检索结果-内蒙古大学图书馆

HF2TNet: A Hierarchical Fusion Two-Stage Training Network for Infrared and Visible Image Fusion

IEEE signal processing LETTERS 2024年 31卷 3164-3168页

作者： Lv, Ting Ji, Chuanming Jiang, Hong Liu, Yu Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Sichuan Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Sydney 2007 Australia Hefei Univ Technol Dept Biomed Engn Hefei 230009 Peoples R China

In the field of infrared and visible image fusion, current algorithms often focus on complex feature extraction and sophisticated fusion mechanisms, ignoring the issues of information redundancy and feature imbalance. These limit effective information aggregation. To address these issues, this paper proposes a hierarchical fusion strategy with a two-stage training network, abbreviated as HF2TNet, which achieves effective information aggregation in a staged manner. In the initial training stage, a three-stream encoder-decoder architecture is proposed, seamlessly integrating CNN and transformer modules. This architecture extracts both global and local features from visible and infrared images, capturing their shared attributes before the fusion process. Moreover, a multi-shared attention module (MSAM) is proposed to profoundly reconstruct and augment the visible and infrared features, ensuring the preservation and enhancement of details across modalities. In the subsequent stage, HF2TNet utilizes the pre-integrated features as query inputs for the dual MSAMs. These modules interact with the previously reconstructed infrared and visible features to enhance complementary information and ensure a balanced feature fusion. Experimental results indicate HF2TNet's superior performance on standard datasets like MSRS and TNO, especially in complex scenes, demonstrating its potential in multimodal image fusion.

关键词： Feature extraction Training Image reconstruction Image fusion Transformers Decoding Convolution Vectors signal processing algorithms Sensor phenomena and characterization CNN deep learning image fusion transformer

来源：评论

学校读者我要写书评

暂无评论

Reconstructed Variational Bayesian Kalman Filter Under Heavy-Tailed and Skewed Noises

引用

IEEE signal processing LETTERS 2024年 31卷 2405-2409页

作者： Wang, Ke Wu, Panlong Zhao, Baochen Kong, Lingqi He, Shan Nanjing Univ Sci & Technol Sch Automat Nanjing 210094 Peoples R China

In this letter, a new reconstructed variational Bayesian (RVB) Kalman filter is proposed for handling heavy-tailed and skewed noises. The Student's t distribution is used to model predicted state, and the skewed Gaussian-exponential mixture distribution is used to model measurement noises. In order to more accurately deal with process noises, we model the predicted covariance based on the inverse Wishart distribution. Subsequently, a new RVB framework is proposed to separate the iterations of process and measurement noise related parameters, which achieves decoupling of hidden variables. Under the new RVB framework, the RVB-ST-SGEM-KF algorithm is derived. The superiority of the proposed RVB framework and algorithm are validated through a maneuvering target tracking scenario.

关键词： Noise signal processing algorithms Noise measurement Heavily-tailed distribution Predictive models Adaptation models Target tracking Heavy-tailed and skewed noises Kalman Filter reconstructed variational Bayesian skewed Gaussian-exponential mixture distribution student's t distribution

来源：评论

学校读者我要写书评

暂无评论

High-Speed Energy-Efficient Fixed-Point Signed Multipliers for FPGA-Based DSP Applications

引用

IEEE EMBEDDED SYSTEMS LETTERS 2024年第4期16卷 417-420页

作者： Nagar, Mitul Sudhirkumar Mathuriya, Aditya Patel, Sohan H. Engineer, Pinalkumar J. Sardar Vallabhbhai Natl Inst Technol Dept Elect Engn Surat 395007 India

Among various platforms for computer vision algorithms, FPGA has gained popularity as a low-power solution. These algorithms involve convolution operation which are extensively performed using signed multipliers. Hence, this work proposes high-speed and energy-efficient signed fixed-point multipliers for digital signal processing (DSP) applications. This work focuses on reducing the combinational path delay (CPD) using LUT-based Booth radix-4 partial product (PP) generation with Bewick's sign extension and Dadda-based concurrent PP reduction with carry save adder (CSA) for Xilinx (now AMD) FPGA. The proposed design eliminates the requirement of a long carry chain for PP reduction. The proposed multiplier reduces CPD by 3%, 4%, and 16% compared to the state-of-the-art (SoA) multiplier for 8x8 , 16x16 , and 32x32 sizes, respectively. We have also analyzed our proposed 32x32 multiplier by pipelining, which offers CPD and EDP reduction by 12.28% and 19.47% at the cost of a 3% and 80% increase in LUTs and flip-flops, respectively, compared to the combinatorial multiplier.

