IEEE Signal Processing Letters最新文献

筛选
英文 中文
MIMO Radar Joint Heart Rate and Respiratory Rate Estimation and Performance Bound Analysis
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3546894
Peichao Wang;Qian He;Haozheng Li
{"title":"MIMO Radar Joint Heart Rate and Respiratory Rate Estimation and Performance Bound Analysis","authors":"Peichao Wang;Qian He;Haozheng Li","doi":"10.1109/LSP.2025.3546894","DOIUrl":"https://doi.org/10.1109/LSP.2025.3546894","url":null,"abstract":"This letter investigates the non-contact heart rate (HR) and respiratory rate (RR) joint estimation employing multiple-input multiple-output (MIMO) radar with widely separated antennas. By developing a signal model for the HR and RR estimation using the MIMO radar, where the initial phases for HR and RR, as well as the reflection coefficients, are deterministic but unknown, we propose an HR-RR joint estimator. Unlike the existing methods, the theoretical performance of the HR and RR estimation is analyzed for the first time, where the corresponding Cramer-Rao Bounds (CRBs) are derived. These bounds provide the first theoretical performance benchmark for this type of radar-based estimation and guide the system parameters design to enhance the HR and RR estimation performance, thereby avoiding the complex numerical computations involved in the joint estimator. It is shown that the proposed method outperforms traditional methods and the CRB can provide the guidance for system parameter optimization.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1266-1270"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716511","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
GLNet: Global-Local Fusion Network for Strip Steel Surface Defects Detection
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3546888
Xuan Wang;Liuxin Bao;Xiaofei Zhou;Lei Xia;Xiaobin Xu
{"title":"GLNet: Global-Local Fusion Network for Strip Steel Surface Defects Detection","authors":"Xuan Wang;Liuxin Bao;Xiaofei Zhou;Lei Xia;Xiaobin Xu","doi":"10.1109/LSP.2025.3546888","DOIUrl":"https://doi.org/10.1109/LSP.2025.3546888","url":null,"abstract":"Surface defect detection in strip steel is a critical task in industrial quality control. However, existing methods struggle with capturing both local details and global context effectively. In this paper, we propose the Global-Local Fusion Network (GLNet) for strip steel surface defect detection, which combines the advantages of VMamba's global feature extraction and CNN's local feature modeling. GLNet employs an encoder-decoder structure, where the encoder consists of two parallel branches: one based on VMamba for capturing global features and the other using ResNet50 for extracting local features. In the decoder, a Global-Local Fusion (GLF) module integrates these features using the Cross Prototype Objective Enhancement (CPOE) and Selective Spatial and Channel Attention (SSCA) modules. The CPOE module facilitates the interaction and fusion between global and local features, while the SSCA module digs the multi-scale information from the global feature through dynamic attention to guide the feature aggregation. Extensive experiments on the ESDIs dataset, demonstrate that GLNet achieves state-of-the-art performance in defect detection, surpassing 13 existing methods in both quantitative and qualitative metrics.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1256-1260"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716529","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
Depth-Aided Color Image Inpainting in Quaternion Domain
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3547662
Shunki Tatsumi;Ryo Hayakawa;Youji Iiguni
{"title":"Depth-Aided Color Image Inpainting in Quaternion Domain","authors":"Shunki Tatsumi;Ryo Hayakawa;Youji Iiguni","doi":"10.1109/LSP.2025.3547662","DOIUrl":"https://doi.org/10.1109/LSP.2025.3547662","url":null,"abstract":"In this paper, we propose a depth-aided color image inpainting method in the quaternion domain, called depth-aided low-rank quaternion matrix completion (D-LRQMC). In conventional quaternion-based inpainting techniques, the color image is expressed as a quaternion matrix by using the three imaginary parts as the color channels, whereas the real part is set to zero and has no information. Our approach incorporates depth information as the real part of the quaternion representations, leveraging the correlation between color and depth to improve the result of inpainting. In the proposed method, we first restore the observed image with the conventional LRQMC and estimate the depth of the restored result. We then incorporate the estimated depth into the real part of the observed image and perform LRQMC again. Simulation results demonstrate that the proposed D-LRQMC can improve restoration accuracy and visual quality for various images compared to the conventional LRQMC. These results suggest the effectiveness of the depth information for color image processing in quaternion domain.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1171-1175"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667601","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
Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3547269
Jinhong He;Shivakumara Palaiahnakote;Aoxiang Ning;Minglong Xue
