimization problems, namely, minimum Q-factor, maximum antenna gain, minimum total active reflection coefficient (TARC), or maximum radiation efficiency with self-resonant constraint. They involve problems with algebraic and geometric multiplicities of the eigenmodes and are completed by an example introducing the selective modification of modal currents falling into one of the symmetry-conformal subspaces. The entire treatment is accompanied by a discussion of finite numerical precision, and mesh grid imperfections and their influence on the results. Finally, the robust and unified algorithm is proposed and discussed, including advanced topics, such as the uniqueness of the optimal solutions, dependence on the number of constraints, or an interpretation of the qualitative difference between the two classes of the optimization problems. [ABSTRACT FROM AUTHOR]

In predictive transform video coding, optimal bit allocation and quantization parameter (QP) estimation are important to control the bit rate of blocks, frames and the whole sequence. Common solutions to this problem rely on trained models to approximate the rate-distortion (R-D) characteristics of the video content during coding. Moreover, these solutions are mainly targeted for natural content sequences, whose characteristics differ greatly from those of screen content (SC) sequences. In this article, we depart from such trained R-D models and propose a low-complexity RC method for SC sequences that leverages the availability of information about the R-D characteristics of previously coded blocks within a frame. Namely, our method first allocates bits at the frame- and block-levels based on their motion and texture characteristics. It then approximates the R-D and R-QP curves of each block by a set control points and random sample consensus (RANSAC). Finally, it computes the appropriate block-level QP values to attain a target bit rate with the minimum distortion possible. The proposed RC method is embedded into a standard High-Efficiency Video Coding (H.265/HEVC) encoder and evaluated on several SC sequences. Our results show that our method not only attains better R-D performance than that of H.265/HEVC and other methods designed for SC sequences but also attains a more constant and higher reconstruction quality on all frames. [ABSTRACT FROM AUTHOR]

Due to the limitation of the satellite attitude measurement accuracy and the system servo control error of the payload scanning mechanism, an optimal use of Micro-Wave Radiation Imager (MWRI) observations requires high geolocation accuracy. In the operational system, the MWRI geolocation accuracy reaches 1 pixel, and there still exists room for improvement. In this article, we improve upon the coastline inflection point method (CIM) and propose to assign the accurate correspondence by employing a nonrigid point set registration method. First, the method identifies a set of latent variables to recognize outliers and then applies nonparametric geometric constraints to the correspondence as a priori distribution. Second, the maximum a posteriori (MAP) estimation is applied by the expectation–maximization (EM) algorithm to obtain correct inliers. The comparison with other methods demonstrates that the proposed method can provide more accurate estimation of geolocation bias. In addition, the pixel error and changes in spacecraft attitude with the long-term geolocation data in FY-3C MWRI before and after correction were analyzed during the period from April 1 to August 30, 2018. The results have shown that the geolocation errors are reduced from [0.50, 0.60] pixels to [0.20, 0.33] pixels in the along- and cross-track directions after the attitude correction. In addition, the reduction of the standard deviation shows that the geolocation quality of MWRI is improved. [ABSTRACT FROM AUTHOR]

Nonrigid point set (PS) registration is an outstanding and fundamental problem in the fields of robotics, computer vision, medical image analysis, and image-guided surgery (IGS). The aim of a nonrigid registration problem is to align together two point sets where one has been deformed. The assumption of isotropic localization error is shared in the previous nonrigid registration algorithms. In this article, we have derived and presented a novel nonrigid registration algorithm, where the position localization error (PLE) is generalized to be anisotropic, which means that the error distribution is not the same in different spatial directions. The motivation of considering the anisotropic characteristic is that the PLE is actually different in three spatial directions in real applications of registrations, such as IGS. Mathematically, the difficulty in dealing with the anisotropic error case comes from the change from a standard deviation that is a scalar to a covariance matrix. The formulas for updating the parameters in both expectation and maximization steps are derived. More specifically, in the expectation step, we compute the posterior probabilities that represent the correspondences between points in two PSs. In the maximization step, given the current posteriors, the covariance matrix of the PLE and the nonrigid transformation are updated. To further speed up the proposed algorithm, the low-rank approximation variation of our method is also presented. We have demonstrated through experiments on both general and medical data sets (corrupted with noise) that the proposed algorithm outperforms the state-of-the-art ones in terms of registration accuracy and robustness to noise. More specifically, all the experimental results have passed the statistical tests at the 5% significance level. Note to Practitioners—This article was motivated by solving the problem of nonrigidly registering two point sets where one has been deformed and corrupted with anisotropic noise. Most existing registration methods generally assume the positional error to be the same in all directions, which in fact is not the case in real scenarios. This article presents a new robust method that assumes the positional error to be anisotropic, which is the case in point sets coming from the stereo reconstruction. The nonrigid registration problem is formulated as a maximum-likelihood (ML) problem and solved with the expectation–maximization (EM) technique. We have demonstrated through extensive experiments on both general and medical data sets that the proposed registration algorithm achieves significantly improved accuracy, robustness to noise, and outliers compared with state-of-the-art algorithms. The algorithm is particularly suitable for biomedical applications involving the registration, such as medical imaging and image-guided surgery (IGS). [ABSTRACT FROM AUTHOR]