关键词： Table lookup Field programmable gate arrays Adders Vegetation Standards signal processing algorithms Resource management Booth radix-4 digital signal processing (DSP) energy-efficient field-programmable gate arrays signed fixedpoint multiplier

来源：评论

学校读者我要写书评

暂无评论

Robust Elliptic Positioning via Sparse Regularization and ADMM for a Distributed MIMO Radar in the Presence of Outliers

引用

IEEE signal processing LETTERS 2024年 31卷 2110-2114页

作者： Dang, Xudong Liu, Hongwei Yan, Junkun Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

Large-magnitude errors, known as outliers, have a significant impact on the accuracy of elliptic positioning (EP) for a distributed MIMO radar. Most of the existing EP techniques are developed in the least squares sense, susceptible to outliers. In this letter, we propose to leverage a sparse argument to model the outliers and decompose the measurement noise into two components, namely, inliers and outliers. By doing so, the robust EP is formulated as a & ell;(0) -norm minimization problem with non-convex constraints. By relaxing the objective & ell;(0) -norm with the convex & ell;(1) -norm, an alternating direction method of multipliers based algorithm is derived to efficiently solve the relaxed optimization problem. Numerical results illustrate the improved performance of the proposed method compared to the existing methods.

关键词： Noise Pollution measurement Noise measurement MIMO radar Optimization Convex functions signal processing algorithms Alternating direction method of multipliers (ADMM) distributed MIMO radar elliptic positioning outliers sparse regularization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Pattern-Coupled Sparse Bayesian Learning for Channel Estimation in OTFS Systems

引用

IEEE signal processing LETTERS 2024年 31卷 2895-2899页

作者： Chen, Zhuo Niu, Xiaoming Ding, Jian Wu, Hong Liu, Zhiyang Nankai Univ Coll Elect Informat & Opt Engn Tianjin 300350 Peoples R China Nankai Univ Tianjin Key Lab Optoelect Sensor & Sensing Network Tianjin 300350 Peoples R China China Res Inst Radiowave Propagat Natl Key Lab Electromagnet Environm Qingdao 266107 Peoples R China Nankai Univ Minist Educ Engn Res Ctr Thin Film Optoelect Technol Tianjin 300350 Peoples R China

The orthogonal time frequency space (OTFS) has emerged as a promising modulation waveform for high-mobility wireless communications owing to its robust advantages of resisting Doppler effects. However, due to the limit of the frame duration, the fractional Doppler shift appears, which is a challenge for channel estimation in OTFS systems. In this letter, we formulate the channel estimation problem as a block sparse signal recovery issue and propose an adaptive pattern-coupled sparse Bayesian learning (APCSBL) method. To be specific, we introduce a pattern-coupled hierarchical Gaussian prior model to characterize the dependencies among adjacent channel coefficients. On this basis, an adaptive hyperparameter strategy is presented, in which we appropriately utilize various coupling parameters further to characterize the strength of the correlation between adjacent elements. Then we exploit the expectation maximization (EM) algorithm to update the hidden variables and the channel vector. Simulation results demonstrate that the proposed algorithm outperforms existing methods and works for various environments.

