检索结果-内蒙古大学图书馆

LFT-Net: Local Feature Transformer Network for Point Clouds Analysis

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第2期24卷 2158-2168页

作者： Gao, Yongbin Liu, Xuebing Li, Jun Fang, Zhijun Jiang, Xiaoyan Huq, Kazi Mohammed Saidul Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201620 Peoples R China Guangzhou Univ Sch Elect & Commun Engn Res Ctr Intelligent Commun Engn Guangzhou 510006 Peoples R China Univ South Wales Fac Comp Engn & Sci Pontypridd CF37 1DL M Glam Wales

6G network enables the rapid connection of autonomous vehicles, the generated internet of vehicles establishes a large-scale point cloud, which requires automatic point cloud analysis to build an intelligent transportation system in terms of the 3d object detection and segmentation. Recently, a great variety of deep convolution networks have been proposed for 3d data analysis, making significant progress in the application of deep learning in 3d computer vision. Inspired by the application of transformer network in 2d computer visual tasks, and in order to increase the expression ability of local fine-grained features, we propose an effective local feature transformer network to learn local feature information and correlations between point clouds. Our network is adaptive to the arrangement of set elements through transformer module, so it is suitable for the feature extraction of local point clouds. In addition, experimental results demonstrate that our LFT-network outperforms the state-of-the-art in 3d model classification tasks on ModelNet40 dataset and segmentation tasks on S3dIS dataset.

关键词： Point cloud compression Transformers Three-dimensional displays Task analysis Feature extraction Convolution Semantics 6G point cloud 3d computer vision transfomer classification segmentation

来源：评论

学校读者我要写书评

暂无评论

deep Bingham Networks: dealing with Uncertainty and Ambiguity in Pose Estimation

引用

INTERNATIONAL JOURNAL OF computer vision 2022年第7期130卷 1627-1654页

作者： deng, Haowen Bui, Mai Navab, Nassir Guibas, Leonidas Ilic, Slobodan Birdal, Tolga Tech Univ Munich Informat Munich Germany Corp Technol Siemens AG Munich Germany Stanford Univ Dept Comp Sci Stanford CA 94305 USA

In this work, we introduce deep Bingham Networks (dBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life applications concerning 3d data. While existing works strive to find a single solution to the pose estimation problem, we make peace with the ambiguities causing high uncertainty around which solutions to identify as the best. Instead, we report a family of poses which capture the nature of the solution space. dBN extends the state of the art direct pose regression networks by (i) a multi-hypotheses prediction head which can yield different distribution modes;and (ii) novel loss functions that benefit from Bingham distributions on rotations. This way, dBN can work both in unambiguous cases providing uncertainty information, and in ambiguous scenes where an uncertainty per mode is desired. On a technical front, our network regresses continuous Bingham mixture models and is applicable to both 2d data such as images and to 3d data such as point clouds. We proposed new training strategies so as to avoid mode or posterior collapse during training and to improve numerical stability. Our methods are thoroughly tested on two different applications exploiting two different modalities: (i) 6d camera relocalization from images;and (ii) object pose estimation from 3d point clouds, demonstrating decent advantages over the state of the art. For the former we contributed our own dataset composed of five indoor scenes where it is unavoidable to capture images corresponding to views that are hard to uniquely identify. For the latter we achieve the top results especially for symmetric objects of ModelNet dataset (Wu et al., in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1912-1920, 2015). The code and dataset accompanying this paper is provided under https://***.

关键词： 3d computer vision Point clouds Camera relocalization 6d Camera pose Object pose Rotation Bingham distribution Posterior distribution Ambiguity Uncertainty Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Geometric mesh corner detection using triangle principle

引用

ELECTRONICS LETTERS 2017年第20期53卷 1354-1355页

作者： Lin, Xinyu Zhu, Ce Zhang, Qian Liu, Yipeng Univ Elect Sci & Technol China UESTC Sch Elect Engn Ctr Robot Chengdu Sichuan Peoples R China

As one of the most significant local features, corners play a fundamental role in 3d computer vision and computer graphics. Two novel corner detection algorithms for 3d mesh data are presented in this Letter, in which the authors examine the geometric properties of the surface in multi-scale space and utilise simple triangle principle to detect mesh corners. Numerical experiments show that our corner detectors outperform six state-of-the-art methods.

