检索结果-内蒙古大学图书馆

Kolmogorov-Arnold pointnet: Deep learning for prediction of fluid fields on irregular geometries

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 439卷

作者： Kashefi, Ali Stanford Univ Dept Civil & Environm Engn Stanford CA 94305 USA

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multilayer Perceptrons (MLPs) in deep learning. KANs have already been integrated into various architectures, such as convolutional neural networks, graph neural networks, and transformers, and their potential has been assessed for predicting physical quantities. However, the combination of KANs with point-cloud-based neural networks (e.g., pointnet) for computational physics has not yet been explored. To address this, we present Kolmogorov-Arnold pointnet (KApointnet) as a novel supervised deep learning framework for the prediction of incompressible steady-state fluid flow fields in irregular domains, where the predicted fields are a function of the geometry of the domains. In KA-pointnet, we implement shared KANs in the segmentation branch of the pointnet architecture. We utilize Jacobi polynomials to construct shared KANs. As a benchmark test case, we consider incompressible laminar steady-state flow over a cylinder, where the geometry of its cross-section varies over the data set. We investigate the performance of Jacobi polynomials with different degrees as well as special cases of Jacobi polynomials such as Legendre polynomials, Chebyshev polynomials of the first and second kinds, and Gegenbauer polynomials, in terms of the computational cost of training and accuracy of prediction of the test set. Furthermore, we examine the robustness of KA-pointnet in the presence of noisy training data and missing points in the point clouds of the test set. Additionally, we compare the performance of pointnet with shared KANs (i.e., KA-pointnet) and pointnet with shared MLPs. It is observed that when the number of trainable parameters is approximately equal, pointnet with shared KANs (i.e., KA-pointnet) outperforms pointnet with shared MLPs. Moreover, KApointnet predicts the pressure and velocity distributions along the surface of cylinders more accurately, resulting in more precise com

关键词： pointnet Kolmogorov-Arnold networks Irregular geometries Steady-state incompressible flow

来源：评论

学校读者我要写书评

暂无评论

Improved pointnet with accuracy and efficiency trade-off for online detection of defects in laser processing

引用

OPTICS AND LASERS IN ENGINEERING 2025年 184卷

作者： Pan, Yangyi Yang, Fufei Peng, Weiping Liu, Quan Zhang, Chen Wuhan Univ Inst Technol Sci Wuhan 430072 Peoples R China Wuhan Univ Dong Fureng Inst Econ & Social Dev Wuhan 430072 Peoples R China Wuhan Qingchuan Univ Sch Mech & Elect Engn Wuhan 430204 Peoples R China Wuhan Univ Sch Power & Mech Engn Wuhan 430072 Peoples R China

Structural light vision sensing is widely applied in online detecting defects of laser processing due to their antiinterference ability for laser beams. However, the existing algorithms cannot extract the characteristics of weld defects with high precision. The computing cost of large-scale point cloud data is high. The balance between them is the main challenge to achieve online detection. To improve accuracy and reduce computation costs, this study uses point cloud data with depth information and proposes a point cloud segmentation method. It is a novelty method based on pointnet framework that has been verified for laser welding defect detection. Specifically, it used the pointnet framework as the backbone. It extracted enough local features of weld defects by multi-scale feature fusion, which concatenated features from different feature extraction layers to learn enough features to improve detection accuracy. The experiments were conducted on the real dataset of welds. The results showed its competitive performance in weld bead measurement and classification segmentation, and the accuracy of this method is 97.4 %. The proposed method improved mean intersection-over-union (mIoU) by 2.1 % compared with its backbone (pointnet), indicating a better segmentation accuracy. In addition, the proposed method improved detection speed compared with pointnet++. It can reach 60 frames per second, 7.5 times faster than pointnet++ and meet the online monitoring requirements. To conclude, the new detection method based on the improved pointnet with higher accuracy and faster speed of detection has a wide application prospect thanks to its novel model.

