Showing papers on "Affine transformation published in 2021"

Dimensionality reduction and classification of hyperspectral image via multi-structure unified discriminative embedding

Abstract: Graph can achieve good performance to extract the low-dimensional features of hyperspectral image (HSI). However, the present graph-based methods just consider the individual information of each sample in a certain characteristic, which is very difficult to represent the intrinsic properties of HSI for the complex imaging condition. To better represent the low-dimensional features of HSI, we propose a multi-structure unified discriminative embedding (MUDE) method which considers the neighborhood, tangential, and statistical properties of each sample in HSI to achieve the complementarity of different characteristics. In MUDE, we design the intraclass and interclass neighborhood structure graphs with the local reconstruction structure of each sample, meanwhile we also utilize the adaptive tangential affine combination structure to construct the intraclass and interclass tangential structure graphs. To further enhance the discriminating performance between different classes, we consider the influence of the statistical distribution difference for each sample to develop an interclass Gaussian weighted scatter model. Then, an embedding objective function is constructed to enhance the intraclass compactness and the interclass separability and obtain more discriminative features for HSI classification. Experiments on three real HSI data sets show the proposed method can make full use of the structure information of each sample in different characteristics to achieve the complementarity of different features and improve the classification performance of HSI compared with the state-of-the-art methods.

Affine Transformation-Enhanced Multifactorial Optimization for Heterogeneous Problems

Abstract: Evolutionary multitasking (EMT) is a newly emerging research topic in the community of evolutionary computation, which aims to improve the convergence characteristic across multiple distinct optimization tasks simultaneously by triggering knowledge transfer among them. Unfortunately, most of the existing EMT algorithms are only capable of boosting the optimization performance for homogeneous problems which explicitly share the same (or similar) fitness landscapes. Seldom efforts have been devoted to generalize the EMT for solving heterogeneous problems. A few preliminary studies employ domain adaptation techniques to enhance the transferability between two distinct tasks. However, almost all of these methods encounter a severe issue which is the so-called degradation of intertask mapping. Keeping this in mind, a novel rank loss function for acquiring a superior intertask mapping is proposed in this article. In particular, with an evolutionary-path-based representation model for optimization instance, an analytical solution of affine transformation for bridging the gap between two distinct problems is mathematically derived from the proposed rank loss function. It is worth mentioning that the proposed mapping-based transferability enhancement technique can be seamlessly embedded into an EMT paradigm. Finally, the efficacy of our proposed method against several state-of-the-art EMTs is verified experimentally on a number of synthetic multitasking and many-tasking benchmark problems, as well as a practical case study.

Adaptive Control Barrier Functions

Abstract: It has been shown that optimizing quadratic costs while stabilizing affine control systems to desired (sets of) states subject to state and control constraints can be reduced to a sequence of Quadratic Programs (QPs) by using Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). In this paper, we introduce Adaptive CBFs (AdaCBFs) that can accommodate time-varying control bounds and noise in the system dynamics,while also guaranteeing the feasibility of the QPs, which is a challenging problem in current approaches. We propose two different types of AdaCBFs: Parameter-Adaptive CBF (PACBF) and Relaxation-Adaptive CBF (RACBF). Central to AdaCBFs is the introduction of appropriate time-varying functions to modify the definition of a common CBF. These time-varying functions are treated as High Order CBFs (HOCBFs) with their own auxiliary dynamics, which are stabilized by CLFs. We demonstrate the advantages of using AdaCBFs over the existing CBF techniques by applying both the PACBF-based method and the RACBF-based method to a cruise control problem with time-varying road conditions and noise in the system dynamics, and compare their relative performance

Stereoscopic Image Description with Trinion Fractional-Order Continuous Orthogonal Moments

Abstract: Some research progress has been made on fractional-order continuous orthogonal moments (FrCOMs) in the past two years. Compared with integer-order continuous orthogonal moments (InCOMs), FrCOMs increase the number of affine invariants and effectively improve numerical stability. However, the existing types of FrCOMs are still very limited, of which all are planar image oriented. No report on stereoscopic images is available yet. To this end, in this paper, FrCOMs corresponding to various types of InCOMs are first deduced, and then, they are combined with trinion theory to construct trinion FrCOMs (TFrCOMs) applicable to stereoscopic images. Furthermore, the reconstruction performance and geometric invariance of TFrCOMs are analyzed theoretically and experimentally. Finally, an application in the stereoscopic image zero-watermarking algorithm is investigated to verify the superior performance of TFrCOMs.

Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training

Abstract: In this work, we propose a novel one-stage and keypoint-based framework for monocular 3D object detection using only RGB images, called KM3D-Net. 2D detection only requires a deep neural network to predict 2D properties of objects, as it is a semanticity-aware task. For image-based 3D detection, we argue that the combination of a deep neural network and geometric constraints are needed to synergistically estimate appearance-related and spatial-related information. Here, we design a fully convolutional model to predict object keypoints, dimension, and orientation, and combine these with perspective geometry constraints to compute position attributes. Further, we reformulate the geometric constraints as a differentiable version and embed this in the network to reduce running time while maintaining the consistency of model outputs in an end-to-end fashion. Benefiting from this simple structure, we propose an effective semi-supervised training strategy for settings where labeled training data are scarce. In this strategy, we enforce a consensus prediction of two shared-weights KM3D-Net for the same unlabeled image under different input augmentation conditions and network regularization. In particular, we unify the coordinate-dependent augmentations as the affine transformation for the differential recovering position of objects, and propose a keypoint-dropout module for network regularization. Our model only requires RGB images, without synthetic data, instance segmentation, CAD model, or depth generator. Extensive experiments on the popular KITTI 3D detection dataset indicate that the KM3D-Net surpasses state-of-the-art methods by a large margin in both efficiency and accuracy. And also, to the best of our knowledge, this is the first application of semi-supervised learning in monocular 3D object detection. We surpass most of the previous fully supervised methods with only 13% labeled data on KITTI.

Event-Triggered Optimal Dynamic Formation of Heterogeneous Affine Nonlinear Multiagent Systems

Abstract: This article studies an optimal dynamic formation problem for heterogeneous affine nonlinear systems. The nonidenticality in agents and the requirement for dynamic spatial reconfiguration make it a challenging task to coordinate different types of agents to maintain an optimized formation shape. In an architecture of event-triggered decision and control, this article investigates how to fulfill dynamic formation by distributively optimizing a team cost function. The basic idea is to design a decision unit for each agent to generate an implicit trajectory as a servo signal, based on which a control unit is designed with a displacement-gradient-based law to achieve the desired local solution. Typical heterogeneous characteristics including different nonlinearities and nonidentical dimensions are dealt with in a unified framework. It is shown that with the proposed triggering mechanisms, the optimal dynamic formation problem can be solved by a distributed control law with only intermittent communication. In theory, the properties of convergence of trajectory tracking errors, optimality of the team solution, and Zeno-freeness of event-triggered mechanisms are proved. Two simulation examples are given to verify the proposed method.

Affine Transformed IT2 Fuzzy Event-Triggered Control Under Deception Attacks

Abstract: Stabilization of type-2 fuzzy system in the presence of cyber attacks is investigated in this article. For a practical application, a class of nonlinear system can be represented by an interval type-2 fuzzy system through a set of membership functions. Unlike existing schemes, 1) affine membership functions are considered in the controller design; moreover, 2) a robust adaptive event-triggered control is proposed to avoid the unwanted triggering events, which makes the proposed scheme more reliable and relaxes the conservativeness of stability analysis.In the numerical simulation, the mass–spring–damper system and the tracking control system are considered to illustrate the robustness and effectiveness of the proposed approach.

Fuzzy-Affine-Model-Based Output Feedback Dynamic Sliding Mode Controller Design of Nonlinear Systems

Abstract: This paper investigates the problem of output feedback sliding mode control (SMC) for a class of uncertain nonlinear systems through Takagi–Sugeno fuzzy affine models. By adopting a state-input augmentation method, a descriptor system is first constructed to characterize the dynamical properties of the sliding motion. Based on a common quadratic Lyapunov function and piecewise quadratic Lyapunov functions, sufficient conditions for asymptotic stability analysis of the sliding motion are obtained with some convexification techniques. An output feedback dynamic SMC design scheme is proposed to force the states of the resulting closed-loop system onto the sliding surface locally in finite time. Two simulation examples are finally shown to illustrate the effectiveness of the proposed approaches.

