检索结果-内蒙古大学图书馆

GVI: Guideable Visual Interpretation on medical tomographic images to improve the performance of deep network

Pattern Recognition Letters 2025年 196卷 162-168页

作者： Hui Liu Fan Wei Lixin Yan Sushan Wang Chongfu Jia Lina Zhang Jiansheng Peng Yi Xu School of Control Science and Engineering Dalian University of Technology Dalian China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China Liaoning Key Laboratory of Integrated Circuit and Biomedical Electronic System Dalian China Department of Cardiovascular Radiology The First Affiliated Hospital of Dalian Medical University Dalian China Department of Radiology The First Affiliated Hospital of Dalian Medical University Dalian China Department of Artificial Intelligence and Manufacturing Hechi University Hechi China

In medical image analysis, the demand for interpretable deep neural networks is rapidly growing. However, a major challenge is that most existing interpretative methods are applied after training, leading to a lack of integration with the model’s learning process. As a result, these methods often fail to highlight regions within complex medical images critical for decision-making, such as abnormal tissues or lesions, which are essential for accurate diagnoses and treatment planning. This paper introduces Guided Visual Interpretation (GVI), a framework designed to enhance both the performance and interpretability of deep networks. Building on a deep network model with image-level labels, GVI incorporates a small amount of pixel-level annotations combined with attention mechanisms. These mechanisms facilitate visual interpretation through forward propagation, directing the model’s focus to the most relevant regions. By aligning the network’s decision-making with human cognitive processes, GVI improves interpretability. In our study, an attention layer was added after the convolutional layers of a pre-trained classification network. GVI is trained using a mixed supervision approach that integrates pixel-level annotations with a large amount of image-level data. Experimental results on both private and public datasets show that GVI generates visual explanations consistent with human decision-making principles and achieves superior classification accuracy compared to traditional methods. These findings highlight GVI’s potential to improve interpretability and diagnostic performance in critical fields like medical imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds

arXiv

引用

arXiv 2024年

作者： Long, Juncheng Su, Honglei Liu, Qi Yuan, Hui Gao, Wei Song, Jiarun Wang, Zhou The College of Electronics and Information Qingdao University Qingdao266071 China The School of Control Science and Engineering Shandong University Ji'nan250061 China The School of Electronic and Computer Engineering Peking University Shenzhen518055 China The Peng Cheng Laboratory Shenzhen518066 China The School of Telecommunications Engineering Xidian University Xi'An710071 China The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we develop the first PCQA model dedicated to Trisoup-Lifting encoded 3D point clouds by analyzing bitstreams without full decoding. Specifically, we investigate the relationship among texture bitrate per point (TBPP), texture complexity (TC) and texture quantization parameter (TQP) while geometry encoding is lossless. Subsequently, we estimate TC by utilizing TQP and TBPP. Then, we establish a texture distortion evaluation model based on TC, TBPP and TQP. Ultimately, by integrating this texture distortion model with a geometry attenuation factor, a function of trisoupNodeSizeLog2 (tNSL), we acquire a comprehensive NR bitstream-layer PCQA model named streamPCQ-TL. In addition, this work establishes a database named WPC6.0, the first and largest PCQA database dedicated to Trisoup-Lifting encoding mode, encompassing 400 distorted point clouds with both 4 geometric multiplied by 5 texture distortion levels. Experiment results on M-PCCD, ICIP2020 and the proposed WPC6.0 database suggest that the proposed streamPCQ-TL model exhibits robust and notable performance in contrast to existing advanced PCQA metrics, particularly in terms of computational cost. The dataset and source code will be publicly released at https://***/qdushl/Waterloo-Point-Cloud-Database-6.0. Copyright © 2024, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Perceptual Quality Assessment of Octree-RAHT Encoded 3D Point Clouds

