检索结果-内蒙古大学图书馆

distect: automatic sample-position tracking for X-ray experiments using computer vision algorithms

JOURNAL OF SYNCHROTRON RADIATION 2024年第Pt 6期31卷 1514-1524页

作者： Berg, Michael Furrer, Dirk Thominet, Vincent Wang, Xiaoqiang Zeugin, Stefan Grabner, Helmut Stockinger, Kurt Piamonteze, Cinthia Zurich Univ Appl Sci Sch Engn Zurich Switzerland Paul Scherrer Inst CH-5232 Villigen Switzerland

Soft X-ray spectroscopy is an important technique for measuring the fundamental properties of materials. However, for measurements of samples in the sub-millimetre range, many experimental setups show limitations. Position drifts on the order of hundreds of micrometres during thermal stabilization of the system can last for hours of expensive beam time. To compensate for drifts, sample tracking and feedback systems must be used. However, in complex sample environments where sample access is very limited, many existing solutions cannot be applied. In this work, we apply a robust computer vision algorithm to automatically track and readjust the sample position in the dozens of micrometres range. Our approach is applied in a complex sample environment, where the sample is in an ultra-high vacuum chamber, surrounded by cooled thermal shields to reach sample temperatures down to 2.5 K and in the center of a superconducting split coil. Our implementation allows sample-position tracking and adjustment in the vertical direction since this is the dimension where drifts occur during sample temperature change in our setup. The approach can be easily extended to 2D. The algorithm enables a factor of ten improvement in the overlap of a series of X-ray absorption spectra in a sample with a vertical size down to 70 mu m. This solution can be used in a variety of experimental stations, where optical access is available and sample access by other means is reduced.

关键词： variable temperature inserts sample-position tracking soft X-ray absorption spectroscopy computer vision algorithms sample-position accuracy

来源：评论

学校读者我要写书评

暂无评论

Quantitative detection and sorting of broken kernels and chalky grains in milled rice using computer vision algorithms

引用

JOURNAL OF FOOD ENGINEERING 2024年 383卷

作者： Fan, Fanghui Chen, Haoran Gao, Yi Mou, Tian Shenzhen Univ Coll Chem & Environm Engn Dept Food Sci & Engn Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Univ Med Sch Sch Biomed Engn Shenzhen 518060 Peoples R China Guangdong Prov Key Lab Math & Neural Dynam Syst Dongguan 523000 Peoples R China Marshall Lab Biomed Engn Shenzhen 518060 Peoples R China

The milled rice industry faces challenges in effectively detecting and sorting broken kernels and chalky grains. This paper presents a computer vision approach to detect and characterize broken kernels and chalky grains in three milled rice varieties (HM105, WYD4, and JH6). Broken kernel sorting was validated against an ISO-derived recognition method, while the identification of chalky grains was validated using a DSC to assess thermal behavior. The logistic regression showed a strong discriminatory ability in identifying broken kernels. Unlike the ISO method, logistic regression achieved high sorting accuracy for HM105, WYD4, and JH6. The iterative threshold segmentation algorithm also accurately segmented chalky regions in milled rice grains. Regression analysis revealed a significant positive correlation (R2 >= 0.94) between the chalky region area and Delta H values. Therefore, this study introduces a robust and rapid methodology for quantitatively detecting milled rice, with the potential for automation and intelligentization in rice-based food processes.

关键词： Milled rice quality computer vision algorithms Broken kernels Chalky grains Logistic regression Iterative threshold segmentation

来源：评论

学校读者我要写书评

暂无评论

Analysis of computer vision algorithms to Determine the Quality of Fermented Cocoa (Theobroma Cacao): Systematic Literature Review 2nd

Analysis of Computer Vision Algorithms to Determine the Qual...

