检索结果-内蒙古大学图书馆

Road crack detection network under noise based on feature pyramid structure with feature enhancement (road crack detection under noise)

引用

IET IMAGE PROCESSING 2022年第3期16卷 809-822页

作者： Sun, Mingsi Zhao, Hongwei Li, Jiao Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China Jilin Agr Sci & Technol Coll Coll Elect & Informat Engn Jilin Jilin Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun Peoples R China Jilin Univ Lib Syst Dept Changchun Peoples R China

Road crack detection is an important task for road safety and road maintenance. In the past, people made use of manual detection methods and tried to use computer vision to detect crack. The most prominent feature in recent years is the use of deep learning. However, there is no good deep learning method for road crack detection under noise. This challenge is faced bravely. First, a noise crack dataset is proposed, consisting of multiple noise crack images which is called NCD. Then, an adaptive bilateral filtering algorithm is developed, which can reduce the influence of noise. Finally, a new crack detection network with two new modules is designed. In the end, it is found that all the parts have promoting effects on crack detection under noise. Compared with other state-of-the-art methods, this method performs better, especially in road crack detection under noise. When evaluating the well-known crack500 test set, ODS F-measure of 0.628 is achieved. Besides, this method is also evaluated in another five datasets. Significantly, ODS F-measure of 0.545 is achieved, 4.0% higher than state-of-the-art on GAPs384.

关键词： convolutional neural nets deep learning (artificial intelligence) noise crack dataset feature pyramid structure road crack detection network roads road safety manual detection methods crack detection computer vision structural engineering computing feature enhancement multiple noise crack images feature extraction

来源：评论

学校读者我要写书评

暂无评论

Growing Structure Multiple Model Systems for Anomaly Detection and Fault Diagnosis

引用

JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME 2009年第5期131卷 051001页

作者： Liu, Jianbo Djurdjanovic, Dragan Marko, Kenneth Ni, Jun Univ Texas Austin Dept Mech Engn Austin TX 78712 USA Gen Motors Res & Dev Mfg Syst Res Lab Warren MI 48090 USA ETAS Inc Ann Arbor MI 48103 USA Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA

A new anomaly detection scheme based on growing structure multiple model system (GSMMS) is proposed in this paper to detect and quantify the effects of anomalies. The GSMMS algorithm combines the advantages of growing self-organizing networks with efficient local model parameter estimation into an integrated framework for modeling and identification of general nonlinear dynamic systems. The identified model then serves as a foundation for building an effective anomaly detection and fault diagnosis system. By utilizing the information about system operation region provided by the GSMMS, the residual errors can be analyzed locally within each operation region. This local decision making scheme can accommodate for unequally distributed residual errors across different operational regions. The performance of the newly proposed method is evaluated through anomaly detection and quantification in an electronically controlled throttle system, which is simulated using a high-fidelity engine simulation software package provided by a major automotive manufacturer for control system development.

关键词： digital simulation fault diagnosis self-organising feature maps structural engineering computing

来源：评论

学校读者我要写书评

暂无评论

Line-laser-based visual measurement for pavement 3D rut depth in driving state

引用

ELECTRONICS LETTERS 2018年第20期54卷 1172-1173页

作者： Hong, Ziming Ai, Qingsong Chen, Kun Wuhan Univ Technol Sch Informat Engn Wuhan 430070 Hubei Peoples R China

This Letter develops a line-laser-based real-time visual measurement method to inspect pavement rut depths. The detection vehicle equipped with line-laser projector continuously sends, in its normal driving state, laser light onto the pavement, which is captured by a high-resolution camera on the vehicle, thus a sequence of pavement rut laser line images are created. The pavement rut laser line image is transformed to the convexity index image, in which the peak points of the pavement rut laser line are rapidly sought to obtain the rut laser curve with a single-pixel width. The relationship between pavement rut depth and the visual deformation value of measurement points on the rut laser curve is determined by the calibration blocks, and then the pavement three-dimensional (3D) rut depths can be automatically measured, 3D rut depth curves and 3D rut surface can be reconstructed. Some experimental results verify the effectiveness of the proposed method.

