检索结果-内蒙古大学图书馆

Extracting High-Discriminative Features for Detecting Double JPEG Compression with the Same Quantization Matrix

IEEE Transactions on Circuits and Systems for Video technology 2025年第5期35卷 4727-4739页

作者： Li, Wenjie Li, Xiaolong Ni, Rongrong Zhao, Yao Tianjin University of Technology School of Computer Science and Engineering Tianjin300384 China Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China

Detecting double JPEG compression with the same quantization matrix is a crucial yet challenging task in image forensics. Existing methods often fail to accurately identify and fully exploit the differences between singly and doubly compressed images, resulting in unsatisfactory detection performance, especially for cases with low quality factors (QFs). To address this issue, a novel method is proposed to extract highly discriminative features for performance enhancement. First, we design a new error block classification method that categorizes error blocks into stable error blocks, rounding error blocks (REBs), and truncation error blocks (TEBs). This classification method enables more accurate identification of TEBs, which are the most discriminative blocks in error images for cases with low QFs. Then, based on the theoretical analysis of REBs and TEBs, an intrinsic variable that directly leads to the differences between two classes of images is derived, providing more essential characteristics for the detection. Finally, a number of 25-dimensional highly discriminative features are extracted from REBs, TEBs, and flat blocks. Experimental results demonstrate that the proposed method outperforms several state-of-the-art works, especially on images with low QFs. © 1991-2012 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Several Points are all It Takes: Saluting User-Assisted Single Image Reflection Removal

引用

IEEE Signal Processing Letters 2025年 32卷 1735-1739页

作者： He, Lingzhi Chang, Yakun Zhao, Yao Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Visual Intellgence +X International Cooperation Joint Laboratory of MOE Beijing100044 China

Reflection removal is essential for applications in photography, object detection, and augmented reality. Single-image reflection removal (SIRR) offers greater flexibility and applicability than multi-image methods, making it ideal for real-time scenarios. However, strong reflections obscure large portions of the transmission layer, limiting the performance of existing methods. We propose a novel user-assisted approach for SIRR, where users annotate occluded objects by selecting their categories and locations. This provides critical semantic information to guide accurate transmission layer recovery. Additionally, we design a hybrid CNN-Transformer network that leverages local feature extraction and global context modeling to address strong reflection challenges. Experiments on the strong reflection datasets demonstrate the effectiveness of our method, achieving significant improvements in transmission layer recovery and outperforming existing advanced methods across multiple metrics. © 1994-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design of Large-Span Beamforming Antenna Based on Beam Superposition and Structure Mapping

引用

IEEE Antennas and Wireless Propagation Letters 2025年第5期24卷 1268-1272页

作者： Zhang, Yulu Zhang, Xiang Wang, Junhong Beijing Jiaotong University Key Laboratory of All Optical Network and Advanced Telecommunication Network Ministry of Education of China The Institute of Lightwave Technology Beijing100044 China China Academy of Information and Communications Technology Beijing100191 China

In this paper, a novel beamforming patch array antenna with large-span cosecant-distribution pattern is designed. The antenna contains two layers, and eight radiating patch elements together with feeding microstrip branches are designed on the upper surface of the top layer. The bottom layer is a substrate integrated waveguide (SIW) with a series of slots cut in the upper wall, which couple the energy in SIW up to the feeding microstrip branches. Five linear arrays are designed first to generate beams with different radiation angles, and then mapped into a composite array in a weighted way to generate a large-span cosecant-distribution pattern, and minimize the size of antenna. The proposed antenna can provide a uniform radio wave coverage in long-straight confined spaces for stable mobile communications. © 2002-2011 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

BOTDA temperature extraction based on coordinate attention residual network 4

BOTDA temperature extraction based on coordinate attention r...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Zhang, Zhihao Qian, Yuhao Wang, Liang Ma, Xiaole Yu, Kuanglu Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing Jiao tong University Beijing100044 China Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781510688834

We have proposed and demonstrated a coordinate-attention-based residual network (CARN) that is capable of accurately extracting temperature distributions in Brillouin gain spectra with low signal-to-noise ratio (SNR). The performance of the CARN network is statistically analyzed experimentally and compare it with the conventional Lorentz curve fitting method (LCF) and the BFSCNN network, which show that CARN has higher temperature extraction accuracy and stronger noise tolerance and robustness over a wide range of temperature and SNR. At a relatively low 6.5dB SNR, the average temperature RMSE error extracted by CARN at the end of a 9.6km sensing fiber is only 1.08°C, which is an improvement of about 54% and 29%, respectively. The average SD is only 0.75℃, an improvement of about 64% and 38%, respectively. © 2025 SPIE.