关键词： computer graphics mesh generation computational geometry computer vision edge detection geometric mesh corner detection triangle principle local features 3d computer vision computer graphics 3d mesh data geometric properties multiscale space

来源：评论

学校读者我要写书评

暂无评论

A Kinect-based system for cognitive rehabilitation exercises monitoring

引用

computer METHOdS ANd PROGRAMS IN BIOMEdICINE 2014年第2期113卷 620-631页

作者： Gonzalez-Ortega, d. diaz-Pernas, F. J. Martinez-Zarzuela, M. Anton-Rodriguez, M. Univ Valladolid Telecommun Engn Sch Dept Signal Theory Commun & Telemat Engn E-47011 Valladolid Spain

In this paper, a 3d computer vision system for cognitive assessment and rehabilitation based on the Kinect device is presented. It is intended for individuals with body scheme dysfunctions and left-right confusion. The system processes depth information to overcome the shortcomings of a previously presented 2d vision system for the same application. It achieves left and right-hand tracking, and face and facial feature detection (eye, nose, and ears) detection. The system is easily implemented with a consumer-grade computer and an affordable Kinect device and is robust to drastic background and illumination changes. The system was tested and achieved a successful monitoring percentage of 96.28%. The automation of the human body parts motion monitoring, its analysis in relation to the psychomotor exercise indicated to the patient, and the storage of the result of the realization of a set of exercises free the rehabilitation experts of doing such demanding tasks. The vision-based system is potentially applicable to other tasks with minor changes. (C) 2013 Elsevier Ireland Ltd. All rights reserved.

关键词： Human-computer interaction Cognitive rehabilitation Human body parts detection and tracking 3d computer vision Kinect device

来源：评论

学校读者我要写书评

暂无评论

PointCutMix: Regularization strategy for point cloud classification

引用

NEUROCOMPUTING 2022年 505卷 58-67页

作者： Zhang, Jinlai Chen, Lyujie Ouyang, Bo Liu, Binbin Zhu, Jihong Chen, Yujin Meng, Yanmei Wu, danfeng Guangxi Univ Coll Mech Engn Naning 530004 Guangxi Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100000 Peoples R China Tsinghua Univ Dept Precis Instrument Beijing 100000 Peoples R China

As 3d point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation method for the point cloud data to alleviate those problems. It finds the one-to-one correspondence between two point clouds and generates new training data by replacing the points in one sample with their corresponding pairs. Two replacement strategies are proposed to adapt to the accuracy or robustness requirement for different tasks, one of which is to randomly select all replacing points while the other one is to select k nearest neighbors of a single random point. Both strategies consistently and significantly improve the performance of various models on point cloud clas-sification problems. By introducing the saliency maps to guide the selection of replacing points, the per-formance further improves. Since our method persists local semantic information of the points, we also at the first time extend MSdA for the point cloud segmentation problem. Moreover, PointCutMix is vali-dated to enhance the model's robustness. When using as a defense method, our method outperforms the state-of-the-art defense algorithms. The code is available at:https://***/cuge1995/ PointCutMix.(c) 2022 Elsevier B.V. All rights reserved.