{"title":"Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion","authors":"Jinhong He;Shivakumara Palaiahnakote;Aoxiang Ning;Minglong Xue","doi":"10.1109/LSP.2025.3547269","DOIUrl":"https://doi.org/10.1109/LSP.2025.3547269","url":null,"abstract":"Due to the singularity of real-world paired datasets and the complexity of low-light environments, this leads to supervised methods lacking a degree of scene generalisation. Meanwhile, limited by poor lighting and content guidance, existing zero-shot methods cannot handle unknown severe degradation well. To address this problem, we will propose a new zero-shot low-light enhancement method to compensate for the lack of light and structural information in the diffusion sampling process by effectively combining the wavelet and Fourier frequency domains to construct rich a priori information. The key to the inspiration comes from the similarity between the wavelet and Fourier frequency domains: both light and structure information are closely related to specific frequency domain regions, respectively. Therefore, by transferring the diffusion process to the wavelet low-frequency domain and combining the wavelet and Fourier frequency domains by continuously decomposing them in the inverse process, the constructed rich illumination prior is utilised to guide the image generation enhancement process. Sufficient experiments show that the framework is robust and effective in various scenarios.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1091-1095"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143629597","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
Binary Neural Networks With Feature Information Retention for Efficient Image Classification
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3546895
Rui Ding;Yuxiao Wang;Haijun Liu;Xichuan Zhou
{"title":"Binary Neural Networks With Feature Information Retention for Efficient Image Classification","authors":"Rui Ding;Yuxiao Wang;Haijun Liu;Xichuan Zhou","doi":"10.1109/LSP.2025.3546895","DOIUrl":"https://doi.org/10.1109/LSP.2025.3546895","url":null,"abstract":"Although binary neural networks (BNNs) enjoy extreme compression ratios, there are significant accuracy gap compared with full-precision models. Previous works propose various strategies to reduce the information loss induced by the binarization process, improving the performance of binary neural networks to some extent. However, in this letter, we argue that few studies try to alleviate this problem from the structure perspective, resulting in inferior performance. To this end, we propose a novel Feature Information Retention Network named FIRNet, which incorporates an extra path to propagate the untouched informative feature maps. Specifically, the FIRNet splits the input feature maps into two groups, one of which is fed into the normal layers and another kept untouched for information retention. Then we utilize the concatenation, shuffle and pooling operations to process these features with 64× memory saving. Finally, with only a 1.7% complexity increase, a FIR fusion layer is proposed to aggregate the features from two branches. Experimental results demonstrate that our proposed method achieves 1.0% Top-1 accuracy improvement over the baseline model and outperforms other state-of-the-art BNNs on the ImageNet dataset.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1321-1325"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716523","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
Adaptive and Background-Aware Match for Class-Agnostic Counting
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3546891
Shenjian Gong;Jian Yang;Shanshan Zhang
{"title":"Adaptive and Background-Aware Match for Class-Agnostic Counting","authors":"Shenjian Gong;Jian Yang;Shanshan Zhang","doi":"10.1109/LSP.2025.3546891","DOIUrl":"https://doi.org/10.1109/LSP.2025.3546891","url":null,"abstract":"Class-Agnostic Counting (CAC) aims to count object instances in an image by simply specifying a few exemplar boxes of interest. The key challenge for CAC is how to tailor a desirable interaction between exemplar and query features. Previous CAC methods implement such interaction by solely leveraging standard global feature convolution. We find this interaction leads to under-match caused by intra-class diversity and over-match on background, which harms counting performance severely. In this work, we propose a novel feature interaction method called Adaptive and Background-aware Match (ABM) against high intra-class diversity and noisy background. Concretely, given exemplar and query features, we improve the original high-dimensional coupled spaces match to Adaptive Orthogonal subspaces Match (AOM), avoiding under-match caused by intra-class diversity. Moreover, Background-Specific Match (BSM) employs interaction between the learnable background prototype and query features to provide global background priors, making the match be aware of background regions. Additionally, we find the high scale variance among different query images leads to bad counting performance for extremely small scale objects. Object-Scale Unify (OSU) is proposed to take the size of the exemplars as the scale prior and resize query images so that all objects are at a uniform average scale. Extensive experiments on FSC-147 show that our method performs better. We also conduct extensive ablation studies to demonstrate the effectiveness of each component of our proposed method.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1261-1265"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716526","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
MSTDF: Motion Style Transfer Towards High Visual Fidelity Based on Dynamic Fusion
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-03-03 DOI: 10.1109/LSP.2025.3546885
Ziyun Qian;Dingkang Yang;Mingcheng Li;Zeyu Xiao;Lihua Zhang
