Digital Signal Processing最新文献

{"title":"Light field spatial super-resolution network based on spatial-angular asymmetry and non-local correlation","authors":"Huabo Zhang,&nbsp;Fen Chen,&nbsp;Lian Huang,&nbsp;Wei Wei,&nbsp;Zongju Peng","doi":"10.1016/j.dsp.2025.105139","DOIUrl":"10.1016/j.dsp.2025.105139","url":null,"abstract":"<div><div>In recent years, deep neural networks (DNNs) have made significant progress in the spatial super-resolution (SR) of light field (LF) images. However, existing methods fail to fully account for spatial-angular asymmetry and non-local correlation. As a result, it is challenging to fully exploit the rich spatial-angular features during LF image feature extraction. To address these issues, we propose a novel LF spatial SR network. Specifically, due to spatial-angular asymmetry, we design spatial feature extractor (SFE) and angular feature extractor (AFE) with different receptive fields. This asymmetrical design enables comprehensive extraction of rich spatial information and reduces angular information redundancy when processing sub-aperture images (SAI) and macro-pixel images (MacPI). Furthermore, based on spatial-angular non-local correlation, we propose an epipolar feature extractor (EFE) to deeply extract long-range spatial-angular feature information from the epipolar-plane image (EPI). Moreover, we integrate SFE, AFE, and EFE into a multi-dimensional feature extraction module (MDFEM) to efficiently process SAI, MacPI, and EPI. By cascading multiple MDFEMs, the proposed network can deeply explore the spatial and angular information of the LF. Experimental results on both real-world and synthetic LF datasets show that the proposed method outperforms state-of-the-art methods in terms of visual quality and quantitative metrics, and can be more effectively applied to LF tasks such as depth estimation and LF refocusing.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105139"},"PeriodicalIF":2.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-supervised ultrasound image denoising based on weighted joint loss","authors":"Chunlei Yu,&nbsp;Fuquan Ren,&nbsp;Shuang Bao,&nbsp;Yurong Yang,&nbsp;Xing Xu","doi":"10.1016/j.dsp.2025.105151","DOIUrl":"10.1016/j.dsp.2025.105151","url":null,"abstract":"<div><div>Speckle noise is an important degradation factor of ultrasound imaging, which affects its clinical application. Self-supervised denoising methods based on deep learning have been developing rapidly. However, most of them primarily address spatially independent noise and are not suitable for removing spatially correlated noise. In addition, as a difficult problem in the image denoising task, balancing noise removal and preserving image details has also been the research focus of various denoising methodologies. To address the above problems, this paper proposes a self-supervised ultrasound image denoising algorithm that utilizes a sampling method to construct sub-image pairs as supervision and uses different denoisers for joint training with a novel weighted joint loss. For the input raw noisy image, it is first chunked, then pixel points on the diagonal of the image chunks are randomly sampled and formed into subsampled image pairs as supervision to train the network. Considering the presence of regions in the image with different texture complexity, a joint model based on blind-neighborhood network and U-Net is used as denoising network in the training stage, which strives to remove the noise while preserving the image details. Additionally, this paper uses the standard deviation of local image blocks as the measure of texture complexity and transforms them to adaptive coefficients. In the training process, we use adaptive coefficients to construct the weighted joint loss functions for adjusting the degree of influence of two denoisers on model. In comparison with the self-supervised denoising algorithm Neighbor2Neighbor, the supervised denoising methods RNAN and Restormer, and non-learning denoising methods BM3D and OBNLM, the proposed method achieves better denoising effects on both synthetic images and real ultrasound images.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105151"},"PeriodicalIF":2.9,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wiener filters on graphs and distributed implementations","authors":"Cong Zheng ,&nbsp;Cheng Cheng ,&nbsp;Qiyu Sun","doi":"10.1016/j.dsp.2025.105156","DOIUrl":"10.1016/j.dsp.2025.105156","url":null,"abstract":"<div><div>In this paper, we introduce Wiener filters to recover deterministic and (wide-band) stationary graph signals from their observations corrupted by random noises, and we propose distributed algorithms to implement the Wiener filters. Furthermore, the proposed algorithms can be implemented on distributed networks in which agents are equipped with a data processing subsystem for limited data storage and computation power, and with a one-hop communication subsystem for direct data exchange only with their adjacent agents. Our simulations indicate that the proposed Wiener filtering procedure works well on estimating synthetic (wide-band) stationary signals and real temperature datasets from their noisy observations.