IEEE Signal Processing Letters最新文献_第3页

Instantaneous Frequency Estimation via Spectrogram Projection and P-Spline Approximation 瞬时频率估计通过谱图投影和p样条逼近

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-16 DOI: 10.1109/LSP.2025.3610345

Vittoria Bruni;Rosanna Campagna;Michela Tartaglione;Domenico Vitulano

{"title":"Instantaneous Frequency Estimation via Spectrogram Projection and P-Spline Approximation","authors":"Vittoria Bruni;Rosanna Campagna;Michela Tartaglione;Domenico Vitulano","doi":"10.1109/LSP.2025.3610345","DOIUrl":"https://doi.org/10.1109/LSP.2025.3610345","url":null,"abstract":"Frequency Modulated (FM) signals are usually characterized by two or more components having different waveforms and time-dependent frequencies. The estimation of the instantaneous frequency (IF) represents a very challenging topic when there are two or more interfering components. In this case, available approaches, like the reassignment-based ones, fail in correspondence to the interference region, where IFs of each individual mode are not far enough to be considered separable. In this paper, a novel approach for IF estimation based on spectrogram analysis is proposed. Firstly, it is proved that the projection of signal spectrogram on the temporal axis is itself an amplitude and frequency modulated signal. Its IF depends on the instantaneous frequencies of the individual signal components and the functional dependence can be explicitely given. Then, under proper assumptions, a regression method for the individual IFs estimation is provided using a few selected ’good’ points lying in the interference region. The regression method benefits from a penalized-spline (P-spline) model where a second-order discrete penalty term is also used. Experimental results show that the proposed model is very effective to estimate the individual IFs of multicomponent FM signals in the interference region, making it a suitable method for correcting reassignment estimation where the separability condition is not satisfied.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3725-3729"},"PeriodicalIF":3.9,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210042","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}

引用次数: 0

Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning 超越增强：在自监督表示学习中利用实例间关系

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-16 DOI: 10.1109/LSP.2025.3610549

Ali Javidani;Babak Nadjar Araabi;Mohammad Amin Sadeghi

{"title":"Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning","authors":"Ali Javidani;Babak Nadjar Araabi;Mohammad Amin Sadeghi","doi":"10.1109/LSP.2025.3610549","DOIUrl":"https://doi.org/10.1109/LSP.2025.3610549","url":null,"abstract":"This letter introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook important inter-instance relationships. While our method retains the intra-instance property, it further captures inter-instance relationships by constructing <inline-formula><tex-math>$k$</tex-math></inline-formula> -nearest neighbor (KNN) graphs for both teacher and student streams during pretraining. In these graphs, nodes represent samples along with their latent representations. Edges encode the similarity between instances. Following pretraining, a representation refinement phase is performed. In this phase, Graph Neural Networks (GNNs) propagate messages not only among immediate neighbors but also across multiple hops, thereby enabling broader contextual integration. Experimental results on CIFAR-10, ImageNet-100, and ImageNet-1K demonstrate accuracy improvements of 7.3%, 3.2%, and 1.0%, respectively, over state-of-the-art methods. These results highlight the effectiveness of the proposed graph-based mechanism.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3730-3734"},"PeriodicalIF":3.9,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210099","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}

引用次数: 0

Infrared-Visible Object Detection via Distillation-Fermentation Dual Processing 蒸馏-发酵双重处理红外-可见光目标检测

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-15 DOI: 10.1109/LSP.2025.3610025

Tao Wang;Hui Wang;Yunli Zhu;Xinang Fan;Guoliang Luo

引用次数: 0

Research on Distributed Synthetic Aperture Passive Positioning and Optimal Geometric Configuration 分布式合成孔径无源定位及最优几何构型研究

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-15 DOI: 10.1109/LSP.2025.3610355

Junhua Yang;Hao Huan;Ziming Xu;Ran Tao

{"title":"Research on Distributed Synthetic Aperture Passive Positioning and Optimal Geometric Configuration","authors":"Junhua Yang;Hao Huan;Ziming Xu;Ran Tao","doi":"10.1109/LSP.2025.3610355","DOIUrl":"https://doi.org/10.1109/LSP.2025.3610355","url":null,"abstract":"Synthetic aperture passive positioning (SAPP) has gradually become a hot spot in radiation source location research. However, there are relatively few studies on three-dimensional synthetic aperture passive positioning methods. Moreover, synthetic aperture passive positioning is significantly affected by residual frequency offsets (RFO) resulting from noncooperative operation between transceivers. To address the challenges, a distributed synthetic aperture passive positioning method is proposed. Considering frequency synchronization among platforms, this method leverages the SAPP algorithm to obtain high-precision slant angles. Subsequently, it formulates positioning equations related to the 3D target position and RFO. The distributed geometric configuration is studied under certain constraints, and the analytical solutions for the optimal configuration are obtained. Space-borne simulations illustrate that the positioning accuracy of the proposed method is an order of magnitude higher compared to that of the FOA, FDOA, and DOA methods. Additionally, airborne experiments indicate that in the presence of RFO, the proposed method improves the positioning accuracy by two orders of magnitude and exhibits strong convergence properties.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3685-3689"},"PeriodicalIF":3.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210044","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}

