Pub Date : 2025-12-21DOI: 10.1016/j.sigpro.2025.110456
Do-Hyun Park, Min-Wook Jeon, Hyoung-Nam Kim
The rising demand for detecting hazardous situations has led to increased interest in radar-based human activity recognition (HAR). Conventional radar-based HAR methods predominantly rely on micro-Doppler spectrograms for recognition tasks. However, conventional spectrograms employ a fixed resolution regardless of the varying characteristics of human activities, leading to limited representation of micro-Doppler signatures. To address this limitation, we propose a time-frequency domain representation method that adaptively adjusts the resolution based on activity characteristics. This approach adaptively adjusts the spectrogram resolution in a nonlinear manner, emphasizing frequency ranges that vary with activity intensity and are critical to capturing micro-Doppler signatures. We validate the proposed method by training deep learning-based HAR models on datasets generated using our adaptive representation. Experimental results demonstrate that models trained with our method achieve superior recognition accuracy compared to those trained with conventional methods.
{"title":"Activity-dependent resolution adjustment for radar-based human activity recognition","authors":"Do-Hyun Park, Min-Wook Jeon, Hyoung-Nam Kim","doi":"10.1016/j.sigpro.2025.110456","DOIUrl":"10.1016/j.sigpro.2025.110456","url":null,"abstract":"<div><div>The rising demand for detecting hazardous situations has led to increased interest in radar-based human activity recognition (HAR). Conventional radar-based HAR methods predominantly rely on micro-Doppler spectrograms for recognition tasks. However, conventional spectrograms employ a fixed resolution regardless of the varying characteristics of human activities, leading to limited representation of micro-Doppler signatures. To address this limitation, we propose a time-frequency domain representation method that adaptively adjusts the resolution based on activity characteristics. This approach adaptively adjusts the spectrogram resolution in a nonlinear manner, emphasizing frequency ranges that vary with activity intensity and are critical to capturing micro-Doppler signatures. We validate the proposed method by training deep learning-based HAR models on datasets generated using our adaptive representation. Experimental results demonstrate that models trained with our method achieve superior recognition accuracy compared to those trained with conventional methods.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110456"},"PeriodicalIF":3.6,"publicationDate":"2025-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-20DOI: 10.1016/j.sigpro.2025.110451
Hui Liu , Jicheng Zhu , Hengtai Li , Christian Desrosiers , Caiming Zhang
Multimodal medical image registration and fusion integrate complementary features from different modalities, to enhance diagnostic accuracy and provide comprehensive clinical insights. Existing approaches face critical shortcomings in feature alignment, computational efficiency and clinical interpretability, demanding a novel coupled framework to address these issues. Additionally, the lack of open-source benchmark datasets at the systemic level persists as a major bottleneck. Thus, a novel Imaging Coupled Filtering (ICF), means multi-channel image features coupling filtering, is proposed in this work. First, ICF decomposes source images from different modalities into four feature channels: smoothing, texture, contour and edge. Then, intra-channel fusion strategies are designed to generate fused images. Specifically, in the smoothing channels, we propose a visual saliency decomposition strategy to comprehensively extract energy and partial fiber texture features through multi-scale and multi-dimensional analysis, thereby optimizing the utilization of latent feature information. For the texture channels, we propose a novel texture enhancement operator designed to effectively capture fine details and hierarchical structural information, which enables accurate differentiation of invasion states in adherent lesions. Finally, an imaging coupling mechanism is presented to achieve fused results based on the weights of multi-feature representation. Additionally, we have registered and released 403 groups of multimodal abdominal medical images (Ab-MI) for research purposes. Experiments on Atlas and Ab-MI demonstrate that, compared to six state-of-the-art methods, ICF achieves superior results in terms of visual effects, objective metrics and computational efficiency.