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105156"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint variable factor subspace tracking and federated Kalman filtering for multi-terminal distributed cooperative communications","authors":"Qin Zhang ,&nbsp;Yanan Yu ,&nbsp;Hai Li ,&nbsp;Zhengyu Song","doi":"10.1016/j.dsp.2025.105150","DOIUrl":"10.1016/j.dsp.2025.105150","url":null,"abstract":"<div><div>In recent years, distributed cooperative communications systems have demonstrated great potentials in terms of small size, lightweight, low power consumption, and low cost, allowing for the expansion of transmission range for various tasks. However, issues such as high-precision time-frequency synchronization and complex time-varying channels limit the application of distributed cooperative communications in practical communications systems. Moreover, the residual frequency offset, influenced by the accuracy of frequency offset estimation algorithms and node movement, introduces time-accumulating phase errors into each node's signal, thereby affecting signal consistency. In this paper, we propose a joint multi-terminal phase tracking and notch optimization scheme to address the limitations of time-varying phase errors in distributed nodes and mutual interference between multi-terminal signals in the multi-terminal distributed cooperative communications receiver model. In order to reduce the computational complexity, the original scheme is simplified and decoupled into the estimation of the number of terminals, distributed phase tracking, and notch optimization, where the estimation of the number of terminals is a prerequisite for multi-terminal phase tracking. Specifically, during the distributed phase tracking phase, considering the relative movement of far-field multi-terminals and distributed nodes, a federated Kalman-filter-corrected variable factor subspace tracking method is designed to address the multi-terminal phase tracking problem under low signal-to-noise ratio (SNR) conditions. Multi-terminal signal notch optimization eliminates the impact of overlapping signals on demodulation, resulting in better multi-terminal signal demodulation. Simulation results show that in multi-terminal distributed cooperative communications, the Kalman-filter-corrected variable factor subspace tracking algorithm exhibits better multi-terminal tracking capabilities compared to traditional phase tracking algorithms. More importantly, reliable phase tracking and notch optimization under low SNR conditions can effectively improve the demodulation performance of wireless distributed cooperative communications.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105150"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An all-digital coherent AFSK demodulator for CubeSat applications","authors":"Rubem Vasconcelos Pacelli ,&nbsp;Rodrigo de Lima Florindo ,&nbsp;Felix Antreich ,&nbsp;Antônio Macilio Pareira de Lucena","doi":"10.1016/j.dsp.2025.105147","DOIUrl":"10.1016/j.dsp.2025.105147","url":null,"abstract":"<div><div>Audio frequency-shift keying (AFSK) is a widely adopted modulation scheme for CubeSat systems due to its favorable bandwidth efficiency and implementation simplicity. However, coherent detection usually is avoided because synchronization impairments, caused by intense line-of-sight (LOS) dynamics inherent in low Earth orbit (LEO), may significantly degrade the bit error rate (BER). This paper presents a new all-digital coherent AFSK demodulator based on a Kalman filter (KF) for carrier phase and timing delay synchronization and the Viterbi algorithm for bit detection. The Viterbi algorithm is employed for maximum likelihood sequence detection, and the detected bit statistics are fed back to the KF to estimate phase shift, Doppler frequency shift, and Doppler drift induced by the LOS dynamics. Original mathematical analyses are derived to provide a theoretical foundation for the proposed demodulator's operation, specifically addressing its synchronization accuracy in dynamic LEO environments. The proposed demodulator is evaluated considering an additive white Gaussian noise channel with real CubeSat orbits. The performance results obtained through computer simulations demonstrate that the proposed model can withstand such scenarios with a gain of 5 dB in terms of BER compared to the conventional noncoherent AFSK demodulator. The KF performance is assessed using a moving root-mean-square error (MRMSE) statistic and the trace of its state error covariance matrix estimate.