关键词： Channel estimation Symbols Bayes methods Delays signal processing algorithms Indexes Doppler shift Vectors Estimation Adaptive systems Adaptive pattern-coupled sparse Bayesian learning block sparse signal recovery channel estimation OTFS

来源：评论

学校读者我要写书评

暂无评论

A Density Clustering-Based CFAR Algorithm for Ship Detection in SAR Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1页

作者： Li, Yang Wang, Zeyu Chen, Hongmeng Li, Yachao Beijing Univ Posts & Telecommun Sch Informat & Commun Engn State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Inst Radio Measurement Beijing 100854 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Shaanxi Peoples R China

The clutter selection strategy based on sliding window in the conventional constant false alarm rate (CFAR) algorithm leads to different clutter qualities between pixels of the same target in a complex environment. To solve the problem, this letter proposes an improved CFAR algorithm based on density clustering. First, a two-parameter CFAR is used to detect ship targets. Then, density clustering is performed on each detected target pixel based on spatial distance and detection threshold to improve the target detection accuracy. Finally, false alarms caused by speckle noise are eliminated by using the number of times a pixel is clustered. The experimental results show that compared with the conventional CFAR algorithm and the superpixel-level CFAR detectors for ship detection in synthetic aperture radar (SAR) imagery (SP-CFAR), the proposed algorithm achieves a detection accuracy improvement of over 14.8% in heterogeneous clutter scenarios and dense target scenarios, while maintaining a low false alarm rate no higher than 0.13% in strong noise environments.

关键词： Clustering algorithms Clutter Marine vehicles Radar polarimetry signal processing algorithms Detectors Noise Constant false alarm rate (CFAR) density clustering ship detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Joint Learning Spatial-Temporal Attention Correlation Filters for Aerial Tracking

引用

IEEE signal processing LETTERS 2024年 31卷 686-690页

作者： Zhao, Bo Ma, Sugang Zhao, Zhixian Zhang, Lei Hou, Zhiqiang Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Peoples R China Changan Univ Sch Informat Engn Xian 710064 Peoples R China Northwestern Polytech Univ Sch Automat Xian 710072 Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian 710121 Peoples R China Xian Univ Posts & Telecommun Xian 710121 Peoples R China

Discriminative correlation filter (DCF)-based UAV tracking algorithms have drawn much attention due to their outstanding robustness and high computational efficiency. However, these algorithms are easily disturbed by background noise and abrupt changes in target appearance, leading to tracking failure. To address the issues above, we propose a real-time UAV object tracking algorithm with adaptive spatial-temporal attention. Specifically, we construct two filters with different roles based on the training sample's target foreground and environmental background. The spatial attention filter is implemented by incorporating a spatial context regularizer into the traditional DCF paradigm, which fully utilizes background environmental information to suppress background environmental noise and effectively distinguish between the target and the background. The temporal attention filter focuses on the continuity of the target samples, modeling only the target patch samples during the training process and introducing a temporal context regularizer, which substantially enhances the tracker's robustness against target occlusions and deformations. The two are jointly optimized by the Alternating Direction Method of Multipliers (ADMM) algorithm, which is mutually constrained during training and complemented during detection. Extensive experiments on three mainstream UAV benchmarks demonstrate the tracking advantages of the proposed algorithm.

关键词： Target tracking Filtering algorithms Information filters Training signal processing algorithms Correlation Autonomous aerial vehicles Discriminative correlation filter unmanned aerial vehicle temporal context regularization spatial context regularization dual regularization

来源：评论

学校读者我要写书评

暂无评论

Design and Preliminary Evaluation of a Handheld Compliant Robot for Membrane Peeling Using Negative Pressure Adsorption

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2025年

作者： Zheng, Yu Liu, Jianjun Yang, Yang Yu, Jingjun Guang, Chenhan Wang, Zhaodong Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China Beihang Univ Sch Mech Engn & Automat Beijing 100191 Peoples R China Beihang Univ Robot Inst Beijing 100191 Peoples R China North China Univ Technol Sch Mech & Mat Engn Beijing 100144 Peoples R China