引用次数: 0

Recognition of LPI Radar Waveforms via RCMNet in Low SNR Scenarios 低信噪比下RCMNet对LPI雷达波形的识别

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-12 DOI: 10.1109/LSP.2025.3609636

An Yan;Lan Lan;Xiaorui Li;Shengqi Zhu;Ximin Li;Guisheng Liao

引用次数: 0

Deep Preprocessing Method for Speech Restoration in Parametric Array Loudspeakers via Time-Frequency Domain Modeling 基于时频域建模的参数阵列扬声器语音恢复深度预处理方法

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-11 DOI: 10.1109/LSP.2025.3609247

Wenyao Ma;Yunxi Zhu;Jun Yang

{"title":"Deep Preprocessing Method for Speech Restoration in Parametric Array Loudspeakers via Time-Frequency Domain Modeling","authors":"Wenyao Ma;Yunxi Zhu;Jun Yang","doi":"10.1109/LSP.2025.3609247","DOIUrl":"https://doi.org/10.1109/LSP.2025.3609247","url":null,"abstract":"The parametric array loudspeaker inherently introduces baseband distortions in directional sound applications due to the nonlinear process in air. Recently, DNNs have been used to model this forward process and to generate preprocessed signals for distortion-free speech restoration. However, when trained on real-world audio, the preprocessing network can exploit weaknesses in the forward model, producing adversarial outputs. To address it, we propose a reorganization strategy for the two-stage framework, comprising a causal TF-GridNet for preprocessed signal generation and a modified time-frequency (T-F) domain differential Volterra Filter (DiffVF) as the forward model. The causal TF-GridNet estimates real and imaginary components using a T-F band-split mechanism. The modified forward model integrates the second-order difference and kernel convolution operations of the original time-domain version into the T-F domain, preserving interpretability while stabilizing training. A refined <inline-formula><tex-math>$N$</tex-math></inline-formula>th-order equalization, based on the T-F domain DiffVF model, is implemented as a competitive baseline. Simulated and real-world experiments demonstrate state-of-the-art reconstruction performance of the proposed method across various objective metrics.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3720-3724"},"PeriodicalIF":3.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210043","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}

引用次数: 0

GraphFusion: Robust 3D Detection via Cross-Modal Graph and Uncertainty-Aware Bayesian Fusion GraphFusion：基于跨模态图和不确定性感知贝叶斯融合的鲁棒3D检测

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-11 DOI: 10.1109/LSP.2025.3609243

Huishan Wang;Jie Ma;Jianlei Zhang;Fangwei Chen

{"title":"GraphFusion: Robust 3D Detection via Cross-Modal Graph and Uncertainty-Aware Bayesian Fusion","authors":"Huishan Wang;Jie Ma;Jianlei Zhang;Fangwei Chen","doi":"10.1109/LSP.2025.3609243","DOIUrl":"https://doi.org/10.1109/LSP.2025.3609243","url":null,"abstract":"Multimodal 3D object detection significantly enhances perception by fusing LiDAR point clouds and RGB images. However, existing methods often fail to adaptively estimate modality confidence under challenging conditions such as heavy occlusion or sparse point clouds, leading to degraded fusion performance. In this letter, we propose GraphFusion, a multimodal framework that integrates cross-modal graph modeling with Bayesian uncertainty-aware fusion for robust 3D object detection. Specifically, a heterogeneous graph driven by geometric and semantic cues aligns 3D points with 2D pixels. A Bayesian attention mechanism then leverages predictive uncertainty to dynamically reweight modalities, prioritizing high-confidence information and enabling noise-resilient and spatially adaptive fusion. The proposed module is highly generalizable and can be seamlessly integrated into existing detectors as a plug-and-play component. Extensive experiments on KITTI and nuScenes demonstrate that GraphFusion achieves significant accuracy improvements with superior robustness and generalization, especially in complex environments.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3645-3649"},"PeriodicalIF":3.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141585","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}

引用次数: 0

Efficiently Trained Real Image Dehazing Network With Dual Discrete Priors for Enhanced Naturalness 有效训练的双离散先验真实图像去雾网络增强自然度

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-10 DOI: 10.1109/LSP.2025.3608622

Min Woo Kim;Nam Ik Cho

引用次数: 0

A NeRF 3D Based Fish Weighing Model Under Fluctuating Measuring Condition 波动测量条件下基于NeRF 3D的鱼类称重模型

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-10 DOI: 10.1109/LSP.2025.3608626

Lu Zhang;Zhongze Liu;Junjie Li;Ziqing Lu;Yuqing Liu

引用次数: 0

An Optimal Hybrid Fake-Acknowledgment Attack Strategy on State Estimation With Energy Constraint 一种带能量约束的状态估计混合伪确认攻击策略