{"title":"Imaging coupled filtering: A unified multi-channel framework for multimodal medical image registration and fusion","authors":"Hui Liu , Jicheng Zhu , Hengtai Li , Christian Desrosiers , Caiming Zhang","doi":"10.1016/j.sigpro.2025.110451","DOIUrl":"10.1016/j.sigpro.2025.110451","url":null,"abstract":"<div><div>Multimodal medical image registration and fusion integrate complementary features from different modalities, to enhance diagnostic accuracy and provide comprehensive clinical insights. Existing approaches face critical shortcomings in feature alignment, computational efficiency and clinical interpretability, demanding a novel coupled framework to address these issues. Additionally, the lack of open-source benchmark datasets at the systemic level persists as a major bottleneck. Thus, a novel Imaging Coupled Filtering (ICF), means multi-channel image features coupling filtering, is proposed in this work. First, ICF decomposes source images from different modalities into four feature channels: smoothing, texture, contour and edge. Then, intra-channel fusion strategies are designed to generate fused images. Specifically, in the smoothing channels, we propose a visual saliency decomposition strategy to comprehensively extract energy and partial fiber texture features through multi-scale and multi-dimensional analysis, thereby optimizing the utilization of latent feature information. For the texture channels, we propose a novel texture enhancement operator designed to effectively capture fine details and hierarchical structural information, which enables accurate differentiation of invasion states in adherent lesions. Finally, an imaging coupling mechanism is presented to achieve fused results based on the weights of multi-feature representation. Additionally, we have registered and released 403 groups of multimodal abdominal medical images (Ab-MI) for research purposes. Experiments on Atlas and Ab-MI demonstrate that, compared to six state-of-the-art methods, ICF achieves superior results in terms of visual effects, objective metrics and computational efficiency.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110451"},"PeriodicalIF":3.6,"publicationDate":"2025-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145842703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-20DOI: 10.1016/j.sigpro.2025.110452
Philippe Flores , Konstantin Usevich , David Brie
In this article, a probability mass function (PMF) estimation method called partial coupled tensor factorization of 3D marginals or PCTF3D is proposed. To tame the inherent PMF estimation curse of dimensionality, PCTF3D’s principle is to couple 3-dimensional data projections – seen as order-3 tensors – to obtain a low-rank tensor approximation of the PMF. The contribution of PCTF3D relies on partial coupling which consists in choosing a limited subset of 3D marginals. While PMF estimation is possible with all marginals, coupling only a subset of marginals like in PCTF3D permits to reduce the computational burden without losing significant estimation performance. A key concept of PCTF3D is the choice of marginals to be coupled: this problem is formulated and studied with hypergraphs. This Part I paper introduces the algorithmic framework of PCTF3D: optimization problem, coupling strategies, numerical experiments and a real data application of PCTF3D. On the other hand, the Part II paper studies coupled tensor uniqueness properties of the model introduced by PCTF3D.
{"title":"Coupled tensor models for probability mass function estimation: Part I, principles and algorithms","authors":"Philippe Flores , Konstantin Usevich , David Brie","doi":"10.1016/j.sigpro.2025.110452","DOIUrl":"10.1016/j.sigpro.2025.110452","url":null,"abstract":"<div><div>In this article, a probability mass function (PMF) estimation method called partial coupled tensor factorization of 3D marginals or PCTF3D is proposed. To tame the inherent PMF estimation curse of dimensionality, PCTF3D’s principle is to couple 3-dimensional data projections – seen as order-3 tensors – to obtain a low-rank tensor approximation of the PMF. The contribution of PCTF3D relies on partial coupling which consists in choosing a limited subset of 3D marginals. While PMF estimation is possible with all marginals, coupling only a subset of marginals like in PCTF3D permits to reduce the computational burden without losing significant estimation performance. A key concept of PCTF3D is the choice of marginals to be coupled: this problem is formulated and studied with hypergraphs. This Part I paper introduces the algorithmic framework of PCTF3D: optimization problem, coupling strategies, numerical experiments and a real data application of PCTF3D. On the other hand, the Part II paper studies coupled tensor uniqueness properties of the model introduced by PCTF3D.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110452"},"PeriodicalIF":3.6,"publicationDate":"2025-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-20DOI: 10.1016/j.sigpro.2025.110453
Philippe Flores , Konstantin Usevich , David Brie
In this paper, uniqueness properties of a coupled factorization of 3D marginal tensors (or PCTF3D) are studied. The PCTF3D method (detailed in the Part I article) performs estimation of probability mass functions (PMFs) by coupling 3D marginals, seen as order-3 tensors. The core novelty of PCTF3D’s approach relies on the partial coupling which consists in choosing a limited set of 3D marginals to be coupled. PCTF3D uniqueness is examined through the prism of polynomial mappings and their recoverability. A numerical algorithm is proposed for finding the maximal rank for which recoverability is guaranteed. This approach properly accounts for the coupling strategy and simplex constraints. Using the proposed algorithm, the different coupling strategies from Part I are examined with respect to their uniqueness properties. Finally, a new identifiability bound is given for a so-called Cartesian coupling which improves existing sufficient bounds available in the literature.