Asynchronous Sampled-Data Filtering Design for Fuzzy-Affine-Model-Based Stochastic Nonlinear Systems

Abstract: This article studies the asynchronous sampled-data filtering design problem for Ito stochastic nonlinear systems via Takagi–Sugeno fuzzy-affine models. The sample-and-hold behavior of the measurement output is described by an input delay method. Based on a novel piecewise quadratic Lyapunov–Krasovskii functional, some new results on the asynchronous sampled-data filtering design are proposed through a linearization procedure by using some convexification techniques. Simulation studies are given to illustrate the effectiveness of the proposed method.

A fusion-domain color image watermarking based on Haar transform and image correction

Abstract: The leapfrog development of computer technology has greatly enhanced the breadth of information dissemination. As a larger information carrier, color image becomes more and more popular, but the copyright protection problem becomes more and more serious. To solve this problem, this paper proposes a fusion-domain color watermarking based on Haar transform and image correction. Firstly, the maximum energy coefficient of Haar transform is directly obtained in spatial domain. Then, the coefficient is quantified with the help of variable quantization steps to embed the color watermark that encrypted by affine transform. If the watermarked image is processed by geometric attack, then the attacked image can be corrected by using of the geometric properties. Finally, the inverse embedding process is performed to extract the watermark. The performances of the proposed method are shown as follows: 1) all PSNR (Peak Signal-to-Noise Ratio) values are greater than 40 dB; 2) all SSIM (Structural Similarity Index Metric) values are greater than 0.96; 3) most NC (Normalized Cross-correlation) values are more than 0.9; 4) the key space is more than 2432; 5) the maximum embedded capacity is 0.25bpp; 6) the running time is about 6 s. Compared with the related methods, the experimental results show that the proposed method is feasible and has good performance.

Scaled Simplex Representation for Subspace Clustering

Abstract: The self-expressive property of data points, that is, each data point can be linearly represented by the other data points in the same subspace, has proven effective in leading subspace clustering (SC) methods. Most self-expressive methods usually construct a feasible affinity matrix from a coefficient matrix, obtained by solving an optimization problem. However, the negative entries in the coefficient matrix are forced to be positive when constructing the affinity matrix via exponentiation, absolute symmetrization, or squaring operations. This consequently damages the inherent correlations among the data. Besides, the affine constraint used in these methods is not flexible enough for practical applications. To overcome these problems, in this article, we introduce a scaled simplex representation (SSR) for the SC problem. Specifically, the non-negative constraint is used to make the coefficient matrix physically meaningful, and the coefficient vector is constrained to be summed up to a scalar $s to make it more discriminative. The proposed SSR-based SC (SSRSC) model is reformulated as a linear equality-constrained problem, which is solved efficiently under the alternating direction method of multipliers framework. Experiments on benchmark datasets demonstrate that the proposed SSRSC algorithm is very efficient and outperforms the state-of-the-art SC methods on accuracy. The code can be found at https://github.com/csjunxu/SSRSC .

Fuzzy-Affine-Model-Based Sampled-Data Filtering Design for Stochastic Nonlinear Systems

Abstract: This article addresses the sampled-data piecewise affine (PWA) filter design problem for Ito stochastic nonlinear systems represented by Takagi–Sugeno fuzzy affine models. An input delay method is used to describe the sample-and-hold behavior of the measurement output. Based on a novel piecewise quadratic Lyapunov–Krasovskii functional, some new results on the robust sampled-data PWA filtering design are proposed through a linearization procedure by using some convexification techniques. Simulation studies on a tunnel diode circuit system, and an inverted pendulum system are given to illustrate the effectiveness of the proposed method.

On the c -differential uniformity of certain maps over finite fields

Abstract: We give some classes of power maps with low c-differential uniformity over finite fields of odd characteristic, for $$c=-1$$ . Moreover, we give a necessary and sufficient condition for a linearized polynomial to be a perfect c-nonlinear function and investigate conditions when perturbations of perfect c-nonlinear (or not) function via an arbitrary Boolean or p-ary function is perfect c-nonlinear. In the process, we obtain a class of polynomials that are perfect c-nonlinear for all $$c e 1$$ , in every characteristic. The affine, extended affine and CCZ-equivalence is also looked at, as it relates to c-differential uniformity.