关键词： driving state 3D rut surface convexity index image calibration blocks single-pixel width cameras optical projectors image reconstruction high-resolution camera automatic optical inspection structural engineering computing vehicle equipped detection laser light pavement 3D rut depth roads image sequences measurement by laser beam line-laser-based visual measurement pavement rut laser line image visual deformation value calibration line-laser projector rut laser curve

来源：评论

学校读者我要写书评

暂无评论

Sample generation of semi-automatic pavement crack labelling and robustness in detection of pavement diseases

引用

ELECTRONICS LETTERS 2019年第23期55卷 1235-1237页

作者： Jia, Guohui Song, Weidong Jia, Di Zhu, Hong Liaoning Tech Univ Sch Geomat Fuxin 123000 Peoples R China Liaoning Tech Univ Sch Elect & Informat Engn Huludao 125105 Peoples R China Inst Disaster Prevent Coll Ecol & Environm Beijing 101601 Peoples R China

Recent convolutional neural networks have made significant advancements in the detection of road cracks. However, the lack of accurate crack training data reduces the generalisation ability of the deep model. In this Letter, a semi-automatic pavement crack labelling algorithm is proposed to solve the problem of insufficient training data. First, the modified C-V model is used to obtain the preliminary segmentation results. Second, the direction of the initial segmentation area is calculated by the ellipse fitting method, and the preliminary segmentation results are used as samples for accurate labelling. Finally, a multi-scale feature extraction module is proposed for learning rich deep convolutional features, which allows the acquired crack features under a complex background to be more discriminant. The experimental results were compared with the manual marking method, and this method can achieve accurate marking of crack images with a low amount of interaction, thereby significantly reducing the cost of ground-truth making. The results of the validation and comparison experiments on test data sets indicate that the proposed method can not only effectively identify cracks, but also overcome the interference of many factors in the environment.

关键词： pavement diseases convolutional neural networks semiautomatic pavement crack labelling algorithm crack detection image segmentation Civil and mechanical engineering computing manual marking method road cracks modified C–V model road building rich deep convolutional features convolutional neural nets generalisation ability ellipse fitting method crack images Fracture mechanics and hardness (mechanical engineering) multiscale feature extraction module Optical, image and video signal processing Computer vision and image processing techniques feature extraction sample generation Construction industry Mechanical engineering applications of IT crack features structural engineering computing Neural computing techniques learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Molecular engineering of Solar-Powered Windows

引用

computing IN SCIENCE & engineering 2018年第1期20卷 84-87页

作者： Cole, Jacqueline M. Univ Cambridge Mol Engn Grp Cambridge England Argonne Natl Lab Argonne IL 60439 USA

A new initiative in data science is using the Mira and Theta supercomputers at the US Department of Energy’s Argonne National Laboratory to discover new dye materials suitable for dye-sensitized solar cells. This project aims to develop a new material-by-design methodology by using natural language processing, machine learning, and data mining in conjunction with large-scale simulation and experiments. This synergistic computational and experimental science approach will enable the discovery of new light-absorbing dye molecules, which are needed for the development of solar-powered windows that have the potential to power buildings in an entirely energy-sustainable fashion.

关键词： Data Mining Design engineering Learning Artificial Intelligence Natural Language Processing Solar Cell Arrays structural engineering computing Sustainable Development Windows Construction Energy Sustainable Fashion Light Absorbing Dye Molecules Experimental Science Approach Synergistic Computational Approach Large Scale Simulation Data Mining Machine Learning Natural Language Processing Material By Design Methodology Dye Sensitized Solar Cells Dye Materials US Department Of Energy Argonne National Laboratory Solar Powered Windows Data Driven Molecular engineering Photovoltaic Cells Databases Data Mining US Department Of Energy Machine Learning Supercomputers Theta Mira Data Science Scientific Computer Simulation Sustainable Energy Materials Discovery

来源：评论

学校读者我要写书评

暂无评论

Efficient pavement distress classification via deep patch soft selective learning and knowledge distillation

