Real-Time Flight trajectory prediction (RT-FTP) is an important task for future air traffic management (ATC). Real ADS-B trajectories are often irregularly sampled, i.e. the data arrive at irregular intervals, there exists much missing data after converting it to regularly sampled. Most existing methods mitigate this problem by offline data preprocessing (e.g. outlier detection, trajectory imputation). However, these methods add additional processing steps and are not always applicable for real-time application. In this work, we introduce the RT-FTP task and transform it into an short-term time-series prediction task with missing data. We have collected real ADS-B data and constructed a new Real-Time Flight Trajectory dataset (RTFT). We replaced the normalization methods of some existing advanced time series forecasting methods with Mask Stationary Standardization (MSS) and established theRTFTbenchmark. Furthermore, we designed a novel RT-FTP architecture named Independent Distance Extrapolation Architecture (IDEA), IDEA consists of a decomposition module, Range Attention module and the Temporal Extrapolation Network (TEN). TEN is an improvement over Temporal Convolutional Network (TCN) and it can extract independent features at different distances, thereby providing a certain degree of interpretability. We further simplified the structure of TEN to introduce a more lightweight model called FastTEN. IDEA-FastTEN have achieved SOTA in both performance and performance-speed balance on theRTFTbenchmark. We hope that our work can help advance ADS-B trajectory prediction towards real-time application.

Recent advancements in subject-driven image generation have led to zero-shot generation, yet precise selection and focus on crucial subject representations remain challenging. Addressing this, we introduce the SSR-Encoder, a novel architecture designed for selectively capturing any subject from single or multiple reference images. It responds to various query modalities including text and masks, without necessitating test-time fine-tuning. The SSR-Encoder combines a Token-to-Patch Aligner that aligns query inputs with image patches and a Detail-Preserving Subject Encoder for extracting and preserving fine features of the subjects, thereby generating subject embeddings. These embeddings, used in conjunction with original text embeddings, condition the generation process. Characterized by its model generalizability and efficiency, the SSR-Encoder adapts to a range of custom models and control modules. Enhanced by the Embedding Consistency Regularization Loss for improved training, our extensive experiments demonstrate its effectiveness in versatile and high-quality image generation, indicating its broad applicability. Project page: ssr-encoder.github.io

Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an effective and fast approach that could balance the text-image consistency and identity consistency of the generated image and reference image. Our method can generate personalized images without any fine-tuning while maintaining the inherent text-to-image generation ability of diffusion models. Given a prompt and a reference image, we merge the custom concept into generated images by manipulating cross-attention and self-attention layers of the original diffusion model to generate personalized images that match the text description. Comprehensive experiments highlight the superiority of our method.

Hyperspectral (HS) and multispectral (MS) images’ fusion aims to improve their spatial resolutions and circumvent the main limitation of HS sensors. However, existing HS–MS fusion methods account for spectral variability fail to consider the global spectral correlation. To overcome this problem, this letter presents a novel joint weighted Schatten-p norm and spatial smoothness regularization for HS–MS fusion account for both spatial and spectral changes. First, the relationship between the spectral variability and the spectral signatures is formulated as an explicit parametric model. Second, to preserve the inherent correlation among the bands, we design a weighted Schatten-p ($ 0\lt p\lt 1 $) norm regularization method, which considers the importance of different components. Third, a spatial smoothness regularization term is exploited to reconstruct the spatial details. Finally, an iterative procedure based on the framework of alternating direction method of multipliers (ADMM) is designed to solve the resulting optimization problem. Extensive experiments on both synthetic and real datasets demonstrate that the proposed method outperforms six state-of-the-art methods from visual and quantitative assessments. The datasets and results are released inhttp://github.com/phan1007/WSGS.

Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of results, because CLIP alone cannot provide enough guidance information for fine-scale pixel-level changes. In this paper, we introduce CLIPVG, a text-guided image manipulation framework using differentiable vector graphics, which is also the first CLIP-based general image manipulation framework that does not require any additional generative models. We demonstrate that CLIPVG can not only achieve state-of-art performance in both semantic correctness and synthesis quality, but also is flexible enough to support various applications far beyond the capability of all existing methods.

Strong tracking Kalman filter is proposed to address the performance degradation and divergence caused by process model uncertainty. However, strong tracking filters depend on prior information about the measurement noise, which is frequently unknown or time-varying in real-world applications. This paper proposed an adaptive strong tracking cubature Kalman filtering algorithm with unknown measurement noise covariance. First, we introduce a modified pseudo-measurement-based covariance estimation method. It estimates measurement covariance by calculating the second-order mutual difference between the measurement sequence and pseudo measurement sequence. Second, we propose a filter divergence detecting method to help decide when to adjust the prediction error covariance matrix. The accuracy of the measurement noise covariance matrix estimating method and the effectiveness of filter divergence detecting methods have been proved by simulation results, respectively. As a result, the proposed filter outperforms several other algorithms in precision or robustness with inaccurate measurement noise covariance.

Abstract In multi‐target tracking, non‐Gaussian heavy‐tailed process noise (PN) and measurement noise (MN) are introduced by unknown manoeuvring and noise‐corrupted measurements. This study proposes a Gaussian approximation approach based on multivariate Student‐ t distribution, which is designed to characterise non‐Gaussian heavy‐tailed MN covariance and PN covariance. The variational Bayesian approach is applied to a generalised labelled multi‐Bernoulli (GLMB) with an augmented state, and a robust adaptive generalised labelled multi‐Bernoulli (RAGLMB) framework is derived to recursively propagate the joint posterior density of noise covariance and target state. The simulation results indicate that the proposed RAGLMB filter is robust to targets affected by non‐Gaussian heavy‐tailed PN and MN.

We consider the uncalibrated vision-based control problem of robotic manipulators in this work. Though lots of approaches have been proposed to solve this problem, they usually require calibration (offline or online) of the camera parameters in the implementation, and the control performance may be largely affected by parameter estimation errors. In this work, we present new fully uncalibrated visual servoing approaches for position control of the 2DOFs planar manipulator with a fixed camera. In the proposed approaches, no camera calibration is required, and numerical optimization algorithms or adaptive laws for parameter estimation are not needed. One benefit of such features is that exponential convergence of the image position errors can be ensured regardless of the camera parameter uncertainties. Generally, existing uncalibrated approaches only can guarantee asymptotical convergence of the position errors. Moreover, different from most existing approaches which assume that the robot motion plane and the image plane are parallel, one of the proposed approaches allows the camera to be installed at a general pose. This also simplifies the controller implementation and improves the system design flexibility. Finally, simulation and experimental results are provided to illustrate the effectiveness of the presented fully uncalibrated visual servoing approaches.

This article introduces a novel consensus-based labeled multi-Bernoulli (LMB) filter to tackle multitarget tracking (MTT) in a distributed sensor network (DSN), whose sensor nodes have limited and different fields of view (FoVs). Although consensus-based algorithms are effective for distributed fusion and MTT, it may be problematic when distributed sensor nodes have different FoVs. To deal with this issue, the proposed method constructs an extended label space mapping to overcome the "label space mismatching" phenomenon; after that, the model of the undetected multitargets is established so that the tracks can be initialized outside the FoV of local sensors; finally and most important, weight selection and evolution mechanism are proposed such that the fusion weights are automatically tuned for each track at each time step and consensus step. The efficiency and robustness of the proposed algorithm are demonstrated in a distributed MTT scenario via numerical simulations.