{"title":"MSTDF: Motion Style Transfer Towards High Visual Fidelity Based on Dynamic Fusion","authors":"Ziyun Qian;Dingkang Yang;Mingcheng Li;Zeyu Xiao;Lihua Zhang","doi":"10.1109/LSP.2025.3546885","DOIUrl":"https://doi.org/10.1109/LSP.2025.3546885","url":null,"abstract":"Emotion-guided motion style transfer is a novel research direction, enabling the efficient generation of motion in various emotional styles for use in films, games, and other domains. However, existing methods primarily rely on global feature statistics for motion style transfer, neglecting local semantic structure and resulting in the degradation of motion content structure. This letter proposes a novel Motion Style Transfer based on Dynamic Fusion (MSTDF) framework, which treats content and style motion as distinct signals and employs dynamic fusion for high-fidelity motion style transfer. Additionally, to address the challenge of traditional discriminators capturing subtle motion style features, we propose the Motion Dynamic Fusion (MDF) discriminator to capture the details and fine-grained style characteristics of motion sequences, assisting the generator in producing higher-fidelity stylized motion. Finally, extensive experiments on the Xia dataset demonstrate that our method surpasses state-of-the-art methods in qualitative and quantitative comparisons.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1101-1105"},"PeriodicalIF":3.2,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143675975","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
Low-Resource Speech Recognition of Radiotelephony Communications Based on Continuous Learning of In-Domain and Out-of-Domain Knowledge
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-02-26 DOI: 10.1109/LSP.2025.3545955
Guimin Jia;Dong He;Xilong Zhou
{"title":"Low-Resource Speech Recognition of Radiotelephony Communications Based on Continuous Learning of In-Domain and Out-of-Domain Knowledge","authors":"Guimin Jia;Dong He;Xilong Zhou","doi":"10.1109/LSP.2025.3545955","DOIUrl":"https://doi.org/10.1109/LSP.2025.3545955","url":null,"abstract":"Automatic speech recognition (ASR) in air traffic control (ATC) is a low-resource task with limited data and difficult annotation. Fine-tuning self-supervised pre-trained models is a potential solution, but it is time-consuming and computationally expensive, and may degrade the model's ability to extract robust features. Therefore, we propose a continuous learning approach for end-to-end ASR to maintain performance in both new and original tasks. To address catastrophic forgetting in continuous learning for ASR, we propose a knowledge distillation-based method combined with stochastic encoder-layer fine-tuning. This approach efficiently retains knowledge from previous tasks with limited training data, reducing the need for extensive joint training. Experiments on open-source ATC datasets show that our method effectively reduces forgetting and outperforms existing techniques.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1136-1140"},"PeriodicalIF":3.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654995","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
A Burn After Reading Data Hiding Framework
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-02-25 DOI: 10.1109/LSP.2025.3545805
Jingyuan Jiang;Zichi Wang;Guanghui He;Xinpeng Zhang
{"title":"A Burn After Reading Data Hiding Framework","authors":"Jingyuan Jiang;Zichi Wang;Guanghui He;Xinpeng Zhang","doi":"10.1109/LSP.2025.3545805","DOIUrl":"https://doi.org/10.1109/LSP.2025.3545805","url":null,"abstract":"We propose a novel data hiding framework based on a multimodal generative model, named Burn After Reading Data Hiding (BarDH). Unlike previous related work in the field of data hiding, our proposed BarDH introduces a novel function: once the receiver extracts the secret data, the secret data cannot be extracted again. We have named this function as ‘Burn After Reading’. The concept of ‘Burn After Reading’ was first introduced into data hiding research. We believe that this mechanism constitutes a highly effective means of safeguarding secret data, such as in scenarios where the receiver's device has been hacked or stolen. Our proposed BarDH model enhances the multimodal generative model, Latent Diffusion Models (LDMs), better aligning it with data hiding tasks and requirements. Experimental results demonstrate that the proposed BarDH framework effectively facilitates the functionality of ‘Burn After Reading’. Simultaneously, the framework demonstrates competitiveness in both the accuracy of secret data extraction and security.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1131-1135"},"PeriodicalIF":3.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654994","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
Hardware-Decoder-Friendly High Throughput String Prediction for SCC Implemented in AVS3
IF 3.2 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-02-25 DOI: 10.1109/LSP.2025.3545284
Liping Zhao;Zhuge Yan;Zongda Wu;Jiangda Wang;Tao Lin
{"title":"Hardware-Decoder-Friendly High Throughput String Prediction for SCC Implemented in AVS3","authors":"Liping Zhao;Zhuge Yan;Zongda Wu;Jiangda Wang;Tao Lin","doi":"10.1109/LSP.2025.3545284","DOIUrl":"https://doi.org/10.1109/LSP.2025.3545284","url":null,"abstract":"String prediction (SP) is a highly efficient screen content coding technique adopted into international and China video coding standards. However, SP requires a high number of SRAM fetches to decode and output a block for display, leading to low throughput (T). Low T results in a high decoder and SRAM clock frequency to output the required number of display pixels, which is determined by the specific display resolution and frame rate. To achieve hardware-decoder-friendly high throughput SP (HTSP), this paper exploits specific SRAM fetch rate constraints for five SRAM-cell sizes commonly used in hardware decoder designs. Additionally, the optimal reference string selection process is formulated as a multi-constraint rate-distortion optimization (MCRDO) problem and a novel reference string searching method is presented. HTSP boosts throughput by up to 4 times compared to the state-of-the- art SP, with only a negligible impact on coding efficiency.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1166-1170"},"PeriodicalIF":3.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667630","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信