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105147"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pattern synthesis of sparse linear arrays based on the atomic norm minimization and alternating direction method of multipliers approach","authors":"Qiang Guo ,&nbsp;Moukun Fang ,&nbsp;Stepan Douplii ,&nbsp;Yani Wang","doi":"10.1016/j.dsp.2025.105160","DOIUrl":"10.1016/j.dsp.2025.105160","url":null,"abstract":"<div><div>To address the mesh mismatch issue and enhance array performance, this paper proposes a design algorithm for sparse reconfigurable linear arrays based on the ANM-ADMM framework. Initially, the algorithm formulates a meshless sparse optimization model grounded on the low-dimensional semidefinite programming theory of atomic norm minimization. This model simultaneously optimizes the quantity of array elements, their placements, and their excitations. Subsequently, an efficient iterative algorithm solves the low-rank Toeplitz matrix using the alternating direction method of multipliers (ADMM). Finally, the Root-MUSIC algorithm is employed to determine the locations and excitations of the array components in the sparsely reconfigurable linear array, which is designed using the ANM-ADMM approach. Since the proposed algorithm operates in a continuous domain, it effectively addresses the mesh mismatch problem, thereby enhancing the matching accuracy of reconstructed linear array beampatterns. Simulation results demonstrate that compared to existing algorithms, the proposed method requires fewer array elements while achieving higher matching accuracy and better fitting performance.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105160"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ARAFNet: An attribute refinement attention fusion network for advanced visual captioning","authors":"Md. Bipul Hossen ,&nbsp;Zhongfu Ye ,&nbsp;Md. Shamim Hossain ,&nbsp;Md. Imran Hossain","doi":"10.1016/j.dsp.2025.105155","DOIUrl":"10.1016/j.dsp.2025.105155","url":null,"abstract":"<div><div>Visual captioning, at the nexus of computer vision and natural language processing, is one of the pivotal aspects of multimedia content understanding, demands precise and contextually fitting image descriptions. Attribute-based approaches with attention mechanisms are effective in this realm. However, many of these approaches struggle to capture semantic details due to the prediction of irrelevant attributes and reduced performance. In response to these challenges, we propose an innovative solution: the Attribute Refinement Attention Fusion Network (ARAFNet), which aims to produce significant captions by distinctly identifying major objects and background information. The model features a comprehensive Attribute Refinement Attention (ARA) module, equipped with an attribute attention mechanism, which interactively extracts the most important attributes according to the linguistic context. Diverse attributes are employed at different time steps, enhancing the model's capability to utilize semantic features effectively while also filtering out irrelevant attribute words, thereby enhancing the precision of semantic guidance. An integrated fusion mechanism is then introduced to narrow the semantic gap between visual and attribute features. Finally, this fusion mechanism combined with the language LSTM to generate precise and contextually relevant captions. Extensive experimentation demonstrates our model's superiority over advanced counterparts, achieving an average CIDEr-D score of 11.88% on the Flickr30K dataset and 11.25% on the MS-COCO dataset through cross-entropy optimization. The ARAFNet model consistently outperforms the baseline model across a diverse range of evaluation metrics and makes a significant contribution to the field of image captioning precision. The implementing code and associated materials will be published at <span><span>https://github.com/mdbipu/ARAFNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105155"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"One-class IoT anomaly detection system using an improved interpolated deep SVDD autoencoder with adversarial regularizer","authors":"Abdulkarim Katbi,&nbsp;Riadh Ksantini","doi":"10.1016/j.dsp.2025.105153","DOIUrl":"10.1016/j.dsp.2025.105153","url":null,"abstract":"<div><div>The rapid proliferation of Internet of Things (IoT) devices and their integration into various sectors have significantly increased their exposure to security threats. Traditional Machine