关键词： Signal to noise ratio Temperature distribution Signal detection Temperature metrology Convolution Data processing Optical fibers Signal processing Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

A Consolidated Game Framework for Cooperative Defense Against Cross-Domain Cyber Attacks in Satellite-Enabled Internet of Things

引用

IEEE Internet of Things Journal 2025年第9期12卷 12853-12868页

作者： Huang, Linan Liu, Peilong Chen, Xu Jiang, Chunxiao Kuang, Linling Lu, Jianhua Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China Tsinghua University Department of Electronic Engineering Beijing100084 China Tsinghua University Beijing National Research Center for Information Science and Technology State Key Laboratory of Space Network and Communications Beijing100084 China Tsinghua University Department of Electronic Engineering State Key Laboratory of Space Network and Communications Beijing100084 China

As the adoption of satellite-enabled Internet of Things (IoT) continues to rise, its intricate multidomain architecture becomes increasingly susceptible to cross-domain cyber threats. Attackers can exploit compromised IoT devices, inject malicious packets into data streams aggregated at the IoT gateway for satellite backhaul, and potentially endanger the satellite network during transmission by exploiting the hardware, software, and protocol vulnerabilities. Compared to single-domain defenses, cooperative defense at the IoT devices, IoT access network, and satellite transmission network provides fine-granularity defense against cross-domain intelligent attacks. However, quantifying cross-domain impacts and tilting incentive misalignment among different participants remain significant challenges, making systematic cooperative defense development a complex task. To address this, we develop a tripartite security game framework to characterize the impacts of attacks and defense methods across both the terrestrial and satellite domains. Leveraging this game model, we devise flow pricing to optimally motivate the IoT network operator (IoT-NO) to prevent malicious packet infiltration into the satellite domain. Subsequently, we propose efficient learning algorithms enabling both the IoT-NO to ascertain their ideal flow sampling strategies and the satellite service provider (SAT-SP) to determine optimal flow pricing. The simulation results corroborate the effectiveness of the consolidated game in counteracting cross-domain cyber attacks and facilitating cooperative defense between the IoT-NO and the SAT-SP with nonaligned incentives. © 2014 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Brillouin Frequency Shift Extraction for BOTDA Based on Gramian Angular Fields 4

Brillouin Frequency Shift Extraction for BOTDA Based on Gram...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Zhu, Borong Zhang, Zhihao Qian, Yuhao Ma, Xiaole Wang, Liang Yu, Kuanglu Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China National Engineering Laboratory for Next Generation Internet Access System School of Optics and Electronic Information Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781510688834

To accurately extract Brillouin frequency shift of BOTDA with large sweeping step sizes, a novel structure of GAFCNN is proposed, combining time series coding with convolutional neural networks. The experimental data validation results demonstrate that the GAFCNN is capable of obtaining more accurate results under large sweep steps and low signal-to-noise ratios (SNRs) than other current methods. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image reconstruction based on Graph structure for MRI-guided diffuse optical tomography 17

Image reconstruction based on Graph structure for MRI-guided...

引用

17th International Conference on Photonics and Imaging in Biology and Medicine, PIBM 2024

作者： Zou, Peiwen Wei, Chengpu Hu, Ting Li, Zhe Sun, Zhonghua Jia, Kebin Feng, Jinchao Beijing Key Laboratory of Computational Intelligence and Intelligent System School of Information Science and Technology Beijing University of Technology Beijing100124 China Beijing Laboratory of Advanced Information Networks Beijing100124 China

