Digital Signal Processing最新文献_第8页

Improved Threshold-free Automatic Dependent Surveillance-Broadcast preamble detection algorithm based on deep learning framework 基于深度学习框架的改进无阈值自动相关监视-广播序言检测算法

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-12 DOI: 10.1016/j.dsp.2025.105307

Shulong Zhuo, Jinmei Shi, Hao Bai, Xiaojian Zhou, Jicheng Kan, Jiajing Cai

{"title":"Improved Threshold-free Automatic Dependent Surveillance-Broadcast preamble detection algorithm based on deep learning framework","authors":"Shulong Zhuo, Jinmei Shi, Hao Bai, Xiaojian Zhou, Jicheng Kan, Jiajing Cai","doi":"10.1016/j.dsp.2025.105307","DOIUrl":"10.1016/j.dsp.2025.105307","url":null,"abstract":"<div><div>In the study of Automatic Dependent Surveillance-Broadcast (ADS-B) signal decoding in S-mode, accurate detection of the signal preamble is a critical prerequisite for successful decoding. To address the challenges of low detection accuracy and slow processing speed in low Signal-to-Noise Ratio (SNR) environments, we propose an intelligent ADS-B signal preamble detection algorithm. First, an improved You Only Look Once version 8 (YOLOv8) object detection model is utilized to precisely capture the ADS-B signal Preamble in the frequency domain. Next, a coordinate transformation method is employed to obtain the temporal position of the preamble pulses within the time domain signal. Finally, an enhanced threshold-free cross-correlation preamble detection algorithm is applied to achieve precise preamble detection in the time domain. Experimental results demonstrate that, in both simulated datasets and real-world measurement environments, the proposed algorithm effectively mitigates the issue of preamble detection accuracy degradation caused by threshold fluctuations under low-SNR conditions. Specifically, the proposed algorithm achieves detection accuracies of 58.7% and 99.8% at SNR = -3 dB and 15 dB, respectively, surpassing traditional detection algorithms in accuracy.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105307"},"PeriodicalIF":2.9,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948875","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

Multiscale entropy rates: A study on different stochastic processes 多尺度熵率：不同随机过程的研究

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-09 DOI: 10.1016/j.dsp.2025.105303

Eric Grivel , Pierrick Legrand , Bastien Berthelot

{"title":"Multiscale entropy rates: A study on different stochastic processes","authors":"Eric Grivel , Pierrick Legrand , Bastien Berthelot","doi":"10.1016/j.dsp.2025.105303","DOIUrl":"10.1016/j.dsp.2025.105303","url":null,"abstract":"<div><div>In this paper, we propose to analyze the behavior of the entropy rate (ER) when applied to a signal and its coarse-grained versions. The “multiscale entropy rate” (MSER) is deduced by storing in a vector the resulting ERs. Our contribution consists in studying the MSER calculated on different stochastic processes. When dealing with Gaussian complex or real moving average (MA) processes or autoregressive (AR) processes, which can be seen as the filtering of a white Gaussian driving process, the MSER depends on the variances of the driving processes of the corresponding minimum-phase ARMA process at each scale. More particularly, we derive the analytical expression of the MSER for <span><math><msup><mrow><mn>1</mn></mrow><mrow><mi>s</mi><mi>t</mi></mrow></msup></math></span>-order MA or AR processes using different approaches. This study allows us to better understand what each scale brings in and to describe the behavior of the MSER for these types of processes. We also show that there is a mapping between the stochastic-process parameters and the ER computed at different scales. Finally, we show that the multiscale procedure is not relevant for a sum of complex exponentials disturbed by an additive white Gaussian noise.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105303"},"PeriodicalIF":2.9,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942564","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

ViWiTraj: Variational motion tracking in multi-link device-free Wi-Fi sensing under uncertainty 不确定条件下多链路无设备Wi-Fi传感中的变分运动跟踪

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-09 DOI: 10.1016/j.dsp.2025.105286

