检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yida Li Jun Shi Zhaohui Wang Tiantong Wang Ziqi Zhu Minfan Zhao Junshi Chen Hong An School of Computer Science and Technology University of Science and Technology of China Hefei China School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurate 3D reconstruction of the right ventricle from multi-view echocardiograms is crucial for the quantitative diagnosis of cardiac diseases. However, existing methods often fail to deliver satisfactory results due to the structural complexity of the right ventricle and the sparsity of non-parallel ultrasound views. In this paper, we propose an efficient reconstruction method named Carver, which redefines 3D reconstruction of the right ventricle as a voxel-wise dense prediction task for the first time. The core idea lies in using a deep neural network to learn the end-to-end deformation from a coarse geometric convex hull to a fine structure of the right ventricle, similar to carving. To improve the reconstruction accuracy and robustness, we design a dual-aware network incorporating prior contour information to enhance learning representation. We conduct extensive experiments on an echocardiography dataset containing 1,278 instances to validate the effectiveness of the proposed method. Experimental results demonstrate that Carver outperforms existing state-of-the-art methods, achieving a Volume Similarity (VS) of 98.75%, a Dice Similarity Coefficient (DSC) of 97.80%, a Hausdorff Distance (HD) of 4.96, and a Root Mean Square Error (RMSE) of 0.013 for the ejection fraction, while maintaining considerable robustness even with sparser inputs. The code is available at https://***/ustclyd/Carver.

关键词： Accuracy Three-dimensional displays Convex hulls Ultrasonic imaging Deformation Shape reconstruction algorithms Signal processing Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

Nondestructive Testing Technology for X-ray Computed Tomography with Mask Region-based Convolutional Neural Network

Nondestructive Testing Technology for X-ray Computed Tomogra...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Ruonan Hao Emergency Rescue Center of Xinjiang Oilfield Company Karamay China

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In recent days, the Non-destructive testing (NDT) technology with X-ray Computed Tomography (XCT) has revolutionized for internal inspection of materials and components. The advanced reconstruction algorithms such as back projection and iterative construction improved image quality. However, the reconstruction algorithms are sensitive to noise which led to the artifacts while iterative construction is computationally expensive which is prone to convergence issues. To overcome these issues, Mask Region-based Convolutional Neural Network (Mask RCNN) is proposed for the effective segmentation of XCT images. The proposed Mask RCNN learns to recognize and suppress the noise patterns in the reconstructed images that reduce the noise sensitivity. In addition, the refinement and correct reconstruction of images reduces the computational complexity. Initially, the collected data is preprocessed with Wavelet Fourier Transform (WFT) to remove artifacts from images. After that, the proposed RCNN is utilized to segment the XCT images into semantic labels including pores and cracks. From the results, the proposed Mask RCNN attained better results when compared to existing Modified U-Net based segmentation model in terms of mean Intersection of Union ( mIoU ), for class 1 (pores) of 90.12%, for class 2 (cracks) of 84.08% and the total of 90.12% respectively.

关键词： Wavelet transforms Computed tomography Nondestructive testing Noise Semantics reconstruction algorithms Feature extraction Iterative algorithms Convolutional neural networks X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

A Near-Field 3D Parameter Estimation Method Based on a Symmetric Enhanced Nested Array

A Near-Field 3D Parameter Estimation Method Based on a Symme...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Linke Yu Hua Chen Dingfan Xue Wei Liu Ye Tian Gang Wang Faculty of Electrical Engineering and Computer Science Ningbo University China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, a high-precision three-dimensional (3-D) near-field (NF) localization method is proposed under an underdetermined case based on a symmetric enhanced nested array (SENA). Firstly, the symmetry of the array and the fourth-order cumulant (FOC) are utilized to construct the equivalent virtual far-field (FF) reception data. Then, a gridless sparse and parametric approach (SPA), combined with an l 1 -SVD based pairing procedure, is used to obtain estimates for two paired angles. Finally, a one-dimensional (1-D) spectral estimator is applied to obtain the estimate of range parameter. Simulation results show the effectiveness of the proposed method.