ISBN: (数字)9781510688070

ISBN: (纸本)9781510688063

Diffuse optical tomography (DOT) is a non-invasive, label-free imaging technique widely used in applications such as breast cancer diagnosis and brain imaging. It allows for the quantitative measurement of tissue functional parameters, including the concentrations of oxyhemoglobin, deoxyhemoglobin, and water. However, the quality of reconstructed images is poor due to light scattering. To address this challenge, one effective strategy is to incorporate anatomical information from high-resolution imaging to guide DOT reconstruction. In this study, a new approach (GRI) is developed to leverage MRI images based on graph structure for DOT reconstruction. And its feasibility and effectiveness were evaluated with numerical simulations. The results indicate that GRI significantly improves the structural similarity index (SSIM) of reconstructed total hemoglobin (HbT) images, outperforming conventional Tikhonov regularization and direct regularization imaging (DRI) method by more than 63% and 82%, respectively. These findings are further supported by experiments using real patient data, which demonstrate GRI's potential in breast cancer diagnosis. © 2025 SPIE.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

A Method for Image Super-Resolution Reconstruction with Attention Mechanism in Generative Adversarial networks 24

A Method for Image Super-Resolution Reconstruction with Atte...

引用

13th International Conference on Computing and Pattern Recognition, ICCPR 2024

作者： Wang, Sirong Liu, Pengyu Chen, Shanji Jia, Shaohua Dong, Min Zheng, Tianyang School of Information Science and Technology Beijing University of Technology Beijing China Advanced Information Network Beijing Laboratory Beijing University of Technology Beijing China College of Physics and Electronic Information Engineering Qinghai Minzu University Qinghai China

ISBN: (纸本)9798400717482

The generation of image texture details is a crucial aspect in the assessment of the efficacy of image super-resolution reconstruction. In order to enhance the super-resolution effect of real-world degraded images, this paper proposes a method for image super-resolution reconstruction with an attention mechanism in generative adversarial networks. Firstly, a multi-angle degradation modeling process is introduced for real-world image degradation scenarios to better simulate complex real-world degradation;secondly, the structure of the Residual-in-Residual Dense Block (RRDB) commonly used in super-resolution reconstruction generative adversarial networks was optimized, and combined with the dynamic attention mechanism, a Residual-in-Residual Dense Block with Dynamic Channel and Spatial Attention Mechanism (RRDB-DCSA) is proposed, and this module is used to construct a generator for Generative adversarial networks (GAN);and lastly, locally discriminative learning loss is introduced to reduce the artifacts caused by the GAN network with the aim of learning features associated with image degradation. The experimental results demonstrate that the proposed algorithm is capable of reconstructing the detailed components of an image while simultaneously suppressing the artifacts present in scenes featuring people, animals, and landscapes. In terms of subjective assessment, the algorithm exhibits superior performance in this regard, with an improvement of nearly 17 in PSNR and SSIM, respectively. Additionally, the algorithm exhibits a reduction of nearly 15 in LPIPS and NIQE when compared with traditional and classical algorithms of the GAN network. © 2024 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Communication Scene Recognition Framework Based on Deep Learning with Multi-Sensor Fusion

引用

China Communications 2025年第4期22卷 174-201页

作者： Feng Yufei Zhong Xiaofeng Chen Xinwei Zhou Shidong Department of Electronic Engineering Tsinghua UniversityBeijing 100084China State Key Laboratory of Space Network and Communications(Tsinghua University) Beijing 100084China Beijing National Research Center for Information Science and Technology Beijing 100084China

This paper presents a comprehensive framework that enables communication scene recognition through deep learning and multi-sensor *** study aims to address the challenge of current communication scene recognition methods that struggle to adapt in dynamic environments,as they typically rely on post-response mechanisms that fail to detect scene changes before users experience *** proposed framework leverages data from multiple smartphone sensors,including acceleration sensors,gyroscopes,magnetic field sensors,and orientation sensors,to identify different communication scenes,such as walking,running,cycling,and various modes of *** experimental comparative analysis with existing methods on the open-source SHL-2018 dataset confirmed the superior performance of our approach in terms of F1 score and processing ***,tests using a Microsoft Surface Pro tablet and a self-collected beijing-2023 dataset have validated the framework's efficiency and generalization *** results show that our framework achieved an F1 score of 95.15%on SHL-2018and 94.6%on beijing-2023,highlighting its robustness across different datasets and ***,the levels of computational complexity and power consumption associated with the algorithm are moderate,making it suitable for deployment on mobile devices.

关键词： communication scene recognition deep learning sensor fusion SHL smartphone-based applications

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：