检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON MEdICAL ROBOTICS ANd BIONICS 2025年第1期7卷 242-253页

作者： Zhang, Shuai Zhao, Liang Huang, Shoudong Mazomenos, Evangelos B. Stoyanov, danail UCL UCL Hawkes Inst London WC1E 6BT England UCL Dept Comp Sci London WC1E 6BT England Univ Edinburgh Sch Informat Inst Percept Act & Behav Edinburgh EH8 9BT Scotland Univ Technol Sydney Robot Inst Fac Engn & Informat Technol Sydney NSW 2007 Australia UCL Dept Med Phys & Biomed Engn London WC1E 6BT England

This paper addresses the problem of reconstructing textured colon surface maps using a sequence of monocular colonoscopic images together with a 3d colon mesh model that has been segmented in CT colonography. The problem is formulated as a direct bundle adjustment (BA) problem which simultaneously optimizes all camera poses and the intensity of vertices on the pre-operative mesh model. This optimization is achieved by maximizing photometric consistency among multiple views of 2d images and the pre-operative 3d mesh model. The key properties of our proposed direct BA formulation involve eliminating the need for reference image specification, data association (feature extraction and matching), and image depth information. Thus, the proposed method is particularly suitable for scenarios where distinct features and image depth are not available, such as 2d colonoscopic images. Furthermore, we have proven that solving the proposed direct BA using the Gauss-Newton (GN) algorithm has the merit of optimizing camera poses only, which is equivalent to optimizing camera poses and the intensities of 3d vertices on the mesh together. Thus, a direct camera-only BA algorithm is proposed and used for 3d textured colon reconstruction from textureless 2d colonoscopic images. Validations using simulation, phantom, and in-vivo datasets are performed to demonstrate the accuracy and feasibility of the proposed algorithm.

关键词： Colon Three-dimensional displays image reconstruction Cameras Surface reconstruction Simultaneous localization and mapping Solid modeling Colonoscopy Shape image segmentation 3d reconstruction camera-only direct bundle adjustment SLAM

来源：评论

学校读者我要写书评

暂无评论

FPGA acceleration of secret sharing for 3d data cubes

引用

JOURNAL OF REAL-TIME image processing 2023年第4期20卷 82页

作者： Wu, Zi-Ming Liu, Tao Yan, Bin Pan, Jeng-Shyang Yang, Hong-Mei Shandong Univ Sci & Technol Coll Elect & Informat Engn Qingdao 266590 Shandong Peoples R China

Secret sharing can protect the security of important secret information in the network environment. However, the computational complexity and processing delay increase drastically when the secret information contains large amounts of data, such as three-dimensional (3d) data cubes. To improve the efficiency of secret sharing on 3d data cubes, this paper proposes a hardware architecture to accelerate the generation of shares and reconstruction of the secret. The proposed hardware architecture parallelizes the secret sharing process and optimizes on this basis to save large amounts of circuit resources. Simulation results show that this architecture performs secret sharing more than ten times faster than the software implementation. This study enables the secret sharing of 3d data cubes, which protect large amounts of data information throughout the process and allows complete reconstruction of 3d data cubes. To be able to handle secrets without decoding them, we then extend the hardware architecture to the four basic processes of multi-party computation, demonstrating the feasibility of the structure and providing preliminary research tools for the effective implementation of multi-party computation.

关键词： Parallel processing 3d data cubes Secret sharing FPGA Multi-party computation

来源：评论

学校读者我要写书评

暂无评论

iBA: Backdoor Attack on 3d Point Cloud via Reconstructing Itself

引用

IEEE TRANSACTIONS ON information FORENSICS ANd SECURITY 2024年 19卷 7994-8008页

作者： Bian, Yuhao Tian, Shengjing Liu, Xiuping Dalian Univ Technol Sch Math Sci Dalian 116024 Liaoning Peoples R China China Univ Min & Technol Sch Econ & Management Xuzhou 221116 Jiangsu Peoples R China