Wenbo Ding, Yang Li, Yunrong Zhu, Yibo Zhang, Dongsheng Wang, Bin Zhao

{"title":"ViWiTraj: Variational motion tracking in multi-link device-free Wi-Fi sensing under uncertainty","authors":"Wenbo Ding, Yang Li, Yunrong Zhu, Yibo Zhang, Dongsheng Wang, Bin Zhao","doi":"10.1016/j.dsp.2025.105286","DOIUrl":"10.1016/j.dsp.2025.105286","url":null,"abstract":"<div><div>The device-free Wi-Fi sensing has numerous benefits in practical settings, as it obviates the requirement for any dedicated device for sensing and can accomplish sensing on current low-cost Wi-Fi devices. Various methods have been proposed for motion tracking using Angle of Arrival (AoA), Time of Flight (ToF), and Doppler Frequency Shift (DFS) from Wi-Fi signals. However, a statistical model for motion tracking with DFS in multi-link scenarios has yet to be established, and uncertainties like the target's initial position can cause severe performance degradation. To address these challenges, we present an algorithm called ViWiTraj for DFS-based motion tracking in Multi-Link Wi-Fi environments. ViWiTraj incorporates a novel Doppler Frequency Shift (DFS) measurement model in multi-link scenarios that explicitly accounts for uncertainties in receiver positions and initial target location, enabling joint estimation of motion-tracking states and model parameters through structural variational inference. This approach improves Wi-Fi motion tracking usability and precision by reducing sensitivity to parameter uncertainties, improving tracking accuracy in multi-link environments, and decreasing reliance on prior knowledge of the environment and target. We have tested our algorithm in simulated and real-world scenarios with different uncertainty levels, demonstrating superior performance in Multi-Link motion tracking compared to existing methods. ViWiTraj achieves improved accuracy while imposing fewer requirements on prior knowledge of the environment and target, making it more adaptable to diverse real-world applications.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105286"},"PeriodicalIF":2.9,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115476","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

YOLO-SAD for fire detection and localization in real-world images YOLO-SAD用于真实世界图像的火灾探测和定位

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-09 DOI: 10.1016/j.dsp.2025.105320

Renlei Yang , Jun Jiang , Fanshuai Liu , Lingyun Yan

{"title":"YOLO-SAD for fire detection and localization in real-world images","authors":"Renlei Yang , Jun Jiang , Fanshuai Liu , Lingyun Yan","doi":"10.1016/j.dsp.2025.105320","DOIUrl":"10.1016/j.dsp.2025.105320","url":null,"abstract":"<div><div>Fire detection aims to effectively monitor fires and provide timely warnings. Accurate identification and precise localization are critical in this task. However, there are several challenges, including feature diversity, background interference, foreground clutter, and the detection of small fires, which hinder overall detection performance. To address these challenges, we propose a fire detection method called YOLO-SAD, which integrates a Swin transformer, an attention and convolution mix (ACmix) module, and a decoupled head based on the YOLO (You Only Look Once) architecture. The Swin transformer is adept at extracting more discriminative features, and thus can mitigate issues related to feature diversity. Additionally, the ACmix module partitions weights for the features, thereby reducing background interference. Finally, the decoupled head incorporates a modified loss function designed to enhance the detection of small fires. Extensive experiments have been conducted on three public benchmark datasets, and the results demonstrate the YOLO-SAD is superior to the state-of-the-art methods in terms of both qualitative and quantitative metrics. The code for this paper is available at: <span><span>https://github.com/yang123456-mao/YOLO-SAD-an-improved-YOLO-based-method-for-fire-detection-and-localization</span><svg><path></path></svg></span></div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105320"},"PeriodicalIF":2.9,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942559","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

AC-MVSNet: An efficient multi-view 3D reconstruction network integrating novel multi-scale feature extraction and edge enhancement AC-MVSNet：一种集成了新型多尺度特征提取和边缘增强的高效多视图三维重建网络

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-09 DOI: 10.1016/j.dsp.2025.105323