引用

2nd International Conference on ICTs in Agronomy and Environment (CITAMA)

作者： Mite-Baidal, Karen Solis-Aviles, Evelyn Martinez-Carriel, Tayron Marcillo-Plaza, Augusto Cruz-Ibarra, Elicia Baque-Bustamante, Wilmer Agr Univ Ecuador Comp Sci Dept Fac Agr Sci Av 25 Julio & Pio JaramilloPOB 09-04-100 Guayaquil Ecuador

ISBN: (纸本)9783030107284;9783030107277

computer vision techniques have been used for the automation of processes in the agricultural sector due to the benefits obtained such as effectiveness and quality. A clear example is the analysis of cocoa beans quality. The increasing interest of computer vision in this area calls for a clear, systematic overview. In this sense, we present a systematic literature review (SLR) of computer vision algorithms to determine the quality of fermented cocoa in a six-year period: from 2013-2018. The aim of this review is to identify the techniques or computer vision algorithms used to assess fermentation index of cocoa beans for quality control, as well, the main physical and chemical characteristics of the cocoa beans identified through the computer vision algorithms. The results show that the PLS (Partial Least-Squares) algorithm is the most used for the classification of images in a statistical approach. Also, color is the physical parameter that is commonly identified through artificial vision algorithms. Meanwhile, Fat and pH are the chemical parameters most identified by FT-NIR (Fourier transform near-infrared) technology in conjunction with the chemometric technique.

关键词： computer vision computer vision algorithms Image recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel 6G Scalable Blockchain Clustering-Based computer vision Character Detection for Mobile Images

引用

computers, Materials & Continua 2024年第3期78卷 3041-3070页

作者： Yuejie Li Shijun Li Department of Mathematics and Computer Engineering Ordos Institute of TechnologyOrdos017000China School of Mathematics and Physics North China Electric Power UniversityBeijing102206China School of Electrical Information Hunan University of EngineeringXiangtan411104China

6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous *** tandem with these advancements,blockchain technology is leveraged to enhance computer vision applications’security,trustworthiness,and *** the widespread use of mobile devices equipped with cameras,the ability to capture and recognize Chinese characters in natural scenes has become increasingly *** can facilitate privacy-preserving mechanisms in applications where privacy is paramount,such as facial recognition or personal healthcare *** can control their visual data and grant or revoke access as *** Chinese characters from images can provide convenience in various aspects of people’s ***,traditional Chinese character text recognition methods often need higher accuracy,leading to recognition failures or incorrect character *** contrast,computer vision technologies have significantly improved image recognition *** paper proposed a Secure end-to-end recognition system(SE2ERS)for Chinese characters in natural scenes based on convolutional neural networks(CNN)using 6G *** proposed SE2ERS model uses the Weighted Hyperbolic Curve Cryptograph(WHCC)of the secure data transmission in the 6G network with the blockchain *** data transmission within the computer vision system,with a 6G gradient directional histogram(GDH),is employed for character *** the deployment of WHCC and GDH in the constructed SE2ERS model,secure communication is achieved for the data transmission with the 6G *** proposed SE2ERS compares the performance of traditional Chinese text recognition methods and data transmission environment with 6G *** results demonstrate that SE2ERS achieves an average recognition accuracy of 88%for simple Chinese characters,compared to 81.2%with traditional ***

关键词： 6G technology blockchain end-to-end recognition Chinese characters natural scene computer vision algorithms convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Performance and precision analysis of 3D surface modeling through UAVs: validation and comparison of different photogrammetric data processing software

引用

PHYSICA SCRIPTA 2024年第3期99卷 035017-035017页

作者： Mora-Felix, Zuriel D. Rangel-Peraza, Jesus Gabriel Monjardin-Armenta, Sergio Alberto Sanhouse-Garcia, Antonio J. Tecnol Nacl Mexico Div Estudios Posgrad Invest Inst Tecnol Culiacan Juan de Dios Batiz 310 Col Guadalupe Culiacan 80220 Mexico Univ Autonoma Sinaloa Fac Ciencias Tierra & Espacio Circuito Interior Oriente SN Culiacan 80040 Mexico