The widespread deployment of deep neural networks (dNNs) for 3d point cloud processing contrasts sharply with their vulnerability to security breaches, particularly backdoor attacks. Studying these attacks is crucial for raising security awareness and mitigating potential risks. However, the irregularity of 3d data and the heterogeneity of 3d dNNs pose unique challenges. Existing methods frequently fail against basic point cloud preprocessing or require intricate manual design. Exploring simple, imperceptible, effective, and difficult-to-defend triggers in 3d point clouds remains challenging. To address this issue, we propose iBA, a novel solution utilizing a folding-based auto-encoder (AE). By leveraging united reconstruction losses, iBA enhances both effectiveness and imperceptibility. Its data-driven nature eliminates the need for complex manual design, while the AE core imparts significant nonlinearity and sample specificity to the trigger, rendering traditional preprocessing techniques ineffective. Additionally, a trigger smoothing module based on spherical harmonic transformation (SHT) allows for controllable intensity. We also discuss potential countermeasures and the possibility of physical deployment for iBA as an extensive reference. Both quantitative and qualitative results demonstrate the effectiveness of our method, achieving state-of-the-art attack success rates (ASR) across a variety of victim models, even with defensive measures in place. iBA's imperceptibility is validated with multiple metrics as well.

关键词： Point cloud compression Three-dimensional displays image reconstruction Solid modeling Smoothing methods Manuals Training Backdoor attack 3d point cloud shape classification

来源：评论

学校读者我要写书评

暂无评论

2-d/3-d Medical image Registration Based on Feature-Point Matching

引用

IEEE TRANSACTIONS ON INSTRUMENTATION ANd MEASUREMENT 2024年 73卷

作者： Si, Shengyuan Li, Zheng Lin, Ze Xu, Xian Zhang, Yudong Xie, Shipeng Nanjing Univ Posts & Telecommun Sch Commun & Informat Engn Nanjing 210003 Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing 210096 Jiangsu Peoples R China

Two-dimensional/3-d medical image registration has a wide range of applications in intraoperative image-guided navigation, which can not only assist surgeons in accurately locating lesions but also serve as a key link for surgical robots to locate the surgical site. current methods for 2-d/3-d spine image registration are susceptible to getting stuck in local optimization, struggling to extract gradient information from noisy real data, and exhibiting slow processing speeds. Recently, deep learning methods have suffered from insufficient training data, poor generalization performance, and a tendency to produce incorrect solutions. We propose an optimized model that significantly improves the speed and accuracy of 2-d/3-d registration by deeply integrating a feature-point matching network. This network demonstrates exceptional robustness in processing high-noise imagery and is adept at coarse registration, providing the initial solution for the optimized model and thereby abbreviating the time required for coarse registration. It also facilitates updates of parameter location modules within the optimized model, diminishing the overall computational demand. Additionally, by harnessing grayscale and spinal feature information, we formulate an objective function enriched with a feature-point similarity metric to govern the descent trajectory, culminating in heightened precision and expedited convergence. Our empirical findings indicate that this method achieves a mean accuracy of 0.2550 mm on real data, substantiating the efficacy of our approach.

关键词： Feature extraction Accuracy X-rays Linear programming Three-dimensional displays Telecommunications Surgery image registration deep learning data models 2-d/3-d registration digital reconstruction radiography (dRR) feature-point matching network similarity measurement spine image registration

来源：评论

学校读者我要写书评

暂无评论

High-quality and efficient phase-only hologram generation method based on complex amplitude constrained Gerchberg-Saxton algorithm☆

引用

displays 2025年 87卷

作者： Hou, Ye-Hao Li, Zhao-Song Zheng, Yi-Wei Huang, Qian Li, Yi-Long Wang, di Wang, Qiong-Hua Beihang Univ Sch Instrumentat & Optoelect Engn Beijing 100191 Peoples R China

The holographic display garners widespread attention for its ability to provide vivid and realistic 3d visuals. The Gerchberg-Saxton (GS) algorithm has played a significant role in computer-generated holography for many years. However, the conventional GS algorithm cannot meet the requirements of holographic display for highquality and realistic visual effects. In this paper, a phase-only hologram generation method is proposed based on the complex amplitude constrained GS (CAC-GS) algorithm. In the proposed method, all information of the 3d scene is precalculated as a complex amplitude field at a target plane, and then the CAC-GS algorithm is used to reconstruct the target complex amplitude field and generate the hologram. The proposed method constrains both amplitude and phase on a target plane, thus significantly improving the image quality and efficiency of the hologram generation. Compared with the conventional GS algorithm, the holographic image quality of the proposed method is improved by approximately 50 %, and the calculation time is reduced by 97.27 %. This novel algorithm holds great promise for a wide range of applications including AR and VR.

