Driven by the filtering challenges in linear systems disturbed by non-Gaussian heavy-tailed noise, robust Kalman filters (RKFs) leveraging diverse heavy-tailed distributions have been introduced. However, the RKFs rely on precise noise models, and large model errors can degrade their filtering performance. Also, the posterior approximation by the employed variational Bayesian (VB) method can further decrease the estimation precision. Here, we introduce an innovative RKF method, the RKFNet, which combines the heavy-tailed-distribution-based RKF framework with the deep learning technique and eliminates the need for the precise parameter estimation of the heavy-tailed distributions. To reduce the VB approximation error, the mixing-parameter-based function and the scale matrix are estimated by the incorporated neural network structures. Also, the stable training process is achieved by our proposed unsupervised scheduled sampling (USS) method, where a loss function based on the Student’s t (ST) distribution is utilised to overcome the disturbance of the noise outliers and the filtering results of the traditional RKFs are employed as reference sequences. Furthermore, the RKFNet is evaluated against various RKFs and recurrent neural networks (RNNs) under three kinds of heavy-tailed measurement noises, and the simulation results showcase its efficacy in terms of estimation accuracy and efficiency. • A Novel Neural Network Aided Robust Kalman Filtering framework. • An unsupervised scheduled sampling training method. • Filtering under heavy-tailed noise.

This paper explores advanced deep learning methods, specifically utilising the Segment Anything Model (SAM) along with image processing techniques, to evaluate the structural damages caused by the devastating earthquake that occurred in Turkey on February 6, 2023. Leveraging exceptionally high-resolution pre- and post-disaster imagery provided by Maxar Technologies, this paper showcases the efficacy of SAM in contrasting and quantifying the magnitude of structural devastation. The proposed unsupervised structural damage assessment (USDA-SAM) method entails a thorough comparative analysis of aerial imagery captured both before and after the seismic event, facilitating a nuanced evaluation of its impact on buildings and critical infrastructure. USDA-SAM also proposes two metrics - damage assessment score (DAS) and affected number of buildings (Nb/km2 ) - to quantitatively measure the damage caused by the disasters. The study highlights the transformative potential of deep learning and image processing, shedding light on their key role in fortifying disaster response strategies and emphasising technology’s indispensable contribution to mitigating the challenges posed by natural disasters, such as earthquakes.

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and resource-constrained applications. The effectiveness of the student model heavily relies on the quality of the distilled knowledge received from the teacher. Given the accessibility of unlabelled remote sensing data, semi-supervised learning has become a prevalent strategy for enhancing model performance. However, relying solely on semi-supervised learning with smaller models may be insufficient due to their limited capacity for feature extraction. This limitation restricts their ability to exploit training data. To address this issue, we propose an integrated approach that combines knowledge distillation and semi-supervised learning methods. This hybrid approach leverages the robust capabilities of large models to effectively utilise large unlabelled data whilst subsequently providing the small student model with rich and informative features for enhancement. The proposed semi-supervised learning-based knowledge distillation (SSLKD) approach demonstrates a notable improvement in the performance of the student model, in the application of road segmentation surpassing the effectiveness of traditional semi-supervised learning methods.

Real-time commentary on football matches is a challenging task that requires precise and coherent descriptions of events as they unfold. Traditional methods often fall short in providing timely and accurate insights into the game. This study aims to explore the utilisation of innovative Large language model (LLM) techniques to develop an adept language model – dubbed LLM-Commentator – that can generate (near-) real-time commentary on football matches. The goal is to demonstrate that open-source language models, when fine-tuned with domain-specific data on consumer-grade hardware, can accurately depict football events from raw match data. Three distinct training strategies are employed to fine-tune the language models, addressing various challenges encountered in generating real-time football commentary. The study evaluates the efficacy of these models in producing coherent and accurate descriptions of unseen football events. Among the three strategies proposed, the Mixed Immediately Model emerges as particularly efficient in learning and adeptly handling challenging workloads. This suggests a promising future for simultaneous multi-task learning with compact, open-source language models in the context of real-time sports commentary. Additionally, the study highlights the practicality of utilising consumer-grade hardware for fine-tuning language models with specialised knowledge. The findings underscore the importance of customising training approaches and ensuring well-balanced datasets when fine-tuning language models for specific tasks. Moreover, they serve as a practical guide for broader accessibility to large language models and significantly contribute to the application of NLP in sports journalism, enabling more insightful and engaging real-time commentary on football matches.