Domain shift is a major challenge for object detectors to generalize well to real world applications. Emerging techniques of domain adaptation for two-stage detectors help to tackle this problem. However, two-stage detectors are not the first choice for industrial applications due to its long time consumption. In this paper, a novel Domain Adaptive YOLO (DA-YOLO) is proposed to improve cross-domain performance for one-stage detectors. Image level features alignment is used to strictly match for local features like texture, and loosely match for global features like illumination. Multi-scale instance level features alignment is presented to reduce instance domain shift effectively, such as variations in object appearance and viewpoint. A consensus regularization to these domain classifiers is employed to help the network generate domain-invariant detections. We evaluate our proposed method on popular datasets like Cityscapes, KITTI, SIM10K and et al.. The results demonstrate considerable improvement when tested under different cross-domain scenarios.

In this letter, a robust minimum error entropy based cubature information filter is proposed for state estimation in non-Gaussian measurement noise. A new combined optimization cost is defined based on the error entropy. Through cubature transform, a statistical linearization regression model is constructed, and a new information filter is then developed by minimizing the error entropy based cost. The fixed-point iteration approach is used to compute the state estimate. Further, the convergence of the proposed information filter is analyzed, and the convergence conditions are derived. Simulations are performed to demonstrate the effectiveness of the proposed algorithm. It is shown that the estimation performance of the proposed filter is more robust than that of traditional methods against the complicated non-Gaussian noises, such as outliers and noises from multimodal distributions.

Different image fusion systems have been developed to deal with the massive amounts of image data for different applications, such as remote sensing, computer vision, and environment monitoring. However, the generalizability and versatility of these fusion systems remain unknown. This article proposes an efficient regularization framework to achieve different kinds of fusion tasks accounting for the spatiospectral and spatiotemporal variabilities of the fusion process. A joint minimization functional is developed by taking an advantage of a composite regularizer for enforcing joint sparsity in the gradient domain and the frame domain. The proposed composite regularizer is composed of the Hessian Schatten-norm regularization and contourlet-based regularization terms. The resulting problems are solved by the alternating direction method of multipliers (ADMM). The effectiveness of the proposed method is validated in a variety of image fusion experiments: 1) hyperspectral (HS) and panchromatic image fusion; 2) HS and multispectral image fusion; 3) multitemporal image fusion (MIF); and 4) multi-image deblurring. Results show promising performance compared with state-of-the-art fusion methods.

Although many vision-based control methods have been proposed for nonholonomic mobile robots, in their implementation, it is usually necessary to calibrate the camera intrinsic and/or extrinsic parameters using offline/online parameter estimation algorithms or online adaptation laws. To avoid the tediousness of camera calibration and to make the system performance highly robust to camera parameter uncertainties, in this article, we propose novel image-based pose stabilization control approaches for nonholonomic mobile robots with a truly uncalibrated overhead fixed camera. In the proposed approaches, only image position information of three feature points from an overhead camera is used for controller design, while information from other sensors (such as wheel encoders) is not required. Furthermore, either offline or online camera calibration is not necessary, and no knowledge about the camera intrinsic and extrinsic parameters is needed, which also can greatly simplify the controller implementation. Simulation and experimental results are given to demonstrate the feasibility and effectiveness of the proposed purely image-based pose stabilization approaches.

The traditional consensus-based filters are widely used in distributed sensor networks. However, they suffer from divergence when outliers occur. This paper proposes a robust consensus nonlinear information filter for distributed state estimation with measurement outliers. Unlike the Gaussian assumption in traditional consensus filers, the measurement of each sensor node is modeled here as a multivariate Student- t process with unknown parameters of the sufficient statistic. The variational Bayesian method is employed to jointly estimate the state and the parameters. As the state and parameters are coupled, the updated equation can be solved by fixed point iteration. The centralized outliers robust information filter is first derived for multiple sensors. It is then extended to a distributed version to fuse information from multiple interconnected local estimators. The integral of the consensus-based nonlinear filter is approximated by Gaussian approximation under the framework of the information filter. The consensuses are based on both likelihoods and prior probability distributions. The consensus and convergence of the proposed method are also analyzed. Simulation results show that the proposed approach is effective in dealing with outliers.