Zhenwu Dong , Chunyuan Wang , Yan Wang , Peng Cui

{"title":"AC-MVSNet: An efficient multi-view 3D reconstruction network integrating novel multi-scale feature extraction and edge enhancement","authors":"Zhenwu Dong , Chunyuan Wang , Yan Wang , Peng Cui","doi":"10.1016/j.dsp.2025.105323","DOIUrl":"10.1016/j.dsp.2025.105323","url":null,"abstract":"<div><div>Multi-view stereo (MVS) reconstruction is a long-term research hotspot in computer vision. This paper presents a novel method, AC-MVSNet, aimed at tackling the existing challenges in multi-view stereo reconstruction, including the arduous task of processing high-resolution images, the substantial GPU memory consumption, and the problem of incomplete reconstruction. It features a new multi-scale feature extractor named CADS-Msfe and a novel depth-map optimization network with boundary enhancement, E-Refinement. Rich and precise feature information is extracted by CADS-Msfe. Subsequently, These features are inputted into the PatchMatch network to generate multi-scale depth maps. Finally, by taking advantage of the boundary enhancement effect of the E-Refinement network, the final depth maps with precise boundary information are obtained. We evaluated our proposed method on the Technical University of Denmark (DTU) and the Tanks and Temples Benchmark datasets. The results on the DTU indicate that the method in this paper enhances PatchMatchNet's completeness by 5.1 %, accuracy by 14.1 %, and overall quality by 10.5 %. It also outperforms other state-of-the-art (SOTA) methods in terms of completeness and overall quality.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105323"},"PeriodicalIF":2.9,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937220","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 symmetrical parallel two-stream adaptive segmentation network for remote sensing images 一种对称并行双流自适应遥感图像分割网络

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-08 DOI: 10.1016/j.dsp.2025.105319

Bicao Li , Lijun Wang , Bei Wang , Zhuhong Shao , Jie Huang , Guangshuai Gao , Mengxing Song , Wei Li , Danting Niu

{"title":"A symmetrical parallel two-stream adaptive segmentation network for remote sensing images","authors":"Bicao Li , Lijun Wang , Bei Wang , Zhuhong Shao , Jie Huang , Guangshuai Gao , Mengxing Song , Wei Li , Danting Niu","doi":"10.1016/j.dsp.2025.105319","DOIUrl":"10.1016/j.dsp.2025.105319","url":null,"abstract":"<div><div>Segmentation of remote sensing images plays an important role in various civil applications. Although some achievements of artificial intelligence have been made in the past, the current challenge of remote sensing image segmentation is mainly the inadequate capture of global and local features, which leads to poor target feature extraction. This paper proposes a parallel two-stream adaptive remote sensing image segmentation network with symmetric semantic reasoning and context awareness, which enhances the feature extraction ability and further improves the segmentation accuracy. The proposed network consists of a main stream and a subordinate flow. Specifically, main stream is mainly used to extract local features from remote sensing images. The subordinate flow obtains the global feature information of the image. In the two-stream network coding stage, a hierarchical aggregation module is proposed to achieve the purpose of mining the global and local features of remote sensing images. In addition, to further improve the discriminate power of multi-scale features, an adaptive semantic reasoning module is proposed to extract multi-scale features. Experiments are carried out on two commonly used data sets, and the experimental results prove the effectiveness of the proposed network.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105319"},"PeriodicalIF":2.9,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937223","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

IDSGA: A high-performance search model for differential-neural cryptanalysis 差分神经密码分析的高性能搜索模型

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-08 DOI: 10.1016/j.dsp.2025.105306

Zhiwen Hu , Lang Li , Siqi Zhu , Yemao Hu

{"title":"IDSGA: A high-performance search model for differential-neural cryptanalysis","authors":"Zhiwen Hu , Lang Li , Siqi Zhu , Yemao Hu","doi":"10.1016/j.dsp.2025.105306","DOIUrl":"10.1016/j.dsp.2025.105306","url":null,"abstract":"<div><div>Differential-neural cryptanalysis poses critical security threats to internet of things-embedded lightweight block ciphers, outperforming traditional methods but requiring efficient input difference identification. Current solutions are constrained by the opacity of neural networks and the prohibitive computational demands during search processes. Therefore, an input difference search model IDSGA is proposed in this paper. IDSGA model innovatively combines cryptographic theory with deep learning through two key processes. First, feature purification enhances differential characteristics by eliminating redundant patterns while preserving attack-relevant statistical properties through traditional differential probability integration. Second, multi-dimensional distribution mapping enables quantitative dataset evaluation by transforming purified data into interpretable statistical metrics. It enables our model to break through the reliance on neural network evaluation. Moreover, IDSGA model constructs a more optimal search path by integrating a genetic algorithm to deal with the problem of differential search of full inputs with high computational complexity. A quantum variant theoretically extends these capabilities. The experimental results show that the execution time of the IDSGA model is 93% less than that of Gohr. For the CARX cipher, the input differences found by IDSGA are more optimal. This work establishes a new paradigm for differential-neural cryptanalysis by decoupling dataset evaluation from neural network training dependencies.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"164 ","pages":"Article 105306"},"PeriodicalIF":2.9,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929260","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