Registering two point sets (PSs) is an essential problem in medical robotics and computer-assisted surgery (CAS). As one typical example, in computer-assisted orthopedic surgery (CAOS), the preoperative scan has to be aligned with the intraoperative scan accurately. In this article, we first formally formulate the generalized PS registration problem in a probabilistic manner. Especially, not only positional but also orientational information is incorporated into the registration. Notably, the positional error is assumed to obey a multivariate Gaussian distribution to accommodate the anisotropic noise. The expectation–maximization (EM) framework is utilized to solve the maximum likelihood (ML) problem. In the E-step, the correspondence probabilities between points in two generalized PSs are computed. In the M-step, the constrained optimization problem with respect to the rigid transformation matrix is reformulated as an unconstrained one. This is achieved by utilizing the Rodrigues parameterization to represent the rotation matrix. Both extensive simulated and real experiments are conducted to validate the proposed algorithm by comparing it with state-of-the-art registration methods. Note to Practitioners—This article was motivated by considering the anisotropic positional uncertainty into the rigid point set (PS) registration in the application of preoperative-to-intraoperative registration within image-guided surgery. We provide iterative solutions that compute the rotation and translation vector that aligns two 3-D PSs. The correspondences between points in two PSs are not known and regarded as hidden variables in the optimization process. Expectation–maximization technique is utilized to solve the maximum likelihood problem. We have demonstrated through experiments that our proposed approach can achieve lower registration error values than the compared state-of-the-art registration methods on various data sets. The readers should note that the proposed method is particularly suitable for cases that anisotropic noise is involved. [ABSTRACT FROM AUTHOR]

This study presents a new point set registration method to align 3D range scans. In our method, fuzzy clusters are utilized to represent a scan, and the registration of two given scans is realized by minimizing a fuzzy weighted sum of the distances between their fuzzy cluster centers. This fuzzy cluster-based metric has a broad basin of convergence and is robust to noise. Moreover, this metric provides analytic gradients, allowing standard gradient-based algorithms to be applied for optimization. Based on this metric, the outlier issues are addressed. In addition, for the first time in rigid point set registration, a registration quality assessment in the absence of ground truth is provided. Furthermore, given specified rotation and translation spaces, we derive the upper and lower bounds of the fuzzy cluster-based metric and develop a branch-and-bound (BnB)-based optimization scheme, which can globally minimize the metric regardless of the initialization. This optimization scheme is performed in an efficient coarse-to-fine fashion: First, fuzzy clustering is applied to describe each of the two given scans by a small number of fuzzy clusters. Then, a global search, which integrates BnB and gradient-based algorithms, is implemented to achieve a coarse alignment for the two scans. During the global search, the registration quality assessment offers a beneficial stop criterion to detect whether a good result is obtained. Afterwards, a relatively large number of points of the two scans are directly taken as the fuzzy cluster centers, and then, the coarse solution is refined to be an exact alignment using the gradient-based local convergence. Compared to existing counterparts, this optimization scheme makes a large improvement in terms of robustness and efficiency by virtue of the fuzzy cluster-based metric and the registration quality assessment. In the experiments, the registration results of several 3D range scan pairs demonstrate the accuracy and effectiveness of the proposed method, as well as its superiority to state-of-the-art registration approaches. [ABSTRACT FROM AUTHOR]