Error estimates for DeepOnets: A deep learning framework in infinite dimensions.

Abstract: DeepOnets have recently been proposed as a framework for learning nonlinear operators mapping between infinite dimensional Banach spaces. We analyze DeepOnets and prove estimates on the resulting approximation and generalization errors. In particular, we extend the universal approximation property of DeepOnets to include measurable mappings in non-compact spaces. By a decomposition of the error into encoding, approximation and reconstruction errors, we prove both lower and upper bounds on the total error, relating it to the spectral decay properties of the covariance operators, associated with the underlying measures. We derive almost optimal error bounds with very general affine reconstructors and with random sensor locations as well as bounds on the generalization error, using covering number arguments. We illustrate our general framework with four prototypical examples of nonlinear operators, namely those arising in a nonlinear forced ODE, an elliptic PDE with variable coefficients and nonlinear parabolic and hyperbolic PDEs. In all these examples, we prove that DeepOnets break the curse of dimensionality, thus demonstrating the efficient approximation of infinite-dimensional operators with this machine learning framework.

Strapdown Inertial Navigation System Initial Alignment based on Group of Double Direct Spatial Isometries

Abstract: The task of strapdown inertial navigation system (SINS) initial alignment is to calculate the attitude transformation matrix from body frame to navigation frame. In this paper, such attitude transformation matrix is divided into two parts through introducing the initial inertially fixed navigation frame as inertial frame. The attitude changes of the navigation frame corresponding to the defined inertial frame can be exactly calculated with known velocity and position provided by GNSS. The attitude from body frame to the defined inertial frame is estimated based on the SINS mechanization in inertial frame. The attitude, velocity and position in inertial frame are formulated together as element of the group of double direct spatial this http URL is proven that the group state model in inertial frame satisfies a particular "group affine" property and the corresponding error model satisfies a "log linear" autonomous differential equation on the Lie algebra. Based on such striking property, the attitude from body frame to the defined inertial frame can be estimated based on the linear error model with even extreme large misalignments. Two different error state vectors are extracted based on right and left matrix multiplications and the detailed linear state space models are derived based on the right and left errors for SINS mechanization in inertial frame. With the derived linear state space models, the explicit initial alignment procedures have been presented. Extensive simulation and field tests indicate that the initial alignment based on the left error model can perform quite well within a wide range of initial attitude errors, although the used filter is still a type of linear Kalman filter. This method is promising in practical products abandoning the traditional coarse alignment stage.

Corner Detection Using Second-Order Generalized Gaussian Directional Derivative Representations

Abstract: Corner detection is a critical component of many image analysis and image understanding tasks, such as object recognition and image matching. Our research indicates that existing corner detection algorithms cannot properly depict the difference between edges and corners and this results in wrong corner detections. In this paper, the capability of second-order generalized (isotropic and anisotropic) Gaussian directional derivative filters to suppress Gaussian noise is evaluated. The second-order generalized Gaussian directional derivative representations of step edge, L-type corner, Y- or T-type corner, X-type corner, and star-type corner are investigated and obtained. A number of properties for edges and corners are discovered which enable us to propose a new image corner detection method. Finally, the criteria on detection accuracy and average repeatability under affine image transformation, JPEG compression, and noise degradation, and the criteria on region repeatability are used to evaluate the proposed detector against nine state-of-the-art methods. The experimental results show that our proposed detector outperforms all the other tested detectors.