关键词： 3d computer vision Point cloud deep learning data augmentation

来源：评论

学校读者我要写书评

暂无评论

Improved estimation of defocus blur and spatial shifts in spatial domain:: a homotopy-based approach

引用

PATTERN RECOGNITION 2003年第9期36卷 2105-2125页

作者： deschênes, F Ziou, d Fuchs, P Univ Sherbrooke Dept Math & Informat Quebec City PQ J1K 2R1 Canada Ecole Mines Paris Ctr Robot F-75272 Paris 06 France

This paper presents a homotopy-based algorithm for the recovery of depth cues in the spatial domain. The algorithm specifically deals with defocus blur and spatial shifts, that is 2d motion, stereo disparities and/or zooming disparities. These cues are estimated from two images of the same scene acquired by a camera evolving in time and/or space. We show that they can be simultaneously computed by resolving a system of equations using a homotopy method. The proposed algorithm is tested using synthetic and real images. The results confirm that the use of a homotopy method leads to a dense and accurate estimation of depth cues. This approach has been integrated into an application for relief estimation from remotely sensed images. (C) 2003 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

关键词： 3d computer vision unified model simultaneous parameter estimation defocus blur disparity motion zoom homotopy method generalized moment expansion

来源：评论

学校读者我要写书评

暂无评论

defining a feature-level digital twin process model by extracting machining features from MBd models for intelligent process planning

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2024年第5期36卷 3227-3248页

作者： Li, Jingjing Zhou, Guanghui Zhang, Chao Hu, Junsheng Chang, Fengtian Matta, Andrea Xi An Jiao Tong Univ Sch Mech Engn 28 Xianning West Rd Xian 710049 Peoples R China Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian Peoples R China Changan Univ Sch Construct Machinery Xian 710064 Peoples R China Politecn Milan Dept Mech Engn Milan Italy

The booming development of emerging technologies and their integration in process planning provide new opportunities for solving the problems in traditional trial-and-error process planning. Combining digital twin with 3d computer vision, this paper defines a novel feature-level digital twin process model (FL-dTPM) by extracting machining features from model-based definition models. Firstly, a multi-dimensional FL-dTPM framework is defined by fusing on-site data, quality information, and process knowledge, where the synergistic mechanism of its virtual and physical processes is revealed. Then, 3d computer vision-enabled machining features extraction method is embedded into the FL-dTPM framework to support the reuse of process knowledge, which involves the procedures of data pre-processing, semantic segmentation, and instance segmentation. Finally, the effectiveness of the proposed features extraction method is verified and the application of FL-dTPM in machining process is presented. Oriented to the impeller process planning, a prototype of FL-dTPM is constructed to explore the potential application scenarios of the proposed method in intelligent process planning, which could provide insights into the industrial implementation of FL-dTPM for aerospace manufacturing enterprises.

关键词： digital twin digital twin process model 3d computer vision Machining features Semantic segmentation Instance segmentation

来源：评论

学校读者我要写书评

暂无评论

dualMLP: a two-stream fusion model for 3d point cloud classification

引用

VISUAL computer 2024年第8期40卷 5435-5449页

作者： Paul, Sneha Patterson, Zachary Bouguila, Nizar Concordia Univ Concordia Inst Informat Syst Engn CIISE Montreal PQ Canada

In this paper, we present dualMLP, a novel 3d model that introduces the idea of a two-stream network for existing 3d models to handle the trade-off between the number of points and the computational overhead. Existing works on point clouds use a small subset of points sampled from the entire 3d object as input. Although increasing the number of input points can enhance scene understanding, it also incurs a higher computational cost for existing networks. To tackle this challenge, we propose a novel architecture called dualMLP, which effectively mitigates the linear increase in computational expense as the number of input points grows. While we evaluate this concept on PointMLP and demonstrate its effectiveness, the idea can be applied to other existing models with minimal adjustments. dualMLP consists of two branches: denseNet and SparseNet. The SparseNet, a relatively larger network, samples a small number of points from the complete point cloud, while the denseNet, a lightweight network, takes in a larger number of points as input. Extensive experiments on the ScanObjectNN and ModelNet40 datasets demonstrate the effectiveness of the proposed model, achieving a 1.00% and 0.81% improvement over PointMLP for ScanObjectNN and ModelNet40 while being computationally efficient than the original PointMLP. To ensure the reproducibility of our experimental results, the code for this work is publicly available at https://***/snehaputul/dualMLP.

