检索结果-内蒙古大学图书馆

7th International Conference on Smart City Applications, SCA 2022

作者： Ouchani, Rahma Merzougui, Mohammed Nasri, M’barek BV Mohammed VI B.P. 524 Oujda60000 Morocco

ISBN: (纸本)9783031268519

image segmentation is a fundamental step in image processing, The existing segmentation techniques are numerous, but they are generally grouped into three main approaches which are the contour approach, the region approach and the cooperative approach. The segmentation by region approach aims to group the pixels with the same characteristics into homogeneous regions. It is characterized by the measure of uniformity of the regions constructed into the image. Generally, we distinguish three families of algorithms for the region approach: classification methods, region growth methods, and methods that divide or merge regions according to the chosen criterion. Our study is based on the unsupervised classification method using the K-means algorithm. This is the most known and used clustering algorithm, because of its simplicity of implementation. We know that this algorithm still suffers from several drawbacks such as The number of classes must be fixed at the beginning, The result depends on initial draw or starting values of the centers of the classes, so a main problem in the initialization phase. For this we propose to improve this behind by a simple initialization technique based on the optimization of the distance between the objects inside each class to obtain a set of compact and clearly separated clusters. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Golub Kahan Based Methods for Partial Multidimensional Singular Value Decomposition 13

Golub Kahan Based Methods for Partial Multidimensional Singu...

引用

13th International Conference on Dependable systems, Services and Technologies, DESSERT 2023

作者： Hachimi, Anas El Hached, Mustapha Jbilou, Khalide Ratnani, Ahmed Mohammed VI Polytechnic University UM6P Vanguard Center Green City Morocco Université du Littoral ULCO Calais France Laboratoire P. Painlevé Université de Lille Villeneuve d'Ascq France Université du Littoral ULCO Laboratoire LMPA Calais France Mohammed VI Polytechnic University Green City Morocco

ISBN: (纸本)9798350396119

Many applications of machine learning, data, image and signal processing require the design of algorithms capable of dealing with very large datasets. Extracting the most meaningful features out of these large datasets is often a computationally challenging task. In the matrix case, the Singular Value Decomposition (SVD) has shown to be a very efficient tool to do so. In recent years there has been a very significant increase in the amount of available data and the datasets are often formatted as tensors, for which some generalisations of the SVD have already been proposed for some specific choices of tensor-tensor products, well adapted to tensors of order 3. In this work, we propose a new generalisation, associated with the well-known Einstein product, regardless of the order of the tensors. As in the matrix case, only a few singular elements need to be computed and we address this problem by proposing an iterative approach based on the tensor Lanczos bidiagonalization applied to the Einstein product. We also propose a refinement to this method in order to increase its accuracy. We give numerical results for both synthetic and real data to illustrate the efficiency of these methods. © 2023 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Interpreting and understanding the image using deep learning and imprecise information from the monitoring system

Interpreting and understanding the image using deep learning...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kubanek, Mariusz Bobulski, Janusz Karbowiak, Lukasz Czestochowa University of Technology Department of Computer Science Czestochowa Poland

ISBN: (纸本)9798350324457

The interpretation and understanding of images using deep learning algorithms in monitoring systems is an important area of research in computer vision. In this paper, we propose a novel approach for interpreting and understanding images of human behaviour captured from cameras and drones in monitoring systems. In the work, we presented a pedestrian detection method. This is the first element of a larger system of interpreting the behaviour of traffic participants. We begin by pre-processing