Practical Linear Algebra : A Geometry Toolbox

Abstract: Descartes' Discovery Local and Global Coordinates: 2D Going from Global to Local Local and Global Coordinates: 3D Stepping Outside the Box Application: Creating Coordinates Here and There: Points and Vectors in 2D Points and Vectors What's the Difference? Vector Fields Length of a Vector Combining Points Independence Dot Product Orthogonal Projections Inequalities Lining Up: 2D Lines Defining a Line Parametric Equation of a Line Implicit Equation of a Line Explicit Equation of a Line Converting Between Parametric and Implicit Equations Distance of a Point to a Line The Foot of a Point A Meeting Place: Computing Intersections Changing Shapes: Linear Maps in 2D Skew Target Boxes The Matrix Form Linear Spaces Scalings Reflections Rotations Shears Projections Areas and Linear Maps: Determinants Composing Linear Maps More on Matrix Multiplication Matrix Arithmetic Rules 2 x 2 Linear Systems Skew Target Boxes Revisited The Matrix Form A Direct Approach: Cramer's Rule Gauss Elimination Pivoting Unsolvable Systems Underdetermined Systems Homogeneous Systems Undoing Maps: Inverse Matrices Defining a Map A Dual View Moving Things Around: Affine Maps in 2D Coordinate Transformations Affine and Linear Maps Translations More General Affine Maps Mapping Triangles to Triangles Composing Affine Maps Eigen Things Fixed Directions Eigenvalues Eigenvectors Striving for More Generality The Geometry of Symmetric Matrices Quadratic Forms Repeating Maps 3D Geometry From 2D to 3D Cross Product Lines Planes Scalar Triple Product Application: Lighting and Shading Linear Maps in 3D Matrices and Linear Maps Linear Spaces Scalings Reflections Shears Rotations Projections Volumes and Linear Maps: Determinants Combining Linear Maps Inverse Matrices More on Matrices Affine Maps in 3D Affine Maps Translations Mapping Tetrahedra Parallel Projections Homogeneous Coordinates and Perspective Maps Interactions in 3D Distance between a Point and a Plane Distance between Two Lines Lines and Planes: Intersections Intersecting a Triangle and a Line Reflections Intersecting Three Planes Intersecting Two Planes Creating Orthonormal Coordinate Systems Gauss for Linear Systems The Problem The Solution via Gauss Elimination Homogeneous Linear Systems Inverse Matrices LU Decomposition Determinants Least Squares Application: Fitting Data to a Femoral Head Alternative System Solvers The Householder Method Vector Norms Matrix Norms The Condition Number Vector Sequences Iterative System Solvers: Gauss-Jacobi and Gauss-Seidel General Linear Spaces Basic Properties of Linear Spaces Linear Maps Inner Products Gram-Schmidt Orthonormalization A Gallery of Spaces Eigen Things Revisited The Basics Revisited The Power Method Application: Google Eigenvector Eigenfunctions The Singular Value Decomposition The Geometry of the 2 x 2 Case The General Case SVD Steps Singular Values and Volumes The Pseudoinverse Least Squares Application: Image Compression Principal Components Analysis Breaking It Up: Triangles Barycentric Coordinates Affine Invariance Some Special Points 2D Triangulations A Data Structure Application: Point Location 3D Triangulations Putting Lines Together: Polylines and Polygons Polylines Polygons Convexity Types of Polygons Unusual Polygons Turning Angles and Winding Numbers Area Application: Planarity Test Application: Inside or Outside? Conics The General Conic Analyzing Conics General Conic to Standard Position Curves Parametric Curves Properties of Bezier Curves The Matrix Form Derivatives Composite Curves The Geometry of Planar Curves Moving along a Curve Appendix A: Glossary Appendix B: Selected Exercise Solutions Bibliography Index Exercises appear at the end of each chapter.

Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization

Abstract: Deep networks are now ubiquitous in large-scale multi-center imaging studies. However, the direct aggregation of images across sites is contraindicated for downstream statistical and deep learning-based image analysis due to inconsistent contrast, resolution, and noise. To this end, in the absence of paired data, variations of Cycle-consistent Generative Adversarial Networks have been used to harmonize image sets between a source and target domain. Importantly, these methods are prone to instability, contrast inversion, intractable manipulation of pathology, and steganographic mappings which limit their reliable adoption in real-world medical imaging. In this work, based on an underlying assumption that morphological shape is consistent across imaging sites, we propose a segmentation-renormalized image translation framework to reduce inter-scanner heterogeneity while preserving anatomical layout. We replace the affine transformations used in the normalization layers within generative networks with trainable scale and shift parameters conditioned on jointly learned anatomical segmentation embeddings to modulate features at every level of translation. We evaluate our methodologies against recent baselines across several imaging modalities (T1w MRI, FLAIR MRI, and OCT) on datasets with and without lesions. Segmentation-renormalization for translation GANs yields superior image harmonization as quantified by Inception distances, demonstrates improved downstream utility via post-hoc segmentation accuracy, and improved robustness to translation perturbation and self-adversarial attacks.