关键词： Point cloud classification 3d computer vision Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Early and non-intrusive lameness detection in dairy cows using 3-dimensional video

引用

BIOSYSTEMS ENGINEERING 2017年 153卷 63-69页

作者： Jabbar, K. Abdul Hansen, Mark F. Smith, Melvyn L. Smith, Lyndon N. Univ West England Bristol Robot Lab Ctr Machine Vis Coldharbour Lane Bristol BS16 1QY Avon England

Lameness is a major issue in dairy herds and its early and automated detection offers animal welfare benefits together with potentially high commercial savings for farmers. Current advancements in automated detection have not achieved a sensitive measure for classifying early lameness. A novel proxy for lameness using 3-dimensional (3d) depth video data to analyse the animal's gait asymmetry is introduced. This dynamic proxy is derived from the height variations in the hip joint during walking. The video capture setup is completely covert and it facilitates an automated process. The animals are recorded using an overhead 3d depth camera as they walk freely in single file after the milking session. A 3d depth image of the cow's body is used to automatically track key regions such as the hooks and the spine. The height movements are calculated from these regions to form the locomotion signals of this study, which are analysed using a Hilbert transform. Our results using a 1-5 locomotion scoring (LS) system on 22 Holstein Friesian dairy cows, a threshold could be identified between LS 1 and 2 (and above). This boundary is important as it represents the earliest point in time at which a cow is considered lame, and its early detection could improve intervention outcome thereby minimising losses and reducing animal suffering. Using a linear Support Vector Machine (SVM) binary classification model, the threshold achieved an accuracy of 95.7% with a 100% sensitivity (detecting lame cows) and 75% specificity (detecting non-lame cows). (c) 2016 IAgrE. Published by Elsevier Ltd. All rights reserved.

关键词： 3d computer vision Early lameness detection Gait asymmetry Locomotion analysis

来源：评论

学校读者我要写书评

暂无评论

A novel computer vision and point cloud-based approach for accurate structural analysis of a tall irregular timber structure

引用

STRUCTURES 2024年 70卷

作者： Xie, Fan Pan, Xiao Yang, T. Y. Ernewein, Ben Li, Minghao Robinson, dave Univ British Columbia Dept Civil Engn Vancouver BC Canada Hong Kong Univ Sci & Technol Dept Civil & Environm Engn Clear Water Bay Hong Kong Peoples R China Univ British Columbia Dept Wood Sci Vancouver BC Canada Univ British Columbia Dept Expt Med Vancouver BC Canada

Wood material has been widely used in critical heritage structures such as pagodas, totem poles, and large-scale sculptures. Conducting rigorous structural analysis is crucial to protect these structures in high-seismic regions. Typically, these types of structures are modeled using an equivalent finite element (FE) model which used simple cylinder with a constant cross section equal to the average of the top and bottom cross section. However, simplified equivalent FE models may not accurately consider the irregularities and complexities of these structures. In this paper, advanced computer vision and point cloud techniques were adopted to accurately and rapidly construct a FE model of a 30-meter irregular timber sculpture. This was achieved using video scans, computer vision-aided 3d reconstruction, point cloud processing, and mesh to solid element conversion. The refined FE model was used to conduct capacity check, mesh sensitivity study, pushover analysis, and response spectrum analysis. The results of the refined FE model were compared to an equivalent FE model. The results show: 1) the proposed numerical modeling methodology for structural analysis can efficiently and accurately measure the dimension of the irregular sculpture up to 98.2 % accuracy;2) the lateral stiffnesses of the 30-meter irregular sculpture vary significantly (up to 42.6 %) from one direction to the other;3) the equivalent FE model overestimated the shear and moment capacities by 20.6 % and 13.2 %, respectively;4) on average, the equivalent FE model overestimated the shear and moment demands by 8.9 % and 5.5 %, respectively. Overall, the proposed application has demonstrated a fast, economical and accurate method to conduct seismic evaluation and design for irregular structures.

关键词： 3d computer vision 3d point cloud processing FE modelling Timber structures Seismic performance evaluation

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：