关键词： Point cloud segmentation pointnet Multiscale feature fusion Defects detection Laser welding

来源：评论

学校读者我要写书评

暂无评论

Classification of 3D shoe prints using the pointnet architecture: proof of concept investigation of binary classification of nike and adidas outsoles

引用

FORENSIC SCIENCE MEDICINE AND PATHOLOGY 2025年第1期21卷 219-228页

作者： Oguz, Ramazan Babacan, Hakki Halil Asicioglu, Faruk Uvet, Hueseyin Istanbul Gendarmerie Criminal Lab Informat Technol Invest Branch Directorate TR-34240 Istanbul Turkiye Istanbul Univ Cerrahpasa Inst Forens Sci & Legal Med TR-34500 Istanbul Turkiye Erzincan Binali Yildirim Univ Psychol TR-24002 Erzincan Turkiye Yildiz Tecn Univ Dept Mechatron Engn TR-34220 Istanbul Turkiye

Shoe prints are one of the most common types of evidence found at crime scenes, second only to fingerprints. However, studies involving modern approaches such as machine learning and deep learning for the detection and analysis of shoe prints are quite limited in this field. With advancements in technology, positive results have recently emerged for the detection of 2D shoe prints. However, few studies focusing on 3D shoe prints. This study aims to use deep learning methods, specifically the pointnet architecture, for binary classification applications of 3D shoe prints, utilizing two different shoe brands. A 3D dataset created from 160 pairs of shoes was employed for this research. This dataset comprises 797 images from the Adidas brand and 2445 images from the Nike brand. The dataset used in the study includes worn shoe prints. According to the results obtained, the training phase achieved an accuracy of 96%, and the validation phase achieved an accuracy of 93%. These study results are highly positive and indicate promising potential for classifying 3D shoe prints. This study is described as the first classification study conducted using a deep learning method specifically on 3D shoe prints. It provides proof of concept that deep learning research can be conducted on 3D shoeprints. While the developed binary classification of these 3D shoeprints may not fully meet current forensic needs, it will serve as a source of motivation for future research and for the creation of 3D datasets intended for forensic purposes.

关键词： Shoeprint Deep learning pointnet Forensic 3D classification Point cloud

来源：评论

学校读者我要写书评

暂无评论

pointnet-Based 3D Point Cloud Target Classification Fused ISS3D and FPFH 8th

PointNet-Based 3D Point Cloud Target Classification Fused IS...

引用

8th International Conference on Life System Modeling and Simulation, LSMS 2024 and 8th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024

作者： Gao, Zhicong Yi, Kaixiang Zhou, Wenju Chen, Yang Wang, Chao School of Mechatronical Engineering and Automation Shanghai Key Lab of Power Station Automation Technology Shanghai University Shanghai200072 China Shanghai Electric Automation Group CO. LTD Shanghai200023 China

ISBN: (纸本)9789819602933

In the field of point cloud classification using neural networks, the traditional pointnet neural network only focuses on single-point feature learning and ignores local information structure features, which makes the accuracy of point cloud classification low. In this paper, we propose IF-pointnet (pointnet of ISS3D and FPFH) point cloud classification network to fill this gap. Firstly IF-pointnet adds the module of ISS3D point cloud key point detection on top of pointnet, so as to better learn the local point cloud structure features. Then, the module of FPFH feature extraction is added to encode the features of the detected key points, which strengthens the connection between the point cloud localities and improves the classification accuracy. The experimental results show that IF-pointnet has higher classification accuracy and robustness on the ModelNet40 dataset. The results verify the effectiveness of the two added modules in point cloud classification and brings new ideas and methods to the field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： FPFH ISS3D Neural Network Point Cloud Classification pointnet

来源：评论

学校读者我要写书评

暂无评论

基于pointnet的钢板毛坯垛点云分割

引用

机电工程技术 2025年第1期54卷 152-156页

作者：林振杨福建三钢闽光股份有限公司福建三明365000

钢板毛坯垛拆垛工序中,钢板毛坯分层厚度的估计是推钢机准确且安全执行推钢动作的关键;当前不少企业此道生产工序仍主要靠操作员人工观察的方式估算钢板厚度及与传送辊道的相对高度,其估算不准易导致碰撞,造成输送设备损坏生产中断。提... 详细信息