Affine Quantization on the Half Line

Abstract: The similarity between classical and quantum physics is large enough to make an investigation of quantization methods a worthwhile endeavour. As history has shown, Dirac's canonical quantization method works reasonably well in the case of conventional quantum mechanics over Rn but it may fail in non-trivial phase spaces and also suffer from ordering problems. Affine quantization is an alternative method, similar to the canonical quantization, that may offer a positive result in situations for which canonical quantization fails. In this paper we revisit the affine quantization method on the half-line. We formulate and solve some simple models, the free particle and the harmonic oscillator.

Spatially-Adaptive Pixelwise Networks for Fast Image Translation

Abstract: We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We design the generator to be an extremely lightweight function of the full-resolution image. In fact, we use pixel-wise networks; that is, each pixel is processed independently of others, through a composition of simple affine transformations and nonlinearities. We take three important steps to equip such a seemingly simple function with adequate expressivity. First, the parameters of the pixel-wise networks are spatially varying, so they can represent a broader function class than simple 1 × 1 convolutions. Second, these parameters are predicted by a fast convolutional network that processes an aggressively low-resolution representation of the input. Third, we augment the input image by concatenating a sinusoidal encoding of spatial coordinates, which provides an effective inductive bias for generating realistic novel high-frequency image content. As a result, our model is up to 18× faster than state-of-the-art baselines. We achieve this speedup while generating comparable visual quality across different image resolutions and translation domains.

Point Set Registration With Similarity and Affine Transformations Based on Bidirectional KMPE Loss

Abstract: Robust point set registration is a challenging problem, especially in the cases of noise, outliers, and partial overlapping. Previous methods generally formulate their objective functions based on the mean-square error (MSE) loss and, hence, are only able to register point sets under predefined constraints (e.g., with Gaussian noise). This article proposes a novel objective function based on a bidirectional kernel mean ${p}$ -power error (KMPE) loss, to jointly deal with the above nonideal situations. KMPE is a nonsecond-order similarity measure in kernel space and shows a strong robustness against various noise and outliers. Moreover, a bidirectional measure is applied to judge the registration, which can avoid the ill-posed problem when a lot of points converges to the same point. In particular, we develop two effective optimization methods to deal with the point set registrations with the similarity and the affine transformations, respectively. The experimental results demonstrate the effectiveness of our methods.

Fast Convergence of Dynamical ADMM via Time Scaling of Damped Inertial Dynamics

Abstract: In this paper, we propose in a Hilbertian setting a second-order time-continuous dynamic system with fast convergence guarantees to solve structured convex minimization problems with an affine constraint. The system is associated with the augmented Lagrangian formulation of the minimization problem. The corresponding dynamics brings into play three general time-varying parameters, each with specific properties, and which are, respectively, associated with viscous damping, extrapolation and temporal scaling. By appropriately adjusting these parameters, we develop a Lyapunov analysis which provides fast convergence properties of the values and of the feasibility gap. These results will naturally pave the way for developing corresponding accelerated ADMM algorithms, obtained by temporal discretization.

Dynamic Output Feedback Control of Discrete-Time Switched Affine Systems

Abstract: This article deals with the codesign of an output-dependent switching function and a full-order affine filter for discrete-time switched affine systems More specifically, from the measured output, the switched filter has the role of providing essential information for the switching function, which must assure global practical stability of a desired equilibrium point The design conditions are based on a general quadratic Lyapunov function and are expressed in terms of linear matrix inequalities Moreover, whenever the system is quadratically detectable, the solution to the output feedback problem coincides with the one for the state feedback case and the associated filter admits the observer form To the best of the authors’ knowledge, this is the first time that the dynamic output feedback control problem is treated in the context of discrete-time switched affine systems The results can be used to cope with sampled-data control and have the property of assuring global asymptotic stability when the sampling period tends to zero A practical application concerning the velocity control of a dc motor driven by a buck–boost converter illustrates the theoretical results