arXiv

引用

arXiv 2024年

作者： Duan, Dongshuai Su, Honglei Liu, Qi Yuan, Hui Gao, Wei Song, Jiarun Wang, Zhou College of Electronics and Information Qingdao University Qingdao266071 China School of Control Science and Engineering Shandong University Ji’nan250061 China School of Electronic and Computer Engineering Peking University Shenzhen518055 China Peng Cheng Laboratory Shenzhen518066 China School of Telecommunications Engineering Xidian University Xi’an710071 China Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we focus on the PCQA problem dedicated to Octree-RAHT encoding mode. First, to address the issue that existing PCQA databases have a small scale and limited distortion levels, we establish the WPC5.0 database which is the first one dedicated to Octree-RAHT encoding mode with a scale of 400 distorted point clouds (PCs) including 4 geometric multiplied by 5 attitude distortion levels. Then, we propose the first PCQA model dedicated to Octree-RAHT encoding mode by parsing PC bitstreams without full decoding. The model introduces texture bitrate (TBPP) to predict texture complexity (TC) and further derives the texture distortion factor. In addition, the Geometric Quantization Parameter (PQS) is used to estimate the geometric distortion factor, which is then integrated into the model along with the texture distortion factor to obtain the proposed PCQA model named streamPCQ-OR. The proposed model has been compared with other advanced PCQA methods on the WPC5.0, BASICS and M-PCCD databases, and experimental results show that our model has excellent performance while having very low computational complexity, providing a reliable choice for time-critical applications. To facilitate subsequent research, the database and source code will be publicly released at https://***/qdushl/Waterloo-Point-Cloud-Database-5.0. Copyright © 2024, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A Study for UAV Autonomous Safe Landing-Site Selection on Rough Terrain 2021

A Study for UAV Autonomous Safe Landing-Site Selection on Ro...

引用

2nd International Conference on Computing and Data Science, CONF-CDS 2021

作者： Zheng, Wenlong Yi, Jianjun Xiang, Haojie Zhou, Bo Wang, Danwei Zhao, Changchun Department of Mechanical Engineering East China University of Science and Technology Shanghai200237 China Intelligent Unmanned System Control Technology Joint Lab Shanghai201109 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Shanghai Aerospace Control Technology Institute Shanghai201109 China

ISBN: (纸本)9781450389570

Autonomous safe landing of UAV is an important function in many scenarios such as force landing and delivery. This paper proposes a method to autonomously select a safe landing site for vertical take-off and landing (VTOL) UAV based on point cloud, which can minimize combined risks posed during touch down at the chosen landing site. The most suitable landing site of a landing zone is selected according to the terrain complexity. In this paper, (1) fine-grained grid elevation map converted from the terrain point cloud is used to calculate the potential risk such as slope, roughness and maximum height difference. (2) A comprehensive risk model is designed to consider all above risks to recognize obstacles and risk areas, and combine the flight distance factors to obtain the final cost map. (3) We process cost map as image by OpenCV to accelerate the processing and reduce reaction time. Terrain point clouds of simulation scene and real world are used for experiments and experimental results show that the selected landing sites can meet the safety requirements, which demonstrate the effectiveness and feasibility of our proposed method. © 2021 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Remote surgery using a neuroendovascular intervention support robot equipped with a sensing function: Experimental verification

引用

Asian Journal of Neurosurgery 2022年第2期16卷 363-366页

作者： Shigeru Miyachi Yoshitaka Nagano Reo Kawaguchi Tomotaka Ohshima Hiroki Tadauchi Department of Neurological Surgery Aichi Medical University Nagakute Neuroendovascular Therapy Center Aichi Medical University Nagakute Department of Electronic Control and Robot Engineering Aichi University of Technology Gamagori Aichi Graduation School of System Engineering Aichi University of Technology Gamagori Aichi

来源：评论

学校读者我要写书评

暂无评论

MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis

arXiv

引用

arXiv 2024年

作者： Liu, Shuhong Deng, Tianchen Zhou, Heng Li, Liuzhuozheng Wang, Hongyu Wang, Danwei Li, Mingrui Department of Information Science and Technology Department of Complexity Science and Engineering The University of Tokyo Tokyo113-8654 Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Department of Mechanical Engineering Columbia University New York10027 United States School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Computer Science Dalian University of Technology Dalian116024 China

Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM, an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, our method ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems. © 2024, CC BY.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

An Object Reconstruction Method Based on Point Cloud with Range Camera 2021

An Object Reconstruction Method Based on Point Cloud with Ra...