In retinal surgery, membrane peeling is a challenging procedure that requires surgeons to limit peeling force and manage disturbance force at the millinewton level. This article presents a novel handheld compliant robot designed to assist in membrane peeling, featuring a five-chain parallel compliant module and a force-sensing tube. The compliant module is used to adjust the tip's transverse position actively, while the tube is designed to adsorb the membrane and sense the peeling force. The Jacobian matrix of the proposed robot is also derived. Then, a data process method based on wavelet decomposition and Kalman filtering is introduced to identify the disturbance force. A control method based on the Jacobian matrix is also proposed to compensate the disturbance force. Finally, the proposed robot is evaluated through bench test and handheld test, in which chicken chorioallantoic membrane is utilized as the ex-vitro model. The handheld test results show that the root mean square and maximum of disturbance force are reduced by 44.1% and 52.7%, respectively. The membrane detaches from the tube when the peeling force approaches 15 mN, which provides a passive safety guarantee of membrane peeling.

关键词： Robots Force Robot sensing systems Surgery Retina Adsorption Deformation signal processing algorithms Robot kinematics Hoses Force control handheld robot membrane peeling negative pressure adsorption

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Bistatic Target Reflectivity in ISAC-Enabled V2V Setup Across Diverse Geometrical Road Layouts

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY

引用

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY 2025年 6卷 948-968页

作者： Khan, Aamir Ullah Mint, Saw James Shah, Syed Najaf Haider Schneider, Christian Robert, Joerg Tech Univ Ilmenau Elect Measurements & Signal Proc Grp D-98693 Ilmenau Germany

Integrated Sensing and Communication (ISAC) is an intriguing emerging research area that combines radar sensing and communication functionalities in a unified platform, capitalizing on shared aspects of signal processing, spectrum utilization, and system design. For sensing applications, the reflectivity of objects between Transmitter (TX) and Receiver (RX) is crucial. It is normally modeled as a uniform scatterer or a group of uniform scatterers in wireless channels. These models do not take into account the dependence of reflectivity on the aspect angles of incident and scattering waves, the composed material, and the geometry of the objects. Therefore, we model the reflectivity of target vehicles using their bistatic Radar Cross Section (RCS), as in radar sensing, within a Vehicle to Vehicle (V2V) setup under the Integrated Sensing and Communication (ISAC) framework. Moreover, we consider constant and variable bistatic Target Reflectivity (TR) integrated setups with two diverse traffic scenarios. These traffic scenarios are modeled to be realistic, with diverse geometrical road layouts, variable vehicle velocities, distinct vehicle positions, and the presence of Diffuse (DI) scattering components. Then, we inspect the impact of the bistatic TR on the behavior of the wireless channel and target detection capability. The variable TR integrated setup leads to a more accurate realization of the scenario, leading to outcomes that closely resemble real-world conditions. The results show the substantial impact of the geometrical setup on the distribution of TR, which emphasizes the need to integrate TR into ISAC-enabled V2V channel models.

关键词： Roads Channel models Radar Integrated sensing and communication Scattering Layout Wireless communication Reflectivity Object detection Radar cross-sections Autonomous driving channel models radar cross-section radar sensing radar clutter signal processing algorithms vehicle-to-vehicle communication

来源：评论

学校读者我要写书评

暂无评论

On the Strong Convexity of PnP Regularization Using Linear Denoisers

引用

IEEE signal processing LETTERS 2024年 31卷 2790-2794页

作者： Sinha, Arghya Chaudhury, Kunal N. Indian Inst Sci Dept Computat & Data Sci Bangalore 560012 India Indian Inst Sci Dept Elect Engn Bangalore 560012 India

-In the Plug-and-Play (PnP) method, a denoiser is used as a regularizer within classical proximal algorithms for image reconstruction. It is known that a broad class of linear denoisers can be expressed as the proximal operator of a convex regularizer. Consequently, the associated PnP algorithm can be linked to a convex optimization problem P . For such a linear denoiser, we prove that P exhibits strong convexity for linear inverse problems. Specifically, we show that the strong convexity of P can be used to certify objective and iterative convergence of any PnP algorithm derived from classical methods.

关键词： signal processing algorithms Convergence Kernel Standards Convex functions Superresolution Inverse problems Indexes Image reconstruction Symmetric matrices proximal operator plug-and-play (PnP) regularization strong convexity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：