关键词： Holographic display Gerchberg-Saxton algorithm 3d display

来源：评论

学校读者我要写书评

暂无评论

Plain-PCQA: No-Reference Point Cloud Quality Assessment by Analysis of Plain Visual and Geometrical Components

引用

IEEE TRANSACTIONS ON CIRCUITS ANd SYSTEMS FOR VIdEO TECHNOLOGY 2024年第7期34卷 6207-6223页

作者： Chai, Xiongli Shao, Feng Mu, Baoyang Chen, Hangwei Jiang, Qiuping Ho, Yo-Sung Ningbo Univ Fac Informat Sci & Engn Ningbo 315211 Peoples R China Gwangju Inst Sci & Technol GIST Sch Informat & Commun Gwangju 61005 South Korea

In reviewing the research progress in Point Cloud Quality Assessment (PCQA), two main pathways have emerged, i.e., 2d projections and 3d point descriptors. The former primarily focuses on visual information, while the latter concentrates on crucial geometrical information in three-dimensional space. However, the current studies lack a thorough investigation of the impact of visual components and seldom pay special attention to plane-point fusion strategies. To comprehensively represent features and effectively tackle various types of impairments, we propose an end-to-end learning paradigm, only considering plain visual and geometrical factors called Plain-PCQA, for quantitatively evaluating objective metrics of 3d dense point clouds associated with human perception. Firstly, we explore a sophisticated preprocessing technique. The entire point clouds are packaged into six projections by moving virtual cameras, which can conveniently increase the visual samples during the training stage. Given the high resolution of the projected image, we have opted for a relatively lightweight network, namely ResNet-18, as the backbone to enable higher resolution input data. Five cropped patches from the projected image are collectively fed into this network. In light of the presence of some invalid information in the projections, a mask weight is devised to calculate the significance of each patch based on its effective informational content. Secondly, dual neural networks, comprising of a No-Reference (NR) branch and a degraded-Reference (dR) branch, are designed with fundamental visual components to provide quantitative quality metrics. Specifically, the NR branch utilizes the feature output of each block in the Vision Transformer (ViT) model to obtain long-range low-level and high-level visual NR quality. The dR branch employs KLT (Karhunen-Lo & egrave;ve Transform) to acquire the principal component information of an image as the macro-structural image, and then feeds the diffe

关键词： Visualization Point cloud compression Feature extraction Three-dimensional displays distortion Quality assessment Encoding No reference point cloud quality assessment deep neural network visual and geometrical components degraded-reference information plane-point interaction transformer

来源：评论

学校读者我要写书评

暂无评论

Joint Segmentation of FAZ and RVs in OCTA images With Auxiliary 3-d image Projection Learning

引用

IEEE TRANSACTIONS ON INSTRUMENTATION ANd MEASUREMENT 2025年 74卷

作者： Jiang, Shuai Hu, Kai Zhang, Yuan Gao, Xieping Xiangtan Univ Key Lab Intelligent Comp & Informat Proc Minist Educ Xiangtan 411105 Peoples R China Hunan Normal Univ Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha 410081 Peoples R China

In the field of ophthalmic clinical practice, the quantitative and qualitative analyses of the foveal avascular zone (FAZ) and retinal vessels (RVs) in optical coherence tomography angiography (OCTA) images hold significant importance for assisting the diagnosis and analysis of eye diseases. However, the segmentation of FAZ and RV is typically based on 2-d images and is naturally separated. In this article, we propose a joint segmentation framework called PL-Joint-Seg, which incorporates 3-d image projection learning (PL) and forms a dual-path structure: 1) in the 3-d image projection path, volume features are extracted using an image projection network with an encoder- decoder-like structure and 2) in the 2-d image segmentation path, 3-d projection features are fused with 2-d encoding features to establish consistency and complementarity (CsCp) between features of different dimensions, leveraging both 3-d structural information and 2-d spatial information for joint segmentation. Furthermore, feature alignment decoding blocks and a multiscale soft fusion module (MSFM) are further inserted into the 2-d image segmentation path to adapt to the differences in the morphological characteristics of FAZ and RV. Finally, we evaluate our method using the publicly available OCTA-500 dataset. The proposed PL-Joint-Seg achieves dice scores of 0.9110/0.8982 and 0.9848/0.9165 for FAZ/RV segmentation on the OCTA_6M and OCTA_3M datasets, respectively, which demonstrate that adding a 3-d projection path plays an important auxiliary role in guiding 2-d image segmentation, while PL-Joint-Seg exhibits good performance in noise robustness and computational efficiency.