A distributed optimization problem (DOP) with affine equality and convex inequality constraints is studied in this article. First, the consensus constraint of the considered DOP is relaxed and a related approximate DOP (ADOP) is presented. It is proved that the optimal solutions of the ADOP (i.e., the near-optimal solutions of the original DOP) are able to approach the optimal solutions of the original DOP. A continuous-time algorithm is proposed for the ADOP and it is demonstrated that the state solution of the presented algorithm converges to the critical point set of the ADOP with general locally Lipschitz continuous objective functions. This means the presented algorithm is efficient for distributed nonconvex optimization problems. Particularly, when the objective functions are convex ones, the state solution of the presented algorithm is further proved to converge to a near-optimal solution of the original DOP. One illustrative example and an application on load sharing problems are shown to validate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper discusses the impact of discrete secondary controllers on the dynamic response of power systems. The idea of the paper originates from the observation that there is a range of values, from few tens of seconds to few minutes, of the execution cycles of conventional automatic generation control (AGC) that leads to a limit cycle. Below and above this range the system is stable. This is certainly not a problem in practice as the AGC updates the power set points of generating units every few seconds. However, this phenomenon has interesting consequences if one considers real-time electricity markets with short dispatch periods (i.e., 5 minutes) as these markets can be modeled as a sort of AGC. The paper first provides a formal analogy between conventional AGC and real-time electricity markets. Then it shows that the discretization-driven instability exists if the system includes a real-time electricity market modeled as secondary frequency controller. Finally, the paper discusses the impact of the combined effect of high wind generation shares and discrete secondary controllers on power system dynamics. [ABSTRACT FROM AUTHOR]

Non-rigid point set registration is the process of transforming a shape represented as a point set into a shape matching another shape. In this paper, we propose an acceleration method for solving non-rigid point set registration problems. We accelerate non-rigid registration by dividing it into three steps: i) downsampling of point sets; ii) non-rigid registration of downsampled point sets; and iii) interpolation of shape deformation vectors corresponding to points removed during downsampling. To register downsampled point sets, we use a registration algorithm based on a prior distribution, called motion coherence prior. Using the same prior, we derive an interpolation method interpreted as Gaussian process regression. Through numerical experiments, we demonstrate that our algorithm registers point sets containing over ten million points. We also show that our algorithm reduces computing time more radically than a state-of-the-art acceleration algorithm. [ABSTRACT FROM AUTHOR]

Point set registration (PSR) is an essential problem in the field of surgical navigation and augmented reality (AR). In surgical navigation, the aim of registration is mapping the pre-operative space to the intra-operative space. This article introduces a reliable hybrid mixture model, in which the reliability of the normal vectors in the generalized point set (GPS) is examined and exploited. The motivation of considering the reliability of orientation information is that normal vectors cannot be estimated or measured accurately in the clinic. The point set (PS) is divided into two subsets according to the reliability of normal vectors. PSR is cast into the maximum likelihood estimation (MLE) problem. The expectation maximization (EM) framework is used to solve the MLE problem. In the E-step, the posterior probabilities between points in two PSs are computed. In the M-step, the transformation matrix and model components are updated by optimizing the objective function. We have demonstrated through extensive experiments on the human femur bone PS that the proposed algorithm outperforms the state-of-the-art ones in terms of accuracy, robustness, and convergence speed. [ABSTRACT FROM AUTHOR]

For communication targets in a specific network, position is of great significance to recognize each of the targets. However, as one of the ways to obtain positions of communication transmitters, passive location has several problems such as uncertainty in the reception of communication signals and a low accuracy, which greatly hinder the use of recursive filtering algorithms like the extended Kalman filter. In this article, a positions-only clustering algorithm suited for passive location data of multiple communication transmitters is proposed. The most innovative idea of this method consists of introducing two types of classes, the single-element class and the multiple-element class, into the clustering process. Four clustering paths having different priorities are herein thoroughly described. For different paths, different criteria based on distance or motion continuity are available. With the help of this method, different communication targets can be recognized and their motion states and moving trails can be determined. And tests with practically collected data show that this method has the potential to relink separated groups of location points which should have belonged to the same target, as well as to distinguish between traces of two motional targets that are close to each other. [ABSTRACT FROM AUTHOR]

During the production process of electronic products, the accuracy of chip component placement on printed circuit boards is crucial and directly affects the realization of product functions. This article introduces a rectangular pin part positioning method based on point set registration to obtain the exact position of the chip component during the placement process. The model point set is built from the component’s datasheet. The feature points extracted from the component image are filtered according to the structure feature and the reckon angle to construct a data point set. A rigid point set registration algorithm is used to solve the alignment problem between these two point sets to obtain the offset and rotation angle. Compared with the Halcon algorithm, the Samsung method, and the state-of-the-art method, the positioning results show an advantage. [ABSTRACT FROM AUTHOR]