{"title":"Coupled tensor models for probability mass function estimation: Part II, uniqueness of the model","authors":"Philippe Flores , Konstantin Usevich , David Brie","doi":"10.1016/j.sigpro.2025.110453","DOIUrl":"10.1016/j.sigpro.2025.110453","url":null,"abstract":"<div><div>In this paper, uniqueness properties of a coupled factorization of 3D marginal tensors (or PCTF3D) are studied. The PCTF3D method (detailed in the Part I article) performs estimation of probability mass functions (PMFs) by coupling 3D marginals, seen as order-3 tensors. The core novelty of PCTF3D’s approach relies on the partial coupling which consists in choosing a limited set of 3D marginals to be coupled. PCTF3D uniqueness is examined through the prism of polynomial mappings and their recoverability. A numerical algorithm is proposed for finding the maximal rank for which recoverability is guaranteed. This approach properly accounts for the coupling strategy and simplex constraints. Using the proposed algorithm, the different coupling strategies from Part I are examined with respect to their uniqueness properties. Finally, a new identifiability bound is given for a so-called <em>Cartesian coupling</em> which improves existing sufficient bounds available in the literature.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110453"},"PeriodicalIF":3.6,"publicationDate":"2025-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The foveal mechanism of the human retina produces sharp central vision with a blurred periphery. By generating foveated images that more closely replicate this mechanism, it is possible to significantly enhance immersion and deliver a more natural visual experience in virtual environments and related applications. In this paper, we proposed a two-stage foveated image reconstruction method to simulate a biologically plausible foveated retina. In the first stage, a monocular humanoid field of view (FOV) model is designed based on the mapping relationship between the human retina and the camera sensor, enabling the capture of images with a human-like FOV using a commonly available uniform-pixel camera. During the second stage, a non-uniform pixel sampling approach is presented to approximate the spatial distribution of photoreceptors across the retina, combined with biharmonic spline-based interpolation for natural-looking resampling. Qualitative and quantitative results demonstrate that the foveated images generated by the proposed method exhibit better consistency with human visual perception than existing representative methods.
{"title":"A method for retinal inspired foveated image reconstruction","authors":"Haoming Xiang, Xiaohua Xia, Haiyun Tan, Zhiwei Duan","doi":"10.1016/j.sigpro.2025.110459","DOIUrl":"10.1016/j.sigpro.2025.110459","url":null,"abstract":"<div><div>The foveal mechanism of the human retina produces sharp central vision with a blurred periphery. By generating foveated images that more closely replicate this mechanism, it is possible to significantly enhance immersion and deliver a more natural visual experience in virtual environments and related applications. In this paper, we proposed a two-stage foveated image reconstruction method to simulate a biologically plausible foveated retina. In the first stage, a monocular humanoid field of view (FOV) model is designed based on the mapping relationship between the human retina and the camera sensor, enabling the capture of images with a human-like FOV using a commonly available uniform-pixel camera. During the second stage, a non-uniform pixel sampling approach is presented to approximate the spatial distribution of photoreceptors across the retina, combined with biharmonic spline-based interpolation for natural-looking resampling. Qualitative and quantitative results demonstrate that the foveated images generated by the proposed method exhibit better consistency with human visual perception than existing representative methods.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110459"},"PeriodicalIF":3.6,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145802318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-19DOI: 10.1016/j.sigpro.2025.110457
Zipeng Li , Yafeng Guo , Jun Wang
The recently emerged hybrid mechanism-data driven KalmanNet can improve the accuracy of data fusion in the presence of model mismatch by implicitly extracting hidden priori information through learning from data. However, KalmanNet only learns the Kalman gain from data, while a substantial amount of hidden information remains unexploited. Besides the Kalman gain, the accuracy of the process model is also a critical factor affecting the performance of the filter. Unfortunately, in many practical applications, obtaining accurate process models by relying solely on mechanism modeling remains challenging. To further improve the filter performance, this paper proposes an enhanced KalmanNet that simultaneously learn both the Kalman gain and the unmodeled effects of the process model, thereby enabling more effective exploitation of the implicit information in the data. The experiment of vehicle localization on real data from public dataset demonstrates that the proposed method significantly improves the estimation accuracy compared to KalmanNet.