Semi-supervised learning has been well developed to help reduce the cost of manual labelling by exploiting a large quantity of unlabelled data. Especially in the application of land cover classification, pixel-level manual labelling in large-scale imagery is labour-intensive, time-consuming and expensive. However, existing semi-supervised learning methods pay limited attention to the quality of pseudo-labels during training even though the quality of training data is one of the critical factors determining network performance. In order to fill this gap, we develop a confidence-guided semi-supervised learning (CGSSL) approach to make use of high-confidence pseudo labels and reduce the negative effect of low-confidence ones for land cover classification. Meanwhile, the proposed semi-supervised learning approach uses multiple network architectures to increase the diversity of pseudo labels. The proposed semi-supervised learning approach significantly improves the performance of land cover classification compared to the classic semi-supervised learning methods and even outperforms fully supervised learning with a complete set of labelled imagery of the benchmark Potsdam land cover dataset.

Filtering in nonlinear state-space models is known to be a challenging task due to the posterior distribution being either intractable or expressed in a complex form. One of the most successful methods, particle filtering (PF), although generally outperforming traditional filters, suffers from sample degeneracy. Drawing from optimal transport theory, the stochastic map filter (SMF) accommodates a solution to this problem, but its performance is influenced by the limited flexibility of nonlinear map parameterisation. To alleviate these drawbacks, we propose a hybrid filter which combines the PF and SMF, and hence call it PSMF. Specifically, the PSMF splits the likelihood into two parts, which are then updated by PF and SMF, respectively. The proposed approach adopts systematic resampling and smoothing to break the particle degeneracy caused by the PF. To investigate the influence of the nonlinearity of transport maps, we introduce two variants of the proposed filter, the PSMF-L and PSMF-NL, which are based on linear and nonlinear maps, respectively. The PSMF is tested on various nonlinear state-space models and a nonlinear non-Gaussian target tracking model. The proposed linear PSMF-L outperforms all the reference models for medium-to-large numbers of particles, whilst the PSMF-NL shows better resilience to parameter changes.

This letter presents a new statistical model for urban scene synthetic aperture radar (SAR) images by combining the Cauchy distribution, which is heavy tailed, with the Rician backscattering. The literature spans various well-known models most of which are derived under the assumption that the scene consists of multitudes of random reflectors. This idea specifically fails for urban scenes since they accommodate a heterogeneous collection of strong scatterers such as buildings, cars, and wall corners. Moreover, when it comes to analyzing their statistical behavior, due to these strong reflectors, urban scenes include a high number of high amplitude samples, which implies that urban scenes are mostly heavy-tailed. The proposed Cauchy–Rician model contributes to the literature by leveraging nonzero location (Rician) heavy-tailed (Cauchy) signal components. In the experimental analysis, the Cauchy–Rician model is investigated in comparison to state-of-the-art statistical models that include$\mathcal {G}_{0}$, generalized gamma, and the lognormal distribution. The numerical analysis demonstrates the superior performance and flexibility of the proposed distribution for modeling urban scenes.

We present a novel statistical model, the generalized-Gaussian–Rician (GG-Rician) distribution, for the characterization of synthetic aperture radar (SAR) images. Since accurate statistical models lead to better results in applications such as target tracking, classification, or despeckling, characterizing SAR images of various scenes including urban, sea surface, or agricultural is essential. The proposed statistical model is based on the Rician distribution to model the amplitude of a complex SAR signal, the in-phase and quadrature components of which are assumed to be generalized-Gaussian (GG) distributed. The proposed amplitude GG-Rician model is further extended to cover the intensity of SAR signals. In the experimental analysis, the GG-Rician model is investigated for amplitude and intensity SAR images of various frequency bands and scenes in comparison to state-of-the-art statistical models that include Weibull,$\mathcal {G}_{0}$, Generalized gamma, and the lognormal distribution. The statistical significance analysis and goodness-of-fit test results demonstrate the superior performance and flexibility of the proposed model for all frequency bands and scenes, and its applicability on both amplitude and intensity SAR images.