We are often interested in clustering objects that evolve over time and identifying solutions to the clustering problem for every time step. Evolutionary clustering provides insight into cluster evolution and temporal changes in cluster memberships while enabling performance superior to that achieved by independently clustering data collected at different time points. In this article we introduce evolutionary affinity propagation (EAP), an evolutionary clustering algorithm that groups data points by exchanging messages on a factor graph. EAP promotes temporal smoothness of the solution to clustering time-evolving data by linking the nodes of the factor graph that are associated with adjacent data snapshots, and introduces consensus nodes to enable cluster tracking and identification of cluster births and deaths. Unlike existing evolutionary clustering methods that require additional processing to approximate the number of clusters or match them across time, EAP determines the number of clusters and tracks them automatically. A comparison with existing methods on simulated and experimental data demonstrates effectiveness of the proposed EAP algorithm. [ABSTRACT FROM AUTHOR]

Registration is an essential problem in image-guided surgery (IGS) since it brings different involved coordinate frames together. Nonrigid or deformable registration still faces many challenges, such as two point sets (PSs) are partially overlapped. To tackle the challenges in the nonrigid registration, we introduce a new two-step point-based registration pipeline that includes two steps. In the first step, the rigid transformation between the two spaces is recovered where the orientation vectors are adopted. In the second step, built on the nonrigid coherent point drift (CPD) approach, the anisotropic positional noise is also assumed. Registration results on the human liver verify the proposed approach’ great improvements over the other methods. First, the rotation and translation are recovered with smaller error values than the existing methods. Second, our registration method’s performance is much more robust to the partial overlapping between two PSs. Third, the two-step registration framework achieves the best performances in most test cases when there is a localization error in acquiring the intraoperative data. Note to Practitioners—A novel registration approach is presented for image-guided liver surgery (LGLS). Compared with existing nonrigid registration methods, two significant changes (or improvements) exist in the proposed registration framework: 1) the normal vectors are extracted and utilized in the rigid registration step and 2) the anisotropic positional uncertainties are considered. In both steps, the registration problems are formulated as a maximum likelihood (ML) problems and dealt with the expectation-maximization (EM) technique. In both steps, the matrix form of the updated positional covariance is provided and can speed up the computational process. The readers are reminded that with extra information and a more general positional error assumption, our approach demonstrates improved performances in the case of partial-to-full alignment. [ABSTRACT FROM AUTHOR]

Due to significant geometric distortions and illumination differences, developing techniques for high precision and robust multisource remote sensing image registration poses a great challenge. This article presents an iterative image registration approach, called iterative scale-invariant feature transform (ISIFT) for remote sensing images, which extends the traditional scale-invariant feature transform (SIFT)-based registration system to a close-feedback SIFT system that includes a rectification feedback loop to update rectified parameters in an iterative manner. Its key idea uses consistent feature point sets obtained by maximum similarity to calculate new alignment parameters to rectify the current sensed image and the resulting rectified sensed image is then fed back to update and replace the current sensed image as a new sensed image to reimplement SIFT for next iteration. The same process is repeated iteratively until an automatic stopping rule is satisfied. To evaluate the performance of ISIFT, both the simulated and real images are used for experiments for the validation of ISIFT. In addition, several data sets are particularly designed to conduct a comparative study and analysis with existing state-of-the-art methods. Furthermore, experiments with different rotation are also performed to verify the adaptability of ISIFT under different rotation distortions. The experimental results demonstrate that ISIFT improves performance and produces better registration accuracy than traditional SIFT-based methods and existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Skyline queries are important in many application domains. In this paper, we propose a novel structure Skyline Diagram, which given a set of points, partitions the plane into a set of regions, referred to as skyline polyominos. All query points in the same skyline polyomino have the same skyline query results. Similar to $k$ k th-order Voronoi diagram commonly used to facilitate $k$ k nearest neighbor ($k$ k NN) queries, skyline diagram can be used to facilitate skyline queries and many other applications. However, it may be computationally expensive to build the skyline diagram. By exploiting some interesting properties of skyline, we present several efficient algorithms for building the diagram with respect to three kinds of skyline queries, quadrant, global, and dynamic skylines. In addition, we propose an approximate skyline diagram which can significantly reduce the space cost. Experimental results on both real and synthetic datasets show that our algorithms are efficient and scalable. [ABSTRACT FROM AUTHOR]

