Digital Signal Processing最新文献_第2页

Multi-rate fusion estimation for multi-sensor systems over Gilbert-Elliott channels

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-10 DOI: 10.1016/j.dsp.2025.105237

Dan Liu , Wenhui Xiong , Wenbing Zhang , Ying Cui

{"title":"Multi-rate fusion estimation for multi-sensor systems over Gilbert-Elliott channels","authors":"Dan Liu , Wenhui Xiong , Wenbing Zhang , Ying Cui","doi":"10.1016/j.dsp.2025.105237","DOIUrl":"10.1016/j.dsp.2025.105237","url":null,"abstract":"<div><div>The distributed fusion estimation problem is discussed in this paper for a class of multi-rate multi-sensor systems. The measurements are assumed to be transmitted from the sensor to estimator over the Gilbert-Elliott channels governed by a two-state Markov chain due to the unreliable wireless network. Moreover, the probabilistic packet losses are considered in the Gilbert-Elliott channels, which is described by a random variable. The underlying system is measured by multiple sensors, where the sampling periods of sensors are integer multiples of the updating periods for system states. The above-mentioned multi-rate system is converted into a general single-rate one by the state iterative approach, and then a general system is put forward to characterize the dynamics from both the plant and transmission channels. Subsequently, the local estimators are devised to ensure the upper bounds of the estimation error covariances, and the estimator parameters are determined properly to minimize the derived upper bounds. In addition, the local estimates are fused by the covariance intersection method, and the corresponding consistency of the proposed fusion estimator is presented. Finally, a numerical example is given to illustrate the validity of the developed fusion estimation scheme.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105237"},"PeriodicalIF":2.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826330","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}

引用次数: 0

Matrix projection and its application in image processing

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-10 DOI: 10.1016/j.dsp.2025.105231

Xinyi Chen , Daizhan Cheng , Jun-e Feng

引用次数: 0

HFGL-Net: High-frequency guided multi-scale non-local network for remote sensing object detection

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-10 DOI: 10.1016/j.dsp.2025.105230

ZhiPing Dan , QiuYue Fu , LongHui Huang , DeAo Hu , XueFei Li , Hang Sun

{"title":"HFGL-Net: High-frequency guided multi-scale non-local network for remote sensing object detection","authors":"ZhiPing Dan , QiuYue Fu , LongHui Huang , DeAo Hu , XueFei Li , Hang Sun","doi":"10.1016/j.dsp.2025.105230","DOIUrl":"10.1016/j.dsp.2025.105230","url":null,"abstract":"<div><div>Recently, deep learning-based object detection methods have been extensively utilized in remote sensing image detection, resulting in notable progress. However, feature pyramid-based approaches for small object detection often fail to effectively utilize high-frequency information, such as edges and textures, which adversely affects the detection performance of small objects in remote sensing images. Moreover, existing channel attention mechanisms are limited by the sensory field, neglecting the effective integration of global context and local information, which adversely affects the learning of channel weights. To address these issues, a High-Frequency Guided Multi-Scale Non-Local Network (HFGL-Net) for remote sensing object detection is proposed. Specifically, the network's feature representation is enhanced by introducing a High-Frequency Component Enhancement Module (HCEM), which captures high-frequency image details through decomposition and explicitly guides the network with this information. Furthermore, the Multi-Scale Non-Local Channel Attention mechanism (MS-GLCA) is introduced, which integrates multi-scale and non-local perception mechanisms to adaptively balance multi-scale features and enhance the network's capability in capturing local features while preserving global dependencies, thereby optimizing feature weighting. Experimental results on the DIOR-H and DIOR-R benchmark datasets demonstrate that HFGL-Net surpasses state-of-the-art methods in detection accuracy. The source code is available at: <span><span>https://github.com/15272874521/HFGL-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105230"},"PeriodicalIF":2.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839075","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}

引用次数: 0

A survey on Deep Image Prior for image denoising

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-09 DOI: 10.1016/j.dsp.2025.105235

Cheng Zhang, Kin Sam Yen

{"title":"A survey on Deep Image Prior for image denoising","authors":"Cheng Zhang, Kin Sam Yen","doi":"10.1016/j.dsp.2025.105235","DOIUrl":"10.1016/j.dsp.2025.105235","url":null,"abstract":"<div><div>Deep Image Prior (DIP) has gained attention as a promising approach that bridges traditional hand-crafted priors and deep learning-based models. By utilizing a convolutional neural network (CNN) structure with \"zero sample\" training, DIP effectively learns the priors of degraded images, primarily for image reconstruction. Despite its potential, there is a lack of comprehensive reviews summarizing the various DIP-based image denoising methods. This paper aims to fill this gap by providing an overview of DIP-based image denoising approaches by reviewing recent papers on the topic. We classify these methods into four groups based on their enhancement strategies: theoretical investigations, network structure, network input, and loss function. The review evaluates the strengths and weaknesses of DIP-based methods, compares state-of-the-art variants, and analyzes the impact of various improvements on denoising performance. Additionally, we identify the challenges in applying DIP to image denoising and suggest directions for future research. This review provides valuable insights into the potential of DIP in image processing, especially for those new to unsupervised deep learning models.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105235"},"PeriodicalIF":2.9,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826328","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}