关键词： Location awareness Three-dimensional displays Parameter estimation Simulation Signal processing algorithms Estimation reconstruction algorithms Multiple signal classification Arrays Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Complementary Carrier based PWM Strategy for Average Current Sampling of Three-Phase Inverter Using Single Current Sensor

A Complementary Carrier based PWM Strategy for Average Curre...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Byeong-Il Kim Joon-Seok Kim Yeongsu Bak June-Seok Lee School of Electronics and Electrical Engineering Dankook University South Korea Department of Electrical Energy Engineering Keimyung University South Korea

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

This paper proposes a complementary carrierbased pulse width modulation (PWM) strategy for the average current sampling of three-phase inverter using single current sensor (SCS) in dc-link. Conventional three-phase current reconstruction method for a three-phase inverter using SCS reconstructs the three-phase currents by measuring the two-phase currents corresponding to the two active voltage vectors. However, the current measured by SCS is not the average current. In addition, there is a current reconstruction dead zone (CRDZ) near the boundary of each sector. The proposed PWM strategy outputs the voltage of the inverter using two carriers that are inverted in phase with each other. This strategy compares the inverted carrier with the voltage references of one or two phases and compares the remaining phase voltage references with the noninverted carrier. This allows us to measure the average current and significantly reduces the CRDZ to the corners of the space vector hexagon. The validity of the proposed strategy is verified by simulation results.

关键词： Voltage measurement Current measurement Simulation Measurement uncertainty Pulse width modulation reconstruction algorithms Inverters Vectors Stability analysis Sensors

来源：评论

学校读者我要写书评

暂无评论

Fast Multi-Contrast MRI Using Joint Multiscale Energy Model

Fast Multi-Contrast MRI Using Joint Multiscale Energy Model

引用

IEEE International Symposium on Biomedical Imaging

作者： Nima Yaghoobi Jyothi Rikhab Chand Yan Chen Steve R. Kecskemeti James H. Holmes Mathews Jacob University of Virginia University of Wisconsin-Madison University of Iowa

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

The acquisition of 3D multicontrast MRI data with good isotropic spatial resolution is challenged by lengthy scan times. In this work, we introduce a CNN-based multiscale energy model to learn the joint probability distribution of the multi-contrast images. The joint recovery of the contrasts from undersampled data is posed as a maximum a posteriori estimation scheme, where the learned energy serves as the prior. We use a majorize-minimize algorithm to solve the optimization scheme. The proposed model leverages the redundancies across different contrasts to improve image fidelity. The proposed scheme is observed to preserve fine details and contrast, offering sharper reconstructions compared to reconstruction methods that independently recover the contrasts. While we focus on 3D MPNRAGE acquisitions in this work, the proposed approach is generalizable to arbitrary multi-contrast settings.

关键词： Solid modeling Three-dimensional displays Magnetic resonance imaging Volume measurement Redundancy reconstruction algorithms Probability distribution Velocity measurement Spatial resolution Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Chat-Driven 3D Human Pose and Shape Editing with Large Language Models

Chat-Driven 3D Human Pose and Shape Editing with Large Langu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Feng Zhou Chi Li Ju Dai Mengxiao Zhu Yongmei Zhang Yu-Kun Lai Paul L. Rosin North China University of Technology Beijing China Peng Cheng Laboratory Shenzhen China Cardiff University Cardiff UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Generating and creating humanoid 3D models has received increasing attention recently due to its fundamental support for many high-level 3D applications. Although automatic 3D pose and shape reconstruction methods have achieved promising results, there are still some failure cases due to self-occlusions, viewpoint changes, and the complexity of human pose articulations. In this paper, we propose a novel way to leverage Large Language Models (LLMs) to interactively reconstruct human pose and shape based on a Skinned Multi-Person Linear (SMPL) model. We construct a mapping table to fine-tune an LLM, enabling it to understand user inputs better and output the positional information of joint points. Additionally, a simple neural network is adopted to regress the shape cues of the SMPL. We demonstrate a gallery of results of numerous poses and shapes. We validate our method via numerical evaluations, user studies, and comparisons to manually posed characters and previous work.