{"title":"Enhanced KalmanNet for accurate data fusion","authors":"Zipeng Li , Yafeng Guo , Jun Wang","doi":"10.1016/j.sigpro.2025.110457","DOIUrl":"10.1016/j.sigpro.2025.110457","url":null,"abstract":"<div><div>The recently emerged hybrid mechanism-data driven KalmanNet can improve the accuracy of data fusion in the presence of model mismatch by implicitly extracting hidden priori information through learning from data. However, KalmanNet only learns the Kalman gain from data, while a substantial amount of hidden information remains unexploited. Besides the Kalman gain, the accuracy of the process model is also a critical factor affecting the performance of the filter. Unfortunately, in many practical applications, obtaining accurate process models by relying solely on mechanism modeling remains challenging. To further improve the filter performance, this paper proposes an enhanced KalmanNet that simultaneously learn both the Kalman gain and the unmodeled effects of the process model, thereby enabling more effective exploitation of the implicit information in the data. The experiment of vehicle localization on real data from public dataset demonstrates that the proposed method significantly improves the estimation accuracy compared to KalmanNet.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110457"},"PeriodicalIF":3.6,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145842702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-17DOI: 10.1016/j.sigpro.2025.110440
Yi Liu, Shunyi Zhao, Xiaoli Luan, Fei Liu
In this paper, a cumulative finite impulse response (FIR) filter is developed for linear discrete time-invariant (TI) systems with temporary modeling uncertainties, which refer to short-term modelling errors that occur intermittently in the system dynamics. The filter is derived based on a cumulative risk-sensitive cost function that accounts for the sum of estimation errors from the initial time to the present moment within the estimation horizon. In contrast to the instantaneous-type filter, the proposed filter considers a wider range of estimation errors, resulting in better estimation performance. To derive the new filter, the cumulative exponential cost function is reformulated into a solvable max-min optimization problem, and then state estimator is achieved by solving this optimization problem. Simulation studies, including an engine model and a moving target tracking scenario, demonstrate that the proposed filter exhibits superior robustness to temporary modeling uncertainties compared to the instantaneous risk-sensitive FIR (IRSFIR) filter, the risk-sensitive filter (RSF), and the H∞ filter.
{"title":"Cumulative risk-sensitive FIR filter for linear discrete time-invariant state-space models","authors":"Yi Liu, Shunyi Zhao, Xiaoli Luan, Fei Liu","doi":"10.1016/j.sigpro.2025.110440","DOIUrl":"10.1016/j.sigpro.2025.110440","url":null,"abstract":"<div><div>In this paper, a cumulative finite impulse response (FIR) filter is developed for linear discrete time-invariant (TI) systems with temporary modeling uncertainties, which refer to short-term modelling errors that occur intermittently in the system dynamics. The filter is derived based on a cumulative risk-sensitive cost function that accounts for the sum of estimation errors from the initial time to the present moment within the estimation horizon. In contrast to the instantaneous-type filter, the proposed filter considers a wider range of estimation errors, resulting in better estimation performance. To derive the new filter, the cumulative exponential cost function is reformulated into a solvable max-min optimization problem, and then state estimator is achieved by solving this optimization problem. Simulation studies, including an engine model and a moving target tracking scenario, demonstrate that the proposed filter exhibits superior robustness to temporary modeling uncertainties compared to the instantaneous risk-sensitive FIR (IRSFIR) filter, the risk-sensitive filter (RSF), and the <em>H</em><sub>∞</sub> filter.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110440"},"PeriodicalIF":3.6,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145842705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-16DOI: 10.1016/j.sigpro.2025.110449
Peichao Wang, Qian He
This paper proposes to employ a multiple-input multiple-output (MIMO) radar system for non-contact sudden abnormal heart rate (HR) alerting, where the HR changes from an unknown initial normal value to an unknown abnormal value. By developing a signal model for the non-contact abnormal HR alerting using MIMO radar, we first propose a pre-change HR maximum likelihood (ML) estimator to estimate the initial HR and derive the Cramer-Rao bound (CRB) for the estimation performance evaluation. Then, employing the estimated initial HR, we investigate generalized likelihood ratio test (GLRT) based quickest change detector for immediate abnormal HR alerting, called quickest abnormal HR alerting (QAHA). The asymptotic test statistic of the GLRT based QAHA is derived in closed-form, and the theoretical bounds of the mean time to false alarm (MTFA) and worst case average detection delay (WADD) are derived for performance analysis. Numerical and experimental results validate the correctness of the theoretical analysis and demonstrate the efficiency of our method compared with state-of-the-art methods.