In this work, the state estimation problem is taken into consideration in the simultaneous presence of sensor faults, out-of-sequence measurements (OOSM) and nonlinear dynamics. We derive the analytic formulae of linear minimum mean squared error (LMMSE) estimation with the arbitrary delay OOSMs and the observation faults, then outline a sequential LMMSE filtering under nonlinear dynamics. The sequential filtering lies first in fulfilling a nonlinear estimation using in-sequence observations, secondly perform a LMMSE correction to the nonlinear estimates with OOSMs. The proposed approach's feasibility is demonstrated by numerical comparisons.

The conventional approaches to the sensor registration problem require a centralized processing structure. This demand cannot be met in the distributed sensor network (DSN). In this paper, we address this sensor registration problem in the DSN. For this purpose, we embed the consensus algorithm into the expectation maximization (EM) iteration procedure such that the conditional expectation of the log-likelihood function can be evaluated in a fully distributed way. Thus each sensor can obtain its estimated bias. Simulations are performed in order to demonstrate the effectiveness of the proposed algorithms.

In multi-target tracking (MTT), the imprecise model for sensor characteristics might result in poor performance. The Variational Bayesian labeled multi-Bernoulli (VB-LMB) filter based on Gamma distribution can handle this problem. However, the predictive likelihood of the existing VB-LMB filter is simply treated as a Gaussian, which is inaccurate. In this paper, a VB-LMB filter with inverse Wishart distribution is presented to perform MTT under the unknown sensor characteristics. The measurement noise covariance is modeled as an inverse Wishart (IW) distribution. This distribution has potential to deal with the full noise covariance matrix compared with the Gamma distribution. Since the state and the measurement noise covariance are coupled, the updated equation can be solved by variational Bayesian (VB) method. The predictive likelihood is calculated via minimizing the Kullback-Leibler divergence by the VB lower bound. A MTT scenario is used to evaluate the proposed method. Simulation results show that our approach has better performance than the existing VB-LMB filter with the Gamma distribution.

Zero‐shot learning (ZSL) aims to classify the objects without any training samples. Attributes are used to transfer knowledge from the training set to testing one in ZSL. Most ZSL methods based on Direct Attribute Prediction (DAP) assume that attributes are independent of each other. In this study, the authors explore the relationship between attributes and propose Joint Attribute Chain Prediction (JACP). Attribute chains are introduced to represent the relations. Conditional probabilities of attributes are estimated orderly along the chain to calculate the joint posteriors of the testing classes without independence assumptions. To reduce the estimation error, attribute relation clustering algorithm is presented to group the long chain into some unrelated small chains. When the max length of chains is one, JACP is essentially identical with DAP. Experiments on three data sets for zero‐shot problem demonstrate the classification accuracy and efficiency of the authors’ algorithm. The results show that mining attribute relations can greatly improve the performance of ZSL effectively.

A robust adaptive filter is proposed by using the variational Bayesian (VB) inference to extended target tracking with heavy‐tailed noise in clutter. An explicit distribution is used to describe the non‐Gaussian heavy‐tailed noise based on Student's t ‐distribution. The need for arbitrary decisions is then eliminated, and the robust operation is provided which is less sensitive to extreme observation. Moreover, an approximate measurement update using the analytical techniques of VB methods is derived to approximate the posterior states at each time step. To obtain a more accurate result, clutter estimation is also integrated considering the uncertainty of target tracking in a cluttered environment. The performance of the proposed algorithm is demonstrated with simulated data.