Learning (ML) methods, as well as some Deep Learning (DL) approaches, often fall short in addressing the unique challenges posed by contemporary IoT datasets, such as non-homogeneity, disparity, and high dimensionality. To tackle these challenges, this paper introduces a novel anomaly detection system specifically designed for IoT environments. The proposed model focused on optimizing the projected latent space to produce more effective separating hyperspheres, which will significantly improve the precision and robustness of anomaly detection. Experimental evaluation of multiple IoT datasets demonstrates that the system is capable of achieving state-of-the-art results compared to other shallow and deep learning approaches.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105153"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TMSF: Taylor expansion approximation network with multi-stage feature representation for optical flow estimation","authors":"Zhenghua Huang ,&nbsp;Wen Hu ,&nbsp;Zifan Zhu ,&nbsp;Qian Li ,&nbsp;Hao Fang","doi":"10.1016/j.dsp.2025.105157","DOIUrl":"10.1016/j.dsp.2025.105157","url":null,"abstract":"<div><div>Optical flow estimation is a fundamental task in computer vision. Existing CNN-based and transformer-based methods have proven their powerful ability in generating preferable performance, but they still suffer from the loss of fine details and objects' shape. To cope with these problems, this paper develops a Taylor expansion approximation network with multi-stage feature representation, namely TMSF, including a basic network and a refine network. In the basic network, multi-stage modules, including feature enhancement module (FEM) for enriching image features, feature/context network for feature extraction, and iterative update module (IUM) for coarse optical flow estimation, are employed to represent fine features. In the refine network, a refinement architecture is constructed based on the third-order Taylor approximation expansion to further refine features from the basic network for optical flow, in which a feature attention module (FAM) is used to estimate each derivative layer. Meanwhile, a novel loss function is formed by end-point-error (EPE) and structural similarity (SSIM) to ensure the convergence of our TMSF to a satisfactory solution. Quantitative associated with qualitative experimental results validate that our TMSF performs better than state-of-the-art optical flow estimation methods on performance improvement and shape preservation. The code will be available at <span><span>https://github.com/MysterYxby/TMSF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105157"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MIR-YOLO: Remote sensing small target detection network based on visible-infrared dual modality","authors":"Jinli Zhong,&nbsp;Jianxun Zhang","doi":"10.1016/j.dsp.2025.105158","DOIUrl":"10.1016/j.dsp.2025.105158","url":null,"abstract":"<div><div>The study of remote sensing detection of small targets is of great significance in the fields of traffic monitoring and military target localization and identification. However, due to small-scale targets occupying fewer pixels, they lack not only physical features such as texture and shape, but also the effective information is lost during forward propagation of the network, leading to inappropriate gradient updates, which in turn affects the accuracy of target detection. To this end, this paper introduces a Multi-order Gated Aggregation module based on Inverted Residual (MIR). This module, designed around the concept of manifolds of interest, effectively adapts to multi-scale variations and significantly mitigates information loss for small-scale targets. Furthermore, we take advantage of the complementary advantages of multi-modal information and design a multistage dual modality fusion framework, which significantly improves detection accuracy. To address the complexity and diversity of remote sensing scenes, this paper proposes a Gradient Path-Based Vision LSTM (GViL) block. This module employs the high efficiency of gradient path analysis and achieves significant results by leveraging the modeling capability of Vision LSTM (ViL) for contexts. We have verified the performance of the model in this paper on the multi-modal remote sensing datasets VEDAI and Dronevehicle, and achieved excellent results. On the VEDAI dataset, the <span><math><mtext>m</mtext><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></math></span> of our model increases by 5.8% over the basic model (YOLOv8s), and by 3.7% over this year's target detection state-of-the-art method, YOLOv9.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105158"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}