{"title":"Sudden abnormal heart rate alerting based on MIMO radar quickest change detection","authors":"Peichao Wang, Qian He","doi":"10.1016/j.sigpro.2025.110449","DOIUrl":"10.1016/j.sigpro.2025.110449","url":null,"abstract":"<div><div>This paper proposes to employ a multiple-input multiple-output (MIMO) radar system for non-contact sudden abnormal heart rate (HR) alerting, where the HR changes from an unknown initial normal value to an unknown abnormal value. By developing a signal model for the non-contact abnormal HR alerting using MIMO radar, we first propose a pre-change HR maximum likelihood (ML) estimator to estimate the initial HR and derive the Cramer-Rao bound (CRB) for the estimation performance evaluation. Then, employing the estimated initial HR, we investigate generalized likelihood ratio test (GLRT) based quickest change detector for immediate abnormal HR alerting, called quickest abnormal HR alerting (QAHA). The asymptotic test statistic of the GLRT based QAHA is derived in closed-form, and the theoretical bounds of the mean time to false alarm (MTFA) and worst case average detection delay (WADD) are derived for performance analysis. Numerical and experimental results validate the correctness of the theoretical analysis and demonstrate the efficiency of our method compared with state-of-the-art methods.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"243 ","pages":"Article 110449"},"PeriodicalIF":3.6,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-16DOI: 10.1016/j.sigpro.2025.110455
Xiaonan Li , Ping Ma , Guanghui Sun , Tao Chao , Ming Yang
This paper presents a novel variational cubature Kalman filter (CKF) to improve robustness against non-stationary process and measurement noises. The proposed method utilizes a hierarchical Gaussian mixture (HGM) and the Gamma distribution to achieve this. Specifically, we propose a state prediction model using a novel HGM distribution, which is composed of several sub-models, to enhance robustness against non-stationary process noises. We utilize auxiliary variables that follow exponential and inverse-Wishart (IW) distributions to adjust the sub-model’s covariance matrix. The Dirichlet and categorical distributions are employed to adaptively mix the hierarchical Gaussian distributions. The mixed distribution can handle scenarios with both normal and abnormal process noise, and this is the reason for its robustness. In addition, observations may be non-stationary due to widespread sensor failures in practical engineering. To address this issue, we utilize an auxiliary variable to update the measurement noise variance (MNV). Thereby, the MNV is adaptively adjusted, which modifies the Kalman gain to mitigate the influence of non-stationary noise. The unknown parameters and states are updated online using the variational Bayesian (VB) framework. Target-tracking tests demonstrate that our method is more accurate than the comparison methods.