关键词： image segmentation Three-dimensional displays Feature extraction data mining Shape Biomarkers Fractals Accuracy Solid modeling Retinal vessels Foveal avascular zone (FAZ) image projection network joint segmentation optical coherence tomography angiography (OCTA) retinal vessel (RV)

来源：评论

学校读者我要写书评

暂无评论

dual convolutional neural network for aberration pre-correction and image quality enhancement in integral imaging display

引用

OPTICS EXPRESS 2023年第21期31卷 34609-34625页

作者： Cao, Shuo Ma, Haowen Li, Chao Zhou, Ruyi Sun, Yutong Li, Jingnan Liu, Juan Beijing Inst Technol Sch Opt & Photon Beijing Engn Res Ctr Mixed Real & Adv Display MoEKey Lab Photoelect Imaging Technol & Syst Beijing 100081 Peoples R China

This paper proposes a method that utilizes a dual neural network model to address the challenges posed by aberration in the integral imaging microlens array (MLA) and the degradation of 3d image quality. The approach involves a cascaded dual convolutional neural network (CNN) model designed to handle aberration pre-correction and image quality restoration tasks. By training these models end-to-end, the MLA aberration is corrected effectively and the image quality of integral imaging is enhanced. The feasibility of the proposed method is validated through simulations and optical experiments, using an optimized, high-quality pre-corrected element image array (EIA) as the image source for 3d display. The proposed method achieves high-quality integral imaging 3d display by alleviating the contradiction between MLA aberration and 3d image resolution reduction caused by system noise without introducing additional complexity to the display system.(c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Holographic displays image enhancement image quality image resolution Medical imaging Three dimensional image processing

来源：评论

学校读者我要写书评

暂无评论

Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments

引用

IEEE ACCESS 2024年 12卷 96911-96923页

作者： Ahn, Jeonghyeon Ha, Jungho Son, Jaemin Han, Junghyun Korea Univ Dept Comp Sci & Engn Seoul 02841 South Korea

currently, it is a norm to design a semiconductor fab using building information models (BIMs), which refer to a digital representation of a building's physical and functional characteristics. The comprehensive data provided by BIMs include 3d geometric models. This paper presents a 3d model-based camera tracking method, which is targeted at navigating a fab's wide indoor environment. The key observation made in designing the method is that there are a number of fixed objects in such an indoor environment. The columns are the representative among them. Our method extracts the columns from the input image and matches them to their BIMs to estimate the camera pose. The estimation accuracy is significantly increased by adopting an instance segmentation network. It is trained with a dataset, which is extracted from the target indoor environment and processed by our own data engine. The test results show that our tracking method is drift-free, accurate and robust. We envision that it can be used in many applications such as AR-based visual inspection.

关键词： image edge detection Cameras Inspection Indoor environment Visualization Three-dimensional displays Augmented reality Building information management building information modeling camera tracking instance segmentation

来源：评论

学校读者我要写书评

暂无评论

Mutual information driven Equivariant Contrastive Learning for 3d Action Representation Learning

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 1883-1897页

作者： Lin, Lilang Zhang, Jiahang Liu, Jiaying Peking Univ Wangxuan Inst Comp Technol Beijing 100080 Peoples R China

Self-supervised contrastive learning has proven to be successful for skeleton-based action recognition. For contrastive learning, data transformations are found to fundamentally affect the learned representation quality. However, traditional invariant contrastive learning is detrimental to the performance on the downstream task if the transformation carries important information for the task. In this sense, it limits the application of many data transformations in the current contrastive learning pipeline. To address these issues, we propose to utilize equivariant contrastive learning, which extends invariant contrastive learning and preserves important information. By integrating equivariant and invariant contrastive learning into a hybrid approach, the model can better leverage the motion patterns exposed by data transformations and obtain a more discriminative representation space. Specifically, a self-distillation loss is first proposed for transformed data of different intensities to fully utilize invariant transformations, especially strong invariant transformations. For equivariant transformations, we explore the potential of skeleton mixing and temporal shuffling for equivariant contrastive learning. Meanwhile, we analyze the impacts of different data transformations on the feature space in terms of two novel metrics proposed in this paper, namely, consistency and diversity. In particular, we demonstrate that equivariant learning boosts performance by alleviating the dimensional collapse problem. Experimental results on several benchmarks indicate that our method outperforms existing state-of-the-art methods.

关键词： Self-supervised learning Skeleton Task analysis Representation learning data models Three-dimensional displays Convolutional neural networks skeleton-based action recognition contrastive learning

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：