引用次数: 0

Multi-dimensional graph linear canonical transform and its application

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-09 DOI: 10.1016/j.dsp.2025.105222

Jian-Yi Chen , Bing-Zhao Li

引用次数: 0

Multi-scale compression artifact attention-driven compressed video quality enhancement

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-07 DOI: 10.1016/j.dsp.2025.105218

Chengdong Lan , Wei Lin , Haolin Liang , Yuanxun Kang

{"title":"Multi-scale compression artifact attention-driven compressed video quality enhancement","authors":"Chengdong Lan , Wei Lin , Haolin Liang , Yuanxun Kang","doi":"10.1016/j.dsp.2025.105218","DOIUrl":"10.1016/j.dsp.2025.105218","url":null,"abstract":"<div><div>Compressed video quality enhancement is crucial for mitigating artifacts introduced by video coding. Video compression often results in unevenly distributed artifacts across different regions of video frames, leading to significant quality variations. Existing algorithms treat all regions uniformly, ignoring these localized differences, limiting their ability to extract high-quality information from reference frames and accurately reconstruct residuals. Additionally, larger temporal gaps between reference and target frames can cause alignment errors, which propagate during fusion and degrade performance. To address these challenges, we propose a Multi-scale Compression Artifact Attention (MSCAA) module that captures artifact distribution, guiding the model to focus on distorted regions. We also introduce a Progressive Fusion Stage that sequentially fuses reference frames based on temporal proximity, reducing error propagation and enhancing temporal coherence. The experimental results show that the proposed method improves average ΔPSNR by 5.15% and ΔSSIM by 3.35% compared to the state-of-the-art method, demonstrating its superior performance in quality enhancement.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105218"},"PeriodicalIF":2.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143815579","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}

引用次数: 0

Attention learning with counterfactual intervention based on feature fusion for fine-grained feature learning

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-07 DOI: 10.1016/j.dsp.2025.105215

Ning Yu , Long Chen , Xiaoyin Yi , Jiacheng Huang

{"title":"Attention learning with counterfactual intervention based on feature fusion for fine-grained feature learning","authors":"Ning Yu , Long Chen , Xiaoyin Yi , Jiacheng Huang","doi":"10.1016/j.dsp.2025.105215","DOIUrl":"10.1016/j.dsp.2025.105215","url":null,"abstract":"<div><div>Deep learning models can learn features from a large amount of data and usually localize the overall region of the target object accurately in visual recognition tasks. However, in fine-grained scenarios with inter-class similarities, such as brand recognition in vehicles and subspecies recognition in organisms, there is a need to capture crucial distinct features and provide reliable explanations when tracking decision behavior. Therefore, this paper builds on the idea of counterfactual intervention in causal reasoning and proposes a counterfactual intervention of attention learning to learn feature information that plays an important role in fine-grained recognition tasks. First, we use the iterative feature fusion attention module that learns different levels of features and fuses them to capture the crucial features of the target object and suppress attention to the unimportant features. Second, we perform the counterfactual intervention on the feature fusion-based attention map. The changes produced by the intervening variables serve as monitoring signals for attentional learning to enhance the feature learning that contributes positively for the predicted result. Besides, we use the contrast learning function as a constraint to avoid focusing solely on salient features, thus enabling the network model to learn richer differential features. Finally, we use GradCAM visualization to explain the process of decision-making. The experimental results show that the method in this paper learned important distinguishable features of the target object, weakens the attention to non-critical regions, and offers reliable traceability analysis in tracing back decision-making behaviors.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105215"},"PeriodicalIF":2.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792217","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}

引用次数: 0

Advances in meta-learning and zero-shot learning for multi-label classification: A review

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-07 DOI: 10.1016/j.dsp.2025.105220

Luis-Carlos Quiñonez-Baca , Graciela Ramirez-Alonso , Abimael Guzman-Pando , Javier Camarillo-Cisneros , David R. Lopez-Flores