引用

2nd International Conference on Computing and Data Science, CONF-CDS 2021

作者： Yan, Sunchao Yi, Jianjun Ding, Hongkai Wang, Danwei Zhao, Changchun Department of Mechanical Engineering East China University of Science and Technology Shanghai200237 China Intelligent Unmanned System Control Technology Joint Lab Shanghai201109 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Shanghai Aerospace Control Technology Institute Shanghai201109 China

ISBN: (纸本)9781450389570

We present an object reconstruction approach based on point cloud. To accurately estimate sensor pose, a combination of frame-to-frame registration and frame-to-model registration is used in our approach with integration to produce the model of reconstructed object. The global optimization used in the approach distributes residual registration errors through the sensor trajectory. Our results demonstrate that the approach is fast and robust to reconstruct objects with a consumer-grade range camera. © 2021 ACM.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Error-state Kalman Filtering with Linearized State Constraints

TechRxiv

引用

TechRxiv 2023年

作者： Do, Hoang Viet Jung, Jae Hyung Park, Chan Gook Song, Jin Woo The Intelligent Navigation and Control Systems Laboratory Department of Convergence Engineering for Intelligent Drone School of Intelligent Mechatronics Engineering Sejong University Seoul05006 Korea Republic of The Department of Aerospace Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of The Navigation and Electronic System Laboratory Department of Aerospace Engineering Institute of Advanced Aerospace Technology Seoul National University Seoul08826 Korea Republic of

In recent years, the error-state Kalman filter (ErKF) has been extensively employed across various applications, including but not limited to robotics, aerospace, and localization. However, incorporating constraints into the ErKF framework when state constraint is necessary has remained a challenging task due to its intrinsic properties. This paper explores all possible ways to achieve this goal in the context of the estimate projection method. In particular, the constraint can be enforced before or after the ErKF’s correction step. We approach the problem from a mathematical perspective by deriving analytical solutions and discussing their statistical properties. We prove that the two mentioned methods are statistically identical for a linear system with linear constraints. Conversely, the filter’s behavior remains uncertain in the presence of linearized constraints. However, we provide a special case of the nonlinear constraint, wherein the results of the linear case remain valid. To support our theorem and verify the filter’s performance when the assumptions are invalidated, we present two Monte Carlo simulations under the increasing initialization error and the constraint’s incompleteness. The simulation results clearly confirm our insights and lead to the conclusion that constraining the error-state after the correction may offer superior outcomes compared to its competitor. © 2023, CC BY.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Towards ISAC-Empowered Vehicular Networks: Framework, Advances, and Opportunities

arXiv

引用

arXiv 2023年

作者： Du, Zhen Liu, Fan Li, Yunxin Yuan, Weijie Cui, Yuanhao Zhang, Zenghui Masouros, Christos Ai, Bo School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Electronic and Electrical Engineering University College London LondonWC1E 7JE United Kingdom State Key Lab of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China

Connected and autonomous vehicle (CAV) networks face several challenges, such as low throughput, high latency, and poor localization accuracy. These challenges severely impede the implementation of CAV networks for immersive metaverse applications and driving safety in future 6G wireless networks. To alleviate these issues, integrated sensing and communications (ISAC) is envisioned as a game-changing technology for future CAV networks. This article presents a comprehensive overview on the application of ISAC techniques in vehicle-to-infrastructure (V2I) networks. We cover the general system framework, representative advances, and a detailed case study on using the 5G New Radio (NR) waveform for sensing-assisted communications in V2I networks. Finally, we highlight open problems and opportunities in the field. Copyright © 2023, The Authors. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Analytical Models for QoT Estimations in Super-C and Super-C + L Bands Optical Transmission systems

Analytical Models for QoT Estimations in Super-C and Super-C...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Yan, Baoluo Sun, Yijun Zhou, Ziwen Liu, Hong Wang, Hongya Huan, Chen Zhao, Zhiyong Feng, Lipeng Zhang, Anxu Feng, Zhenhua Shi, Hu WDM System Department Wireline Product R&D Institute ZTE Corp. Beijing100029 China State Key Laboratory of Mobile Network and Mobile Multimedia Technology 518055 China School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China School of Optical and Electronic Information Wuhan National Laboratory for Optoelectronics Optics Valley Laboratory Huazhong University of Science and Technology Wuhan China China Telecom Research Institute Beijing102209 China

We propose a novel physical model-based QoT estimation with achieved OSNR estimation error 1.5 dB in primary paths and OSNR prediction error 1.76 dB in unestablished lightpaths for both super-C bands and super-C+L ban... 详细信息

ISBN: (纸本)9781957171258

关键词： Light transmission

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：