3D reconstruction of deformable objects using inter-image visual motion from monocular images has been studied under Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM). Most methods have been developed for simple deformation models, primarily isometry. They may treat a surface as a discrete set of points and draw constraints from the points only or they may use a non-parametric representation and use both points and differentials to express constraints. We propose a differential framework based on Cartan's theory of connections and moving frames. It is applicable to SfT and NRSfM, and to deformation models other than isometry. It utilises infinitesimal-level assumptions on the surface's geometry and mappings. It has the following properties. 1) It allows one to derive existing solutions in a simpler way. 2) It models SfT and NRSfM in a unified way. 3) It allows us to introduce a new skewless deformation model and solve SfT and NRSfM for it. 4) It facilitates a generic solution to SfT which does not require deformation modeling. Our framework is complete: it solves deformable 3D reconstruction for a whole class of algebraic deformation models including isometry. We compared our solutions with the state-of-the-art methods and show that ours outperform in terms of both accuracy and computation time. [ABSTRACT FROM AUTHOR]

How to accurately register point sets still remains a challenging task, due to some unfavorable factors. In this article, a robust point set registration approach is proposed based on the Gaussian mixture model (GMM) with multiple effective constraints. The GMM is established by wrapping a model point set to a target point set, via a spatial transformation. Instead of a displacement model, the spatial transformation is decomposed as two types of transformations, an affine transformation and a nonaffine deformation. For the affine transformation, a constraint term of the parameter vector is applied to improve the robustness and efficiency. In order to enforce the smoothness, the square norm of the kernel Hilbert space is adopted as a coherent constraint for the nonaffine deformation. Moreover, the manifold regularization is utilized as a constraint in the proposed model, to capture the spatial geometry of point sets. In addition, the expectation-maximization algorithm is developed to solve the unknown variables of the proposed model. Compared to the state-of-the-art approaches, the proposed model is more robust to deformation and rotation, due to the use of multiple effective constraints. Experimental results on several widely used data sets demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

The iterative closest point (ICP) algorithm is one of the most widely used methods for point sets’ registration. However, ICP is very sensitive to the selection of initial points and is easy to fall into local optimum. To address this problem, many techniques have been developed. In this study, a two-step registration method is proposed for two 3-D point sets’ registration, which is achieved by a combination of rough and fine registrations. Specifically, a multidiscriminant parameter feature (MDPF) extraction approach is developed and embedded into the rough registration stage in order to find new corresponding point pairs for the fine registration. Three geometric features are chosen after experimental investigation for key points selection. By using the threshold discriminant condition to determine the key points and the distance constraint to eliminate the wrong point pairs, the feature points can be extracted, and the final transform parameters can be derived based on these feature points. In order to improve the computational efficiency for fine registration, the center of gravity is created to find the closest point in solving the transformation matrix, which is especially beneficial for registering complex surfaces. Experimental results show that the proposed method outperforms the traditional ICP approach and some typical existing improved algorithms in terms of the root-mean-square error (RMSE), the total number of feature points, and the execution time. In particular, the performance is improved 40% in terms of the RMSE and 50% in terms of the execution time in comparison with ICP on some benchmark data sets. Experiments also demonstrate that reliable reconstruction results can be obtained for both real outdoor and indoor environments. [ABSTRACT FROM AUTHOR]

Computerized registration between maxillofacial cone-beam computed tomography (CT) images and a scanned dental model is an essential prerequisite for surgical planning for dental implants or orthognathic surgery. We propose a novel method that performs fully automatic registration between a cone-beam CT image and an optically scanned model. To build a robust and automatic initial registration method, deep pose regression neural networks are applied in a reduced domain (i.e., two-dimensional image). Subsequently, fine registration is performed using optimal clusters. A majority voting system achieves globally optimal transformations while each cluster attempts to optimize local transformation parameters. The coherency of clusters determines their candidacy for the optimal cluster set. The outlying regions in the iso-surface are effectively removed based on the consensus among the optimal clusters. The accuracy of registration is evaluated based on the Euclidean distance of 10 landmarks on a scanned model, which have been annotated by experts in the field. The experiments show that the registration accuracy of the proposed method, measured based on the landmark distance, outperforms the best performing existing method by 33.09%. In addition to achieving high accuracy, our proposed method neither requires human interactions nor priors (e.g., iso-surface extraction). The primary significance of our study is twofold: 1) the employment of lightweight neural networks, which indicates the applicability of neural networks in extracting pose cues that can be easily obtained and 2) the introduction of an optimal cluster-based registration method that can avoid metal artifacts during the matching procedures. [ABSTRACT FROM AUTHOR]