引用

ELECTRONICS LETTERS 2022年第18期58卷 693-695页

作者： Zhang, Shizheng Tang, Wenhao Wang, Jing Huang, Sheng Zhengzhou Univ Light Ind Coll Software Engn Zhengzhou Peoples R China Chongqing Univ Sch Big Data & Software Engn Chongqing Peoples R China

Pavement distress classification is a vital step for automatic pavement inspection and maintenance. Recently, patch-based approaches have achieved promising performances and thus extensive attention in this field. However, these methods simply assume that all patches contribute equally to the distress classification, leading to weakly discriminating abilities of models. Moreover, their tedious processes also lead to low efficiency in inference. The authors present a novel patch-based pavement distress classification approach named Deep Patch Soft Selective Learning, which addresses these issues. Similar to other patch-based approaches, Deep Patch Soft Selective Learning partitions the pavement images into patches and aggregates the patch features to accomplish the task. To address the first issue, a succinct Soft Patch Feature Selection Network is introduced to assess the importance of each patch to the distress classification with a score based on its feature. These scores will be considered as patch-wise weights for feature aggregation. In such a manner, the most discriminative patches are selected in a soft way, and thereby benefit the final classification. To address the inference efficiency issue, knowledge distillation is leveraged to transfer the classification knowledge from Deep Patch Soft Selective Learning to the image-based approaches, such as EfficientNet-B3. This distilled model enables incorporating both the advantages of patch-based approaches in classification performance and the advantages of image-based approaches in inference efficiency. Extensive experiments on a large-scale pavement image dataset named CQU-BPDD demonstrate that Deep Patch Soft Selective Learning outperforms the baselines by a large margin of +7.4% in P@R on the detection task and +3.1% in F-1 on the recognition task while enjoying 2.1x throughput of baselines.

关键词： patch features CQU-BPDD maintenance engineering patch-wise weights inspection image classification deep learning (artificial intelligence) discriminative patches automatic pavement inspection succinct soft patch feature selection network feature extraction feature aggregation image-based approaches patch-based pavement distress classification approach automatic pavement maintenance deep patch soft selective learning knowledge distillation structural engineering computing roads road building feature selection

来源：评论

学校读者我要写书评

暂无评论

ASME boiler & pressure vessel code requirements for prevention of brittle fracture

引用

JOURNAL OF PRESSURE VESSEL TECHNOLOGY-TRANSACTIONS OF THE ASME 2003年第2期125卷 121-130页

作者： Nickell, RE Appl Sci & Technol Poway CA 92064 USA

The ASME boiler and pressure vessel code requirements for prevention of brittle fracture were discussed. The implicit brittle fracture resistance procedure and an explicit procedure based on fracture mechanics principles were presented. The comparison of implicit and explicit approach was done and they were shown to be essentially equivalent when applied consistently.

关键词： safety fatigue testing stress-strain relations ASME Standards Boilers elastoplasticity Brittle fracture Stress pressure vessels Fracture (Materials) fracture toughness boilers structural engineering computing ductility Temperature Fracture toughness Pressure vessels brittle fracture

来源：评论

学校读者我要写书评

暂无评论

ExteriorTag: Automatic Semantic Annotation of BIM Building Exterior Via Voxel Index Analysis

引用

IEEE COMPUTER GRAPHICS AND APPLICATIONS 2021年第3期41卷 48-58页

作者： Liu, Xiaojun He, Changyan Zhao, Hantao Jia, Jinyuan Liu, Chang Jiaxing Univ Nanhu Coll Jiaxing 314001 Peoples R China Southeast Univ Nanjing 210096 Peoples R China Tongji Univ Shanghai 200092 Peoples R China Nanchang Hangkong Univ Nanchang 330063 Jiangxi Peoples R China

The growing demand for building information modeling (BIM) data and ubiquitous applications make it increasingly necessary to establish a reliable way to share the models on lightweight devices. Building scenes have strong occlusion features and the building exterior plays an important role in digital devices with limited computational resources. This allows the possibility to reduce the resource consumption while roaming in outdoor scenes by culling away the interior building data. This article addresses the task of automatic annotation of BIM building exterior via voxel index analysis. We showcase the research of using industry foundation classes (IFC) and other mainstream formats as our input data and proposed an automatic algorithm for annotating the building exterior. Afterward, a practical and accurate voxel index analysis procedure is designed for frequently flawed models. The annotation can be added directly into the original data file under the same IFC standard, avoiding the complex procedure and information loss in semantics mapping between different standards. The final examinations show the robustness of our algorithm and the capability of handling large BIM building models.