Image restoration is a difficult and challenging problem in various imaging applications. However, despite of the benefits of a single overcomplete dictionary, there are still several challenges for capturing the geometric structure of image of interest. To more accurately represent the local structures of the underlying signals, we propose a new problem formulation for sparse representation with block-orthogonal constraint. There are three contributions. First, a framework for discriminative structured dictionary learning is proposed, which leads to a smooth manifold structure and quotient search spaces. Second, an alternating minimization scheme is proposed after taking both the cost function and the constraints into account. This is achieved by iteratively alternating between updating the block structure of the dictionary defined on Grassmann manifold and sparsifying the dictionary atoms automatically. Third, Riemannian conjugate gradient is considered to track local subspaces efficiently with a convergence guarantee. Extensive experiments on various datasets demonstrate that the proposed method outperforms the state-of-the-art methods on the removal of mixed Gaussian-impulse noise.

In this paper, a new centralized algorithm is developed to estimate the registration error and target states jointly based on the generalized labeled multi-Bernoulli (GLMB) filter. The bias pseudo-measurements are calculated with the tracks generated by the GLMB filter. Then, the bias estimates are computed to compensate the measurements for multi-target tracking. Since the estimates of the sensor biases and target states are calculated exactly with no approximations, the estimation performance of the proposed algorithm is better than the method based on the probability hypothesis density (PHD) filter. The effectiveness and superiority of the proposed algorithm are verified by numerical simulations.

A great deal of interest has been paid to computation problem of Dezert-Smarandache theory (DSmT). But there are still problems on complex analysis and frequently search. The computational measurement of DSmT is presented in which the computation is generated in the search for focal elements, the combination of focal elements and basic belief assignment, the expression of focal elements. A new DSmT computational optimization approach is presented to solve the problems. The proposed approach optimizes the original evidence and combination of focal elements. The original evidence is reduced to keep the effective focal elements. And the focal element relationship is integrated into evidence code to realize self-adaption for combination of focal elements. Numerical results are provided to validate our approach.

This study proposes a recursive solution to target joint detection, tracking, and classification (DTC) based on finite set statistics (FISST) and generalised Bayesian risk. A new Bayesian risk is defined involving the costs of target existence probability estimation (detection), state estimation (tracking), and classification. The estimates and costs are calculated within the FISST framework for different hypotheses and decisions of the target class, and the optimal solution is then derived to minimise the new Bayesian risk. As different costs are unified, the inter‐dependence of DTC is considered, and these three sub‐problems are solved jointly. The effects of the parameters of the new Bayesian risk are also analysed. Simulations show that the authors’ method has a better overall performance compared with traditional methods.

This letter addresses the consensus-based nonlinear state estimation in distributed sensor networks with unknown measurement noise statistics. The existence of naive nodes and the communication constraint in sensor networks requires a hybrid consensus filtering method. In the frame of consensus filtering, a novel consensus nonlinear filtering approach named variational Bayesian consensus cubature Kalman filter (VB-CCKF) is proposed, in which the CKF is employed to handle the nonlinear state estimation and the VB approximation is adopted to iteratively estimate the sufficient statistics of the measurement noise covariance on each step. Simulations are performed in order to demonstrate the effectiveness of the proposed approach.

Zero-shot learning (ZSL) aims to classify the objects without any training samples. Direct Attribute Prediction (DAP) gives a solution with attribute space but it makes the assumption of attribute independence. To relax this assumption and consider the relation among attributes, Joint Attribute Chain Prediction (JACP) algorithm is proposed in this paper. It estimates the joint probability of attribute chain by the multiplication formula without the independence assumption. To deal with the difficulty of estimation, clustering algorithm of attributes is presented to generate several independent attribute sets. Each set trains a series of classifiers to calculate the joint probability individually and then the posteriori of classes can be obtained. Experiments on AwA and aPascal-aYahoo data sets demonstrate the effectiveness of our algorithm.

Image representations using code words from a visual dictionary are widely applied in object detection and categorization. Traditionally, there are two types of methods to construct a dictionary: k-means and optimization-based method. The former cannot achieve a good discriminability because it extracts too many background features. The latter needs to cooperate with coding methods and brings about high computational complexity. In this paper, we present an effective method based on Gist information detection to obtain a more discriminative dictionary with low computational cost. First, we partition the image into increasingly fine sub-regions, and calculate the Gist information of each region. Then extract more features from sub-regions with richer information and fewer features from ones with less information. Finally construct a dictionary using the non-uniform sampling features. Experiments on Caltech101 show that our method can achieve a better performance than traditionally k-means and the optimization-based method. Hence our dictionary has a better discrimination.