CycleGAN-based unsupervised image smoothing framework with wavelet downsampling and multi-scale spatially-adaptive attention 基于小波下采样和多尺度空间自适应关注的cyclegan无监督图像平滑框架

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-08 DOI: 10.1016/j.dsp.2025.105300

Jiafu Zeng , Huiyu Li , Yepeng Liu , Fan Zhang

{"title":"CycleGAN-based unsupervised image smoothing framework with wavelet downsampling and multi-scale spatially-adaptive attention","authors":"Jiafu Zeng , Huiyu Li , Yepeng Liu , Fan Zhang","doi":"10.1016/j.dsp.2025.105300","DOIUrl":"10.1016/j.dsp.2025.105300","url":null,"abstract":"<div><div>Edge-preserving smoothing is an important image processing operation designed to enhance low-frequency structural components while suppressing high-frequency textures and noise. However, existing methods entail high costs for parameter tuning and dataset requirements, and lack generalization across different images. In response, this paper proposes an unsupervised image smoothing framework based on a cycle-consistent adversarial network (CycleGAN). It learns smoothing relationships from unpaired, unlabeled data and uses adversarial training to generate high-quality smoothing results. To better leverage image information, this paper designs a wavelet-based downsampling module to extract key features from subbands in different frequency bands of the image. Furthermore, a multi-scale spatially-adaptive attention module is proposed, which dynamically adjusts the importance of spatial features and facilitates comprehensive information interaction by fusing image features at different scales. Additionally, a composite loss function is employed to guide network optimization and improve the quality of generated results. Qualitative and quantitative experimental results demonstrate that, compared to state-of-the-art smoothing methods, the proposed approach achieves both effective smoothing performance and computational efficiency.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105300"},"PeriodicalIF":2.9,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942565","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

Noise Blind Deep Residual Wiener Deconvolution network for image deblurring 噪声盲深度残差维纳反卷积网络图像去模糊

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-08 DOI: 10.1016/j.dsp.2025.105304

Shengjiang Kong, Weiwei Wang, Xiangchu Feng, Xixi Jia

引用次数: 0

DRA-Net: Improved U-net white blood cell segmentation network based on residual dual attention 基于残差双注意的改进U-net白细胞分割网络

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-05-08 DOI: 10.1016/j.dsp.2025.105301

Jinfeng Wang , Xiangsuo Fan , Jie Meng , Borui Sun , Huajin Chen

{"title":"DRA-Net: Improved U-net white blood cell segmentation network based on residual dual attention","authors":"Jinfeng Wang , Xiangsuo Fan , Jie Meng , Borui Sun , Huajin Chen","doi":"10.1016/j.dsp.2025.105301","DOIUrl":"10.1016/j.dsp.2025.105301","url":null,"abstract":"<div><div>This article aims to improve the segmentation accuracy of white blood cells and proposes a deep learning network called DRA-Net based on U-Net. DRA-Net is a U-shaped neural network based on a residual dual-channel mechanism, utilizing an improved encoder-decoder structure to enhance the interdependence between channels and spatial positions. In the encoding module, the Efficient Channel Attention (ECA) module is connected to the lower layers of the convolutional blocks and residual blocks to effectively extract feature information. In the decoding module, the Triple Vision module is connected to the upper layers of the convolutional blocks, eliminating the correspondence between channels and weights, thereby better extracting and fusing multi-scale features, which enhances the performance and efficiency of the network. This article uses publicly available Kaggle dataset from the Core Laboratory of Hospital Clinic in Barcelona and a self-built DML-LZWH (Liuzhou Workers' Hospital Medical Laboratory) dataset to conduct experiments on medical image segmentation tasks. In the self-built DML-LZWH dataset, compared to the U-Net network model, the IoU improved by 3% and the Dice improved by 2.3%. In the Kaggle public dataset from the Core Laboratory of Hospital Clinic in Barcelona, the IoU improved by 4.3% and the Dice improved by 3.1%. These results validate the effectiveness of the DRA-Net algorithm, and the experimental results indicate that the performance of the DRA-Net algorithm is significantly better than existing segmentation algorithms. Furthermore, when compared to the state-of-the-art (DA-TransUNet) model, DRA-Net also shows a significant performance improvement. The experimental methods and related data in this article will be open-sourced at: <span><span>https://github.com/W-JFenf/DRA-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"165 ","pages":"Article 105301"},"PeriodicalIF":2.9,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948876","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