The planimetric and altimetric accuracies of the Digital Elevation Model (DEM) obtained from Unmanned Aerial Vehicle (UAV) depend on some photogrammetric parameters such as flight height, flight speed, and/or ground sample distance. In the last few years, the study of computer vision algorithms has increased focusing on their importance on the photogrammetric reconstruction process for land surface mapping. According to this, the main goal of this paper was to evaluate the performance of different photogrammetric processing software, such as Open Drone Map (ODM), Agisoft PhotoScan, and Pix4D, on DEM accuracy. For this purpose, a DJI Phantom 4 Pro drone was used for the acquisition of 600 images in a difficult topography area (630 ha) with 27 Ground Control Points (GCP) previously established. The photogrammetric products were generated, and a statistical analysis was carried out for the comparison of the DEMs. The results of the Root Mean Square Error (RMSE) show that the planimetric and altimetric accuracy of Agisoft PhotoScan (RMSExy = 0.514 m;RMSEz = 0.162 m) is greater than those obtained using Pix4D and ODM. Unsatisfactory results were obtained with ODM since deformations and high planimetric and altimetric errors were identified in the orthomosaic and DEM, which was related to inefficient key point detection and an incomplete mosaic construction process. Agisoft PhotoScan modeled the anthropogenic objects as part of the land surface, while Pix4d smoothed the terrain, eliminating these anthropogenic objects and not considering them as part of the ground surface.

关键词： computer vision algorithms photogrammetric reconstruction process digital elevation model UAV photogrammetry planimetric and altimetric accuracy

来源：评论

学校读者我要写书评

暂无评论

Utilization of computer vision and Deep Learning in Fault Identification and Repair of Mechanical and Electronic Equipment

Utilization of Computer Vision and Deep Learning in Fault Id...

引用

作者： Wu, Jun Zhenjiang Higher Vocational and Technical School Jiangsu Province Zhenjiang City China

With the rapid development of computer technology, network communication, and digital signal processing, more and more professionals have begun to focus on learning and researching new knowledge and using advanced software tools to comprehensively upgrade existing equipment. In this context, deep learning machines were used to replace some of the difficulties and shortcomings in traditional teaching. This article focused on the theory, methods, and operational principles of deep neural networks. At the same time, fault diagnosis and repair strategies based on computer vision technology, machine vision, and digital signal processing were analyzed, and data simulation results were achieved through performance testing of the model. The results showed that the accuracy of the model in identifying normal equipment parts was 100%;the accuracy in identifying internal equipment parts was 94%;and the accuracy in identifying external equipment parts was 97%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： computer vision algorithms Deep learning Equipment failures Mechanical and electronic equipment

来源：评论

学校读者我要写书评

暂无评论

Computational Complexity Optimization of Vehicle Video-Recognition Algorithm Using the Virtual Detectors Method

Computational Complexity Optimization of Vehicle Video-Recog...

引用

2024 Systems of Signal Synchronization, Generating and Processing in Telecommunications, SYNCHROINFO 2024

作者： Kuteynikov, Ivan Yashina, Marina Department of Higher Mathematics Moscow Russia Moscow Technical University of Communications and Informatics Moscow Moscow Russia Moscow Russia

ISBN: (纸本)9798350373448

The paper presents the research of computational complexity optimization of a virtual detector method for video-based vehicle recognition. This method enables a more flexible and adaptive analytical research and optimizes the resource utilization. In addition, the optimization of the computational complexity of the video recognition algorithm required to improve accuracy and speed is investigated. This approach allows to significantly reduce the load on computational resources and ensure the accuracy and efficiency of vehicle recognition even when the frame rate is reduced. The paper presents a system for monitoring the dynamics of traffic flows based on the method of virtual detectors - «ViDeS» (Virtual Detectors System) for which the analysis of recognition efficiency depending on the frame rate is conducted. The developed software allows to increase the efficiency of traffic flow vehicle recognition © 2024 IEEE.