In this paper, we analyse synthetic aperture radar (SAR) images of the sea surface using an inverse problem formulation whereby Radon domain information is enhanced in order to accurately detect ship wakes. This is achieved by promoting linear features in the images. For the inverse problem-solving stage, we propose a penalty function, which combines the dual-tree complex wavelet transform (DT-CWT) with the non-convex Cauchy penalty function. The solution to this inverse problem is based on the forward-backward (FB) splitting algorithm to obtain enhanced images in the Radon domain. The proposed method achieves the best results and leads to significant improvement in terms of various performance metrics, compared to state-of-the-art ship wake detection methods. The accuracy of detecting ship wakes in SAR images with different frequency bands and spatial resolution reaches more than 90%, which clearly demonstrates an accuracy gain of 7% compared to the second-best approach.

Synthetic aperture radar (SAR) imagery can provide useful information in a multitude of applications, including climate change, environmental monitoring, meteorology, high dimensional mapping, ship monitoring, or planetary exploration. In this article, we investigate solutions for several inverse problems encountered in SAR imaging. We propose a convex proximal splitting method for the optimization of a cost function that includes a nonconvex Cauchy-based penalty. The convergence of the overall cost function optimization is ensured through careful selection of model parameters within a forward-backward (FB) algorithm. The performance of the proposed penalty function is evaluated by solving three standard SAR imaging inverse problems, including super-resolution, image formation, and despeckling, as well as ship wake detection for maritime applications. The proposed method is compared to several methods employing classical penalty functions such as total variation (TV) and L1norms, and to the generalized minimax-concave (GMC) penalty. We show that the proposed Cauchy-based penalty function leads to better image reconstruction results when compared to the reference penalty functions for all SAR imaging inverse problems in this article.

This paper presents a novel statistical model for the characterisation of synthetic aperture radar (SAR) images of the sea surface. The analysis of ocean surface is widely performed using satellite imagery as it produces information for wide areas under various weather conditions. An accurate SAR amplitude distribution model enables better results in despeckling, ship detection/tracking and so forth. In this paper, we develop a new statistical model, namely the LaplaceRician distribution for modelling amplitude SAR images of the sea surface. The proposed statistical model is based on Rician distribution to model the amplitude of a complex SAR signal, the in-phase and quadrature components of which are assumed to be Laplace distributed. The Laplace-Rician model is investigated for SAR images of the sea surface from COSMO-SkyMed and Sentinel-1 in comparison to state-of-the-art statistical models such as K, lognormal and Weibull distributions. In order to decide on the most suitable model, statistical significance analysis via Kullback-Leibler divergence and Kolmogorov-Smirnov statistics is performed. The results show a superior modelling performance of the proposed model for all of the utilised images.

Ship wake detection methods are mostly based on analyzing real SAR images of the sea surface. This is due to SAR imaging having achieved considerable maturity and becoming effective for their visualization, in particular through Bragg resonance scattering. However, in different environmental conditions, it is often difficult, sometimes impossible, to consider all possible factors that can dramatically change ship wake visualization. In this paper, an analysis of one important sea state factor, namely the fetch length, both for airborne and satellite SAR platforms is investigated and its contribution to the visualization of ship wakes in simulated SAR images is quantified. We study the effect of fetch in terms of wake detectability using a state-of the-art method. The sea surface modelling is performed using the Joint North Sea Wave Project (JONSWAP) spectrum, whilst for Kelvin wake modelling the Michell theory is employed. The simulation results performed help clarify the influence of the sea state on ship wake visualization in SAR imagery.

Ship wake detection is of great importance in the characterisation of synthetic aperture radar (SAR) images of the ocean surface since wakes usually carry essential information about vessels. Most detection methods exploit the linear characteristics of the ship wakes and transform the lines in the spatial domain into bright or dark points in a transform domain, such as the Radon or Hough transforms. This paper proposes an innovative ship wake detection method based on sparse regularisation to obtain the Radon transform of the SAR image, in which the linear features are enhanced. The corresponding cost function utilizes the Cauchy prior, and on this basis, the Cauchy proximal operator is proposed. A proximal Markov chain Monte Carlo (p-MCMC) based Bayesian method, the Moreau-Yoshida unadjusted Langevin algorithm (MYULA), which is computationally efficient and robust is used to reconstruct the image in the transform domain by minimizing the negative log-posterior distribution. The detection accuracy of the Cauchy prior based approach is 86.7%, which is demonstrated by experiments over six COSMO-SkyMed images.