关键词： Architectural CAD Building Management Systems Buildings Structures Solid Modelling structural engineering computing Ubiquitous computing BIM Building Exterior Building Information Modeling Data Building Scenes Digital Devices Outdoor Scenes Interior Building Data Automatic Annotation Voxel Index Analysis Procedure BIM Building Models Semantic Annotation Industry Foundation Classes IFC Format Indexes Annotations Semantics Data Visualization Standards Data Models

来源：评论

学校读者我要写书评

暂无评论

Development of a three-dimensional semi-analytical elastic-plastic contact code

引用

JOURNAL OF TRIBOLOGY-TRANSACTIONS OF THE ASME 2002年第4期124卷 653-667页

作者： Jacq, C Nélias, D Lormand, G Girodin, D SNECMA Ctr Villaroche F-77550 Moissy Cramayel France Inst Natl Sci Appl CNRS Lab Mecan Contacts UMR 5514 F-69621 Villeurbanne France Inst Natl Sci Appl CNRS Etud Met Phys & Phys Mat Grp UMR 5510 F-69621 Villeurbanne France SNR Roulements F-74010 Annecy France

A three-dimensional elastic-plastic contact code based on semi-analytical method is presented and validated. The contact is solved within a Hertz framework. The reciprocal theorem with initial strains is then introduced, to express the surface geometry as a function of contact pressure and plastic strains. The irreversible nature of plasticity leads to an incremental formulation of the elastic-plastic contact problem, and all algorithm to solve this problem is set zip. Closed form expression, which give residual stresses and surface displacements from plastic strains, are obtained by integration of the reciprocal theorem. The resolution of the clastic-plastic contact using the finite clement (FE) method is discussed, and the semi-analytical code presented in this paper is validated by comparing results with experimental data from the nano-indentation test. Finally, the resolution of the rolling elastic-plastic contact is presented for smooth and dented surfaces and for a vertical or rolling loading. The main advantage of this code over classical FE codes is that the calculation time makes the transient analysis of three-dimensional contact problems affordable, including when a fine mesh is required.

关键词： mechanical contact stress analysis Plasticity plasticity finite element analysis Resolution (Optics) Stress Theorems (Mathematics) plastic flow structural engineering computing Pressure elasticity indentation Contact mechanics

来源：评论

学校读者我要写书评

暂无评论

Interactive illustrative rendering on mobile devices

引用

IEEE COMPUTER GRAPHICS AND APPLICATIONS 2007年第3期27卷 48-56页

作者： Huang, Jingshu Bue, Brian Pattath, Avin Ebert, David S. Thomas, Krystal M. Purdue Univ W Lafayette IN 47907 USA USAF Res Lab Wright Patterson AFB OH 45433 USA

Adapting desktop-based automated illustration techniques to satisfy mobile device restrictions entails many challenges. The MobileVis system implements advanced illustrative rendering techniques to let users interacti... 详细信息

关键词： Data Visualisation Interactive Systems Mobile computing Rendering Computer Graphics Solid Modelling structural engineering computing Interactive Illustrative Text Rendering System Mobile Devices Interactive Cutaway Views Ghosted Views Silhouettes Selective Rendering Mobile Vis System Interactive Illustrative 3 D Graphics System 3 D Model Interior Structures Visualization Rendering Computer Graphics Graphics Three Dimensional Displays Laboratories Clocks Handheld Computers Java Research And Development Application Software Mobile computing Mobile Devices Visualization Illustration CAD

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：