关键词： adaptive metrics computer vision algorithms data analysis vehicle counting virtual detector method

来源：评论

学校读者我要写书评

暂无评论

A local real-time bar detector based on the multiscale Radon transform

A local real-time bar detector based on the multiscale Radon...

引用

Conference on Real-Time Image Processing and Deep Learning

作者： Oliva-Garcia, Ricardo Gomez-Cardenes, Oscar Marichal-Hernandez, Jose G. Martin-Hernandez, Javier Phillip-Luke, Jonas Rodriguez-Ramos, Jose M. Univ La Laguna Ind Engn Dept ETSI San Cristobal la Laguna 38200 Spain Wooptix SL Av Trinidad 61 San Cristobal la Laguna 38204 Spain

ISBN: (纸本)9781510650817;9781510650800

We propose a local bar-shaped structure detector that works in real time on high-resolution images. It is based on the Radon transform. Specifically in the muti-scale variant, which is especially fast because it works in integer mathematics and does not use interpolation. The Radon transform conventionally works on the whole image, and not locally. In this paper we describe how by stopping at the early stages of the Radon transform we are able to locate structures locally. We also provide an evaluation of the performance of the algorithm running on the CPU, GPU and DSP of mobile devices to process at acquisition time the images coming from the device's camera.

关键词： Bar detector computer vision algorithms Radon Transform Real-time implementations Code bar detector Local detector

来源：评论

学校读者我要写书评

暂无评论

Visual Features for Improving Endoscopic Bleeding Detection Using Convolutional Neural Networks

引用

SENSORS 2023年第24期23卷 9717-9717页

作者： Brzeski, Adam Dziubich, Tomasz Krawczyk, Henryk Gdańsk Univ Technol Fac Elect Telecommun & Informat PL-80233 Gdansk Poland

The presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods. Each of the proposed feature descriptors outputs a feature activation map in the form of a grayscale image. Acquired feature maps can be appended in a straightforward way to the original color channels of the input image and passed to the input of a convolutional neural network during the training and inference steps. An experimental evaluation is conducted to compare the classification ROC AUC of feature-extended convolutional neural network models with baseline models using regular color image inputs. The advantage of feature-extended models is demonstrated for the Resnet and VGG convolutional neural network architectures.

关键词： machine learning artificial intelligence computer vision algorithms convolutional neural networks medical image analysis

来源：评论

学校读者我要写书评

暂无评论

YOLO-based detection of Halyomorpha halys in orchards using RGB cameras and drones

引用

computerS AND ELECTRONICS IN AGRICULTURE 2023年 213卷

作者： Sorbelli, Francesco Betti Palazzetti, Lorenzo Pinotti, Cristina M. Univ Perugia Dept Math & Comp Sci Perugia Italy Univ Florence Dept Comp Sci & Math Florence Italy

This paper explores the utilization of innovative technologies such as RGB cameras, drones, and computer vision algorithms, for monitoring pests in orchards, with a specific focus on detecting the Halyomorpha halys (HH), commonly known as the "brown marmorated stink bug". The integration of drones and machine learning (ML) into integrated pest management shows promising potential for effectively combating HH infestations. However, challenges arise from relying on vision models solely trained using high-quality images from public datasets. To address this issue, we create an ad hoc dataset of on-site images mainly captured with the help of a drone as well as other devices. We initially conduct an in-depth analysis of the captured images, considering factors such as blurriness and brightness, to possibly improve the performance of the ML algorithms. Afterwards, we undertake the training and evaluation of diverse ML models using distinct approaches within the YOLO framework. We employ a range of metrics to compare their performance and ultimately achieve a satisfactory outcome. Through the optimization of ML models and the correction of image imperfections, we contribute to advancing automated decision-making processes in pest insect monitoring and management, specifically in HH monitoring.

关键词： Unmanned aerial vehicles Insect detection Halyomorpha halys Brown marmorated stink bug computer vision algorithms YOLO

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：