Distortion Robust Relative Radiometric Normalization of Multitemporal and Multisensor Remote Sensing Images Using Image Features

Abstract: In this article, we propose a novel framework to radiometrically correct unregistered multisensor image pairs based on the extracted feature points with the KAZE detector and the conditional probability (CP) process in the linear model fitting. In this method, the scale, rotation, and illumination invariant radiometric control set samples (SRII-RCSS) are first extracted by the blockwise KAZE strategy. They are then distributed uniformly over both textured and texture-less land use/land cover (LULC) using grid interpolation and a set of nearest-neighbors. Subsequently, SRII-RCSS are scored by a similarity measure, and the histogram of the scores is then used to refine SRII-RCSS. The normalized subject image is produced by adjusting the subject image to the reference image using the CP-based linear regression (CPLR) based on the optimal SRII-RCSS. The registered normalized image is finally generated by registration of the normalized subject image to the reference image through a two-pass registration method, namely affine-B-spline and, then, it is enhanced by updating the normalization coefficient of CPLR based on the SRII-RCSS. In this study, eight multitemporal data sets acquired by inter/intra satellite sensors were used in tests to comprehensively assess the efficiency of the proposed method. Experimental results show that the proposed method outperforms the existing state-of-the-art relative radiometric normalization (RRN) methods both qualitatively and quantitatively, indicating its capability for RRN of unregistered multisensor image pairs.

Asymptotic Tracking Control for Nonaffine Systems with Disturbances

Abstract: This article intends to address an adaptive asymptotic tracking control with prescribed performance function for a class of nonaffine systems with unknown disturbances. First, the nonaffine system is transformed into an affine system by using a set of alternative state variables. Subsequently, a prescribed performance function with predefined convergence rate, maximum overshoot and steady-state error is introduced. To achieve the asymptotic tracking control performance, the robust integral of the sign of the error (RISE) feedback term is utilized in the control design to reject the unknown external disturbances and NN approximation errors. Finally, an adaptive controller is presented so that the asymptotic tracking performance with guaranteed prescribed performance is achieved. Comparative experiments are provided to show the effectiveness of the proposed control scheme.

A Coarse-to-Fine Deformable Transformation Framework for Unsupervised Multi-Contrast MR Image Registration with Dual Consistency Constraint

Abstract: Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning. Nevertheless, the efficiency and performance of the existing registration algorithms can still be improved. In this paper, we propose a novel unsupervised learning-based framework to achieve accurate and efficient multi-contrast MR image registration. Specifically, an end-to-end coarse-to-fine network architecture consisting of affine and deformable transformations is designed to improve the robustness and achieve end-to-end registration. Furthermore, a dual consistency constraint and a new prior knowledge-based loss function are developed to enhance the registration performances. The proposed method has been evaluated on a clinical dataset containing 555 cases, and encouraging performances have been achieved. Compared to the commonly utilized registration methods, including VoxelMorph, SyN, and LT-Net, the proposed method achieves better registration performance with a Dice score of 0.8397± 0.0756 in identifying stroke lesions. With regards to the registration speed, our method is about 10 times faster than the most competitive method of SyN (Affine) when testing on a CPU. Moreover, we prove that our method can still perform well on more challenging tasks with lacking scanning information data, showing the high robustness for the clinical application.

SRFlow-DA: Super-Resolution Using Normalizing Flow with Deep Convolutional Block

Abstract: Multiple high-resolution (HR) images can be generated from a single low-resolution (LR) image, as super-resolution (SR) is an underdetermined problem. Recently, the conditional normalizing flow-based model, SRFlow, shows remarkable performance by learning an exact map-ping from HR image manifold to a latent space. The flow-based SR model allows sampling multiple output images from a learned SR space with a given LR image. In this work, we propose SRFlow-DA which has a more suitable architecture for the SR task based on the original SRFlow model. Specifically, our approach enlarges the receptive field by stacking more convolutional layers in the affine couplings, and so our model can get more expressive power. At the same time, we reduce the total number of model pa-rameters for efficiency. Compared to SRFlow, our SRFlow-DA achieves better or comparable PSNR and LPIPS for × 4 and ×8 SR tasks, while having a reduced number of parameters. In addition, our method generates visually clear results without excessive sharpness artifacts.