The analysis of ocean surface is widely performed using synthetic aperture radar (SAR) imagery as it yields information for wide areas under challenging weather conditions, during day or night, etc. Speckle noise constitutes however the main reason for reduced performance in applications such as classification, ship detection, target tracking and so on. This paper presents an investigation into the despeckling of SAR images of the ocean that include ship wake structures, via sparse regularisation using the Cauchy proximal operator. We propose a closed form expression for calculating the proximal operator for the Cauchy prior, which makes it applicable in generic proximal splitting algorithms. In our experiments, we simulate SAR images of moving vessels and their wakes. The performance of the proposed method is evaluated in comparison to the L1 and TV norm regularisation functions. The results show a superior performance of the proposed method for all the utilised images generated.

In order to analyze synthetic aperture radar (SAR) images of the sea surface, ship wake detection is essential for extracting information on the wake generating vessels. One possibility is to assume a linear model for wakes, in which case detection approaches are based on transforms such as Radon and Hough. These express the bright (dark) lines as peak (trough) points in the transform domain. In this article, ship wake detection is posed as an inverse problem, with the associated cost function including a sparsity enforcing penalty, i.e., the generalized minimax concave (GMC) function. Despite being a nonconvex regularizer, the GMC penalty enforces the overall cost function to be convex. The proposed solution is based on a Bayesian formulation, whereby the point estimates are recovered using a maximum a posteriori (MAP) estimation. To quantify the performance of the proposed method, various types of SAR images are used, corresponding to TerraSAR-X, COSMO-SkyMed, Sentinel-1, and Advanced Land Observing Satellite 2 (ALOS2). The performance of various priors in solving the proposed inverse problem is first studied by investigating the GMC along with the L1, Lp, nuclear, and total variation (TV) norms. We show that the GMC achieves the best results and we subsequently study the merits of the corresponding method in comparison to two state-of-the-art approaches for ship wake detection. The results show that our proposed technique offers the best performance by achieving 80% success rate.

In[1], the captions forFigs. 3and5appeared incorrectly. The figures with their correct caption are presented here.

Ship wakes have crucial importance in the analysis of SAR images of the sea surface due to the information they carry about vessels. Since ship wakes mostly appear as lines in SAR images, line detection methods have been widely used for their identification. In the literature, common practice for detecting ship wakes is to use Hough and Radon transforms in which bright (dark) lines appear as peaks (troughs) points. In this paper, the ship wake detection problem is addressed as a Radon transform based inverse problem with a sparse non-convex generalized minimax concave (GMC) regularization. Despite being a non-convex regularizer, the GMC penalty enforces the cost function to be convex. The solution to this convex cost function optimisation is obtained in a Bayesian formulation and the lines are recovered as maximum a posteriori (MAP) point estimates with a sparse GMC based prior. The detection procedure consists of a restricted area search in the Radon domain and the validation of candidate wakes. The performance of the proposed method is demonstrated in TerraSAR-X images of five different ships and with a total of 19 visible ship wakes. The results show a successful detection performance of up to 84% for the utilised images.

Synthetic aperture radar (SAR) and ultrasound (US) are two important active imaging techniques for remote sensing, both of which are subject to speckle noise caused by coherent summation of back-scattered waves and subsequent nonlinear envelope transformations. Estimating the characteristics of this multiplicative noise is crucial to develop denoising methods and to improve statistical inference from remote sensing images. In this paper, reversible jump Markov chain Monte Carlo (RJMCMC) algorithm has been used with a wider interpretation and a recently proposed RJMCMC-based Bayesian approach, trans-space RJMCMC, has been utilized. The proposed method provides an automatic model class selection mechanism for remote sensing images of SAR and US where the model class space consists of popular envelope distribution families. The proposed method estimates the correct distribution family, as well as the shape and the scale parameters, avoiding performing an exhaustive search. For the experimental analysis, different SAR images of urban, forest and agricultural scenes, and two different US images of a human heart have been used. Simulation results show the efficiency of the proposed method in finding statistical models for speckle.