The challenge of visual tracking mainly comes from intrinsic appearance variations of the target and extrinsic environment changes around the target in a long duration, so the tracker that can simultaneously tolerate these variabilities is largely expected. In this study, the authors propose a new tracking approach based on discriminative stable regions (DSRs). The DSRs are obtained based on the criterion of maximal local entropy and spatial discrimination, which enables the tracker to handle well distractors and appearance variations. The collaborative tracking incorporated hierarchical clustering can tolerate motion noise and occlusions. In addition, as an efficient tool, the principle component analysis is used to discover the potential affine relation between DSR and the target, which timely adapts to the shape deformation of the target. Extensive experiments show that the proposed method achieves superior performance in many challenging target tracking tasks.

A dynamic image fusion scheme for infrared and visible sequence based on region target detection is proposed in this paper. Target detection technique is employed to segment the source images into target and background regions. Different fusion rules are adopted respectively in target and background regions. A limitedly redundant discrete wavelet transform (LR DWT) method is introduced to achieve shift invariant multi-resolution representation of each source images. Fusion experiments on real world image sequences indicate that the proposed method is effective and efficient, which achieves better performance than the generic fusion method.

The probability hypothesis density (PHD) filter, which was derived from finite set statistics is a promising approach to multi-target tracking. An analytical closed-form solution for the PHD, named Gaussian mixture PHD Filter, is given for linear Gaussian target dynamics with Gaussian births by B. Vo and W. Ma. Based on the Gaussian mixture PHD filter, in this paper, without consideration of data association technique, a method using three passive sensors for multi-target location system is proposed, which can restrain greatly the false triangulations, calls ghosts, where the measurements of the bearing-only multi-target location system are spoiled by clutter.

Recently, a number of studies have demonstrated that thermal infrared (IR) imagery offers a promising alternative to visible imagery in face recognition problems due to its invariance to visible illumination changes. However, thermal IR has other limitations including that it is opaque to glass. As a result, thermal IR imagery is very sensitive to facial occlusion caused by eyeglasses. Fusion of the visible and thermal IR images is an effective way to solve this problem. In this paper, using the face reconstruction information of the visible images, we propose a nonlinear eyeglasses removing algorithm which can successfully reconstruct the thermal images. Experiments on publicly available data set show the excellent performance of our algorithm.

This paper presents conditions under which the sampling lattice for a filter bank can be replaced without loss of perfect reconstruction. This is the generalization of common knowledge that removing up/downsampling will not lose perfect reconstruction. The results provide a simple way of building oversampled filter banks. If the original filter banks are orthogonal, these oversampled banks construct tight frames of l2 (Z(n)) when iterated. As an example, a quincunx lattice is used to replace the rectangular one of the standard wavelet transform. This replacement leads to a tight frame that has a higher sampling in both time and frequency. The frame transform is nearly shift invariant and has intermediate scales. An application of the transform to image fusion is also presented.

Despite the variety of approaches and tools studied, face recognition is not accurate or robust enough to be used in uncontrolled environments. Recently, infrared (IR) imagery of human faces is considered as a promising alternative to visible imagery. IR face recognition is a biometric which offers the security of fingerprints with the convenience of face recognition. However, IR has its own limitations. The presence of eyeglasses has more influence on IR than visible imagery. In this paper, a method based on Log-Gabor wavelets for IR face recognition is proposed. The method first derives a Log-Gabor feature vector from IR face image, then obtains the independent Log-Gabor features by using independent component analysis (ICA). Experimental results show that the proposed method works well, even in challenging situations.