{"title":"A novel CKF using gamma and hierarchical Gaussian mixture distribution based on the variational Bayesian","authors":"Xiaonan Li , Ping Ma , Guanghui Sun , Tao Chao , Ming Yang","doi":"10.1016/j.sigpro.2025.110455","DOIUrl":"10.1016/j.sigpro.2025.110455","url":null,"abstract":"<div><div>This paper presents a novel variational cubature Kalman filter (CKF) to improve robustness against non-stationary process and measurement noises. The proposed method utilizes a hierarchical Gaussian mixture (HGM) and the Gamma distribution to achieve this. Specifically, we propose a state prediction model using a novel HGM distribution, which is composed of several sub-models, to enhance robustness against non-stationary process noises. We utilize auxiliary variables that follow exponential and inverse-Wishart (IW) distributions to adjust the sub-model’s covariance matrix. The Dirichlet and categorical distributions are employed to adaptively mix the hierarchical Gaussian distributions. The mixed distribution can handle scenarios with both normal and abnormal process noise, and this is the reason for its robustness. In addition, observations may be non-stationary due to widespread sensor failures in practical engineering. To address this issue, we utilize an auxiliary variable to update the measurement noise variance (MNV). Thereby, the MNV is adaptively adjusted, which modifies the Kalman gain to mitigate the influence of non-stationary noise. The unknown parameters and states are updated online using the variational Bayesian (VB) framework. Target-tracking tests demonstrate that our method is more accurate than the comparison methods.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"242 ","pages":"Article 110455"},"PeriodicalIF":3.6,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-15DOI: 10.1016/j.sigpro.2025.110454
Zedong Liang , Lu Liu , Xiaomeng Zhang , Shuo Zhang , Jinliang Ding , Hongli Xu , Xiangyue Zhang , Qi Liu
In nonlinear non-Gaussian target tracking localization systems, measurement noise intensity and distribution states exhibit stochastic uncertainties induced by environmental disturbances and outliers. Existing filtering schemes necessitate simultaneous approximation of noise distribution and precise covariance modeling, invariably compromising computational efficiency while risking model mismatch-induced performance degradation. Therefore, this paper proposes a target tracking localization algorithm integrating jointly Extended Dimension Cubature Kalman Filter (ECKF) and Variational Bayesian (VB). Firstly, the dimension is extended by augmenting the state vectors of adjacent moments to reduce the iterative calculation time. Secondly, ECKF is used to update the propagation prior covariance matrix to realize state prediction and capture the state uncertainty under nonlinear transformation. Finally, based on the residual error judged by the Grubbs criterion, the VB modeling is used to optimize the measurement noise distribution state, and the posterior distribution of the state estimation is adjusted by combining the observation value and the variational inference to complete the state update and target tracking. Simulation and off-line results indicate that the ECKF-VB algorithm can ensure good target tracking localization accuracy and robustness under various measurement scenarios.
{"title":"A fault-tolerant target tracking localization algorithm based on extended dimension cubature kalman filter and variational bayesian","authors":"Zedong Liang , Lu Liu , Xiaomeng Zhang , Shuo Zhang , Jinliang Ding , Hongli Xu , Xiangyue Zhang , Qi Liu","doi":"10.1016/j.sigpro.2025.110454","DOIUrl":"10.1016/j.sigpro.2025.110454","url":null,"abstract":"<div><div>In nonlinear non-Gaussian target tracking localization systems, measurement noise intensity and distribution states exhibit stochastic uncertainties induced by environmental disturbances and outliers. Existing filtering schemes necessitate simultaneous approximation of noise distribution and precise covariance modeling, invariably compromising computational efficiency while risking model mismatch-induced performance degradation. Therefore, this paper proposes a target tracking localization algorithm integrating jointly Extended Dimension Cubature Kalman Filter (ECKF) and Variational Bayesian (VB). Firstly, the dimension is extended by augmenting the state vectors of adjacent moments to reduce the iterative calculation time. Secondly, ECKF is used to update the propagation prior covariance matrix to realize state prediction and capture the state uncertainty under nonlinear transformation. Finally, based on the residual error judged by the Grubbs criterion, the VB modeling is used to optimize the measurement noise distribution state, and the posterior distribution of the state estimation is adjusted by combining the observation value and the variational inference to complete the state update and target tracking. Simulation and off-line results indicate that the ECKF-VB algorithm can ensure good target tracking localization accuracy and robustness under various measurement scenarios.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"242 ","pages":"Article 110454"},"PeriodicalIF":3.6,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号