{"title":"Advances in meta-learning and zero-shot learning for multi-label classification: A review","authors":"Luis-Carlos Quiñonez-Baca , Graciela Ramirez-Alonso , Abimael Guzman-Pando , Javier Camarillo-Cisneros , David R. Lopez-Flores","doi":"10.1016/j.dsp.2025.105220","DOIUrl":"10.1016/j.dsp.2025.105220","url":null,"abstract":"<div><div>Effectively dealing with multi-label classification is a significant challenge. Traditional methods often struggle with issues such as label dependencies, data imbalance, and a limited number of annotated datasets. However, meta-learning and zero-shot learning models offer promising solutions by leveraging previous tasks to enable rapid generalization with minimal data. In this paper, we provide a comprehensive review of meta-learning and zero-shot strategies for multi-label classification in various domains, including audio, text, image, and sensor data, focusing on research published between 2019 and 2025. It presents an overview of commonly used datasets and a detailed description of models designed to capture the relationships inherent in multi-label scenarios. In addition, we propose a novel categorization framework based on neural architecture enhancements, algorithm adaptation, and problem transformation to highlight the main contributions of the reviewed literature. The aim of this review is to provide valuable insights into the current state of meta-learning and zero-shot approaches for multi-label classification, offering guidance for future research and development in addressing the complexities of real-world multi-label tasks.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105220"},"PeriodicalIF":2.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792218","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}

引用次数: 0

Design and analysis of grouping five-dimensional index modulation for high data rate DCSK communication system

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-07 DOI: 10.1016/j.dsp.2025.105211

Fadhil S. Hasan

{"title":"Design and analysis of grouping five-dimensional index modulation for high data rate DCSK communication system","authors":"Fadhil S. Hasan","doi":"10.1016/j.dsp.2025.105211","DOIUrl":"10.1016/j.dsp.2025.105211","url":null,"abstract":"<div><div>In this paper, a new index modulation system termed grouping five-dimensional index modulation differential chaos shift keying (G5DIM-DCSK) is proposed, which is intended to provide ultra-high data rate transmission based on grouping technique. This system uses five different types of index sources: subcarrier, time slot, permutation chaos, Walsh code, and permutation code. There is an equal distribution of mapping and modulating bits among the G groups formed by the input information bits. In all time slots and active subcarriers, the modulating bits are sent via either the chaotic reference sequence or the permutation chaotic reference, which is chosen by the permutation chaotic index bits. The Kronecker product of a chaotic signal and the first row of the Walsh coding matrix yield the chaotic reference sequence. In the unselected time slots and inactive subcarriers, the modulating bits are carried by a sequence created by the Kronecker product between the chaotic signal and the selected row of the Walsh code matrix. This operation is completed by permuting the selected Wlash codes using the permutation code index bits. Our examination looks at the system's information rate, spectral efficiency, and complexity, comparing them to similar systems. Furthermore, the analytical BER for the G5DIM-DCSK system under multipath Rayleigh fading channels and additive white Gaussian noise (AWGN) is derived. Simulation results not only support the performance analysis, but also show that the proposed system outperforms similar systems under equivalent conditions.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105211"},"PeriodicalIF":2.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792219","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}

引用次数: 0

Single image deraining using asymmetric feature pyramid context-aware network

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-04-07 DOI: 10.1016/j.dsp.2025.105216

Shan Gai, Minglei Yin

{"title":"Single image deraining using asymmetric feature pyramid context-aware network","authors":"Shan Gai, Minglei Yin","doi":"10.1016/j.dsp.2025.105216","DOIUrl":"10.1016/j.dsp.2025.105216","url":null,"abstract":"<div><div>Existing image deraining algorithms have challenges of accurately identifying the size and density of rain streaks, which can lead to incomplete removal and difficulties in restoring high resolution images. To address these challenges, we propose a context-aware network based on an asymmetric feature pyramid (CA-AFPN) for effective rain streak removal. The CA-AFPN is composed of feature extraction module, image restoration module, and a multi-scale feature fusion module. In the feature extraction module, the key features are extracted using a channel and self-attention (CS-Attention) module, which can perform downsampling on the image to capture color, semantic, and spatial information from various feature layers. The image restoration module employs the context-aware deep upsampling (CADU) technique to globally and dynamically restore the original features. Additionally, horizontal connections between the two modules integrate shallow physical positioning and deep semantic information, expanding the network receptive field and spatial context. Finally, the multi-scale feature fusion module (MFF) utilizes a residual network and dilated convolution layers to merge feature information across different scales for reconstructing the rain-free image. Extensive experimental results demonstrate that the proposed method is effective not only on synthetic datasets but also achieves superior performance on real-world data.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"163 ","pages":"Article 105216"},"PeriodicalIF":2.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792216","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}

引用次数: 0