关键词： Solid modeling Three-dimensional displays Shape Large language models Neural networks Humanoid robots Signal processing reconstruction algorithms Complexity theory Speech processing

来源：评论

学校读者我要写书评

暂无评论

RAS-GNN: Reconstructing APT Attack Scenario Using Graph Neural Network

RAS-GNN: Reconstructing APT Attack Scenario Using Graph Neur...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhicheng Huang Ping Wang Peking University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

As a kind of multi-step attack, the APT attack is long-term, highly hidden, and usually exploits novel vulnerabilities. To detect and respond to APT attacks, security analysts need to analyze a large number of system logs and network traffic to determine the sequence of activities executed by APT attacks. Provenance graph is an effective approach to determining the sequence of APT attacks and reconstructing the APT attack scenario for detection and defense. However, its weakness of relying on prior knowledge and difficulty in fine-grained detection of attack behavior hinder provenance graph in practice. In this paper, we propose RAS-GNN, a graph neural network framework with an attention mechanism to reconstruct the APT attack scenario, without prior knowledge. We embed the attributes of attack nodes and their edges in provenance graph, and use the state transition information. We evaluated RAS-GNN’s ability to detect APT attacks and reconstruct APT attack scenarios on 10 APT attack scenarios. RAS-GNN can detect APT attacks with precision, recall, and F1-score of 95.32%, 99.12%, 97.09%, respectively. Moreover, it has a higher reconstruction ability than other attack scenario reconstruction methods.

关键词： Knowledge engineering Attention mechanisms Image edge detection Telecommunication traffic Signal processing reconstruction algorithms Graph neural networks Security Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

Let There Be Light: Robust Lensless Imaging Under External Illumination With Deep Learning

Let There Be Light: Robust Lensless Imaging Under External I...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Eric Bezzam Stefan Peters Martin Vetterli Audiovisual Communications Laboratory École Polytechnique Fédérale de Lausanne (EPFL) Lausanne Switzerland

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Lensless cameras relax the design constraints of traditional cameras by shifting image formation from analog optics to digital post-processing. While new camera designs and applications can be enabled, lensless imaging is very sensitive to unwanted interference (other sources, noise, etc.). In this work, we address a prevalent noise source that has not been studied for lensless imaging: external illumination e.g. from ambient and direct lighting. Being robust to a variety of lighting conditions would increase the practicality and adoption of lensless imaging. To this end, we propose multiple recovery approaches that account for external illumination by incorporating its estimate into the image recovery process. At the core is a physics-based reconstruction that combines learnable image recovery and denoisers, all of whose parameters are trained using experimentally gathered data. Compared to standard reconstruction methods, our approach yields significant qualitative and quantitative improvements. We open-source our implementations and a 25K dataset of measurements under multiple lighting conditions.

关键词： Source separation Noise Lighting Interference reconstruction algorithms Cameras Optics Speech processing Image reconstruction Standards

来源：评论

学校读者我要写书评

暂无评论

Fast algorithms of Image Fusion for Super-Resolution reconstruction from Multiple Images with Random Shifts

引用

Chinese Journal of Electronics 2023年第1期21卷 69-72页

作者： Beijia Ning Jie Li Xinbo Gao VIPS Laboratory School of Electronic Engineering Xidian University Xi'an China

The commonly-used image Super-resolution (SR) reconstruction methods are computationally expensive and only applicable to “offline processing” cases. To reduce the work-load of SR fusion, three algorithms, i.e., Neighborhood searching nearest interpolation (NSNI), Fixed-distance searching nearest interpolation (FDSNI) and Two-direction linear interpolation (TDLI), are proposed in this paper in the condition of multiple lower resolution images with global random shifts. The simulation results illustrate the effectiveness, speed and quality advantages of the three proposed SR algorithms over classic algorithms.

关键词： Interpolation Simulation Superresolution reconstruction algorithms Real-time systems Image fusion Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

algorithms for the nonuniform acquisition and subsequent reconstruction of data

Algorithms for the nonuniform acquisition and subsequent rec...

引用

International Conference on Digital Signal Processing (DSP)

作者： G.B. Irvine D.R.S. Cumming Department of Electronics and Electrical Engineering University of Glasgow Glasgow UK

algorithms are presented for the purposes of nonuniform sampling and reconstruction of data. The sampling procedure is based on the Adams-Bashforth-Moulton multistep predictor-corrector method for the solution of ordinary differential equations, with Newton backward differencing interpolation formulae facilitating sample rate changes. It is necessary to store 2n + 1 equispaced past values of t and the corresponding values of y, where y = g(t), and n is the order of the Adams methods. The technique is demonstrated using third order methods and the results compared with those obtained using second and fourth order forms. The data reconstruction algorithm for unevenly spaced data is based on a Lagrange cubic polynomial.

关键词： Sampling methods Polynomials Nonuniform sampling Differential equations Interpolation reconstruction algorithms Lagrangian functions Microsensors Timing Time measurement

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：