钢板毛坯垛拆垛工序中,钢板毛坯分层厚度的估计是推钢机准确且安全执行推钢动作的关键;当前不少企业此道生产工序仍主要靠操作员人工观察的方式估算钢板厚度及与传送辊道的相对高度,其估算不准易导致碰撞,造成输送设备损坏生产中断。提出一种钢板毛坯垛智能分层方法,该方法结合现场工况环境采用激光雷达,对钢板毛坯垛进行三维点云成像,然后对采集的点云数据,用pointnet神经网络框架进行特征识别、分层分割与提取,最后对分割的不同层根据标定值,换算成真实厚度。根据现场实验结果表明,pointnet对钢板毛坯垛分割的识别率达到了87.4%,厚度估算误差低于1.2cm,根据钢厂钢板毛坯规格表(3种规格150、160、180cm)可以准确估计出钢板毛坯厚度的规格,识别速度15帧/s,满足现场工况要求。

关键词：钢板毛坯垛点云分割特征识别 pointnet

来源：评论

学校读者我要写书评

暂无评论

pointnet-Transformer Fusion Network for In-Cabin Occupancy Monitoring With mm-Wave Radar

引用

IEEE SENSORS JOURNAL 2024年第4期24卷 5370-5382页

作者： Xiao, Zhiqiang Ye, Kuntao Cui, Guolong Jiangxi Univ Sci & Technol Sch Sci Ganzhou 341000 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Due to the irregular distribution of 3-D point clouds and the random movement of the passengers, it is difficult to accurately and rapidly determine the passenger occupancy based on the multiple-input and multiple-output (MIMO) radar. In this study, we present a lightweight neural network, dubbed pointnet and transformer fusion neural network (PTFNet), that fuses the pointnet and transformer to quickly and accurately detect the occupancy of three rear seats and two footwells. PTFNet adapts an input transform block to encode the 3-D point cloud directly, which makes it more lightweight than conventional voxelization, heatmap, and pointnet based algorithms. Meanwhile, a cross-attention mechanism block inspired by transformer is employed to efficiently extract features from 3-D point clouds, resulting in an improvement in detection accuracy. An in-cabin occupancy monitoring system (OMS) is implemented in a real vehicle to obtain 3-D point cloud datasets, which are then used to evaluate the detection performance of PTFNet. Our datasets cover both the rear seat area and the footwell area. The footwell space is considered for the first time in the point cloud datasets. The experimental results demonstrate that PTFNet outperforms other popular approaches in terms of detection accuracy by at least 1.6%, while the consumption of memory and running time are reduced by at least 44% and 34%, respectively.

关键词： 3-D point cloud multiple-input and multiple-output (MIMO) millimeter-wave (mm-Wave) radar sensor passenger occupancy detection pointnet transformer

来源：评论

学校读者我要写书评

暂无评论

pointnet-based modeling of systematic distance deviations for improved TLS accuracy

引用

JOURNAL OF APPLIED GEODESY 2024年第4期18卷 613-628页

作者： Hartmann, Jan Ernst, Dominik Neumann, Ingo Alkhatib, Hamza Leibniz Univ Hannover Geodet Inst Hannover Germany

Terrestrial laser scanners (TLSs) have become indispensable for acquiring highly detailed and accurate 3D representations of the physical world. However, the acquired data is subject to systematic deviations in distance measurements due to external influences, such as distance and incidence angle. This research introduces a calibration approach by applying a deep learning model based on pointnet to predict and correct these systematic distance deviations, incorporating not only the XYZ coordinates but also additional features like intensity, incidence angle, and distances within a local neighbourhood radius of 5 cm. By predicting and subsequently correcting systematic distance deviations, the quality of TLS point clouds can be improved. Hence, our model is designed to complement and build upon the foundation of prior internal TLS calibration. A data set collected under controlled environmental conditions, containing various objects of different materials, served as the basis for training and validation the pointnet based model. In addition our analysis showcase the model's capability to accurately model systematic distance deviations, outperforming existing methods like gradient boosting trees by capturing the spatial relationships and dependencies within the data more effectively. By defining test data sets, excluded from the training process, we underscore the ongoing effectiveness of our model's distance measurement calibration, showcasing its ability to improve the accuracy of the TLS point cloud.

关键词： terrestrial laser scanning systematic distance deviation deep learning pointnet calibration

来源：评论

学校读者我要写书评

暂无评论

Methodology for Activity Unit Segmentation of Design 3D Models Using pointnet Deep Learning Technique

引用

KSCE JOURNAL OF CIVIL ENGINEERING 2024年第1期28卷 29-44页

作者： Lee, JaeHee Park, SangMi Kang, LeenSeok Gyeongsang Natl Univ Dept Civil Engn Jinju 52828 South Korea Korea Inst Civil Engn & Bldg Technol Dept Future & Smart Construct Res BIM Cluster Goyang 10223 South Korea Gyeongsang Natl Univ Engn Res Inst Dept Civil Engn Jinju 52828 South Korea

This paper discusses the challenge of using 3D models created during the design stage in the construction stage due to the need for segmentation or remodeling to incorporate activity concepts. To address this challenge, the paper proposes a methodology that uses the pointnet deep learning technique to automatically classify and segment design model elements into activity units for the construction stage while preserving attribute information. The authors introduce a module that utilize the bounding box concept to simplify the segmentation process after importing the 3D model into the 4D system used in the construction stage. This eliminates the need for separate CAD software and allows for direct segmentation into activity units within the 4D system and simultaneous simulation. The proposed methodology was applied to two real bridge projects and demonstrated increased 3D model reusability in the construction stage. The paper concludes that this approach can improve the usability of 3D models for construction projects.

关键词： Building information model 3D model segmentation pointnet Schedule management 4D simulation

来源：评论

学校读者我要写书评

暂无评论

Jitter Decomposition by pointnet-Based Dual-Dirac Model

引用

IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY 2022年第3期64卷 840-849页

作者： Ren, Nan Fu, Zaiming Zhou, Dandan Kong, Dexuan Liu, Hanglin Tian, Shulin Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611731 Peoples R China

Jitter is one of the main factors affecting the bit error rate, and jitter decomposition is a crucial tool with which to characterize jitter at a given BER. In this article, we address this problem based on pointnet and propose a pointnet-based dual-Dirac model (pointnet-DD), where its input is the two-dimensional point cloud formed by the coordinate of the jitter histogram. In particular, we develop a feature extractor, where the stride size of the one-dimensional convolution layer of pointnet is changed to better learn the local features, the corresponding variance and mean features hidden under the jitter histogram point cloud are extracted by global max pooling and global average pooling, respectively. Then, we introduce a dual-Dirac model in the network for jitter calculation to make the estimated deterministic jitter and random jitter more accurate. Consequently, the pointnet-DD can improve the mean absolute error of jitter decomposition. Finally, this approach is practically tested on the test circuits. Experimental results show that the performance, robustness, space, and time of the proposed method are better than other methods.

关键词： Jitter Feature extraction Histograms Point cloud compression Reactive power Data mining Convolution Dual-Dirac model global average pooling (GAP) global max pooling (GMP) jitter decomposition pointnet

来源：评论

学校读者我要写书评

暂无评论

Seabed Segmentation of Airborne Bathymetric Light Detection and Ranging Point Cloud Using Window-based Attention and Orthogonal Regularized pointnet

引用

SENSORS AND MATERIALS 2024年第9期36卷 3997页

作者： Song, Ahram Lee, Jaebin Kyungpook Natl Univ Dept Locat Based Informat Syst Sangju 37224 Gyeongsangbuk D South Korea Mokpo Natl Univ Dept Architectural Civil & Environm Engn Muan 58554 Jeonnam South Korea

Seabed segmentation from airborne bathymetric Light Detection and Ranging (LiDAR) point cloud data presents unique challenges, primarily due to variations in the z-axis resulting from differences in water depth and seabed topography. To address these complexities, we introduced an improved version of pointnet specifically designed for seabed segmentation using Airborne Bathymetric LiDAR (ABL) point cloud data. The proposed method integrates a window-based attention mechanism to capture spatial relationships in both horizontal and vertical dimensions while incorporating orthogonal regularization to preserve geometric integrity. The model's performance was assessed using various normalization methods and window sizes, demonstrating its effectiveness in accurately identifying seabed regions. Experimental results indicate that while the proposed network generally improves segmentation accuracy, its performance is sensitive to the choice of normalization and window parameters. This study represents a meaningful advancement in applying deep learning techniques to bathymetric LiDAR data, offering a robust framework for seabed segmentation.

关键词： airborne bathymetric LiDAR seabed segmentation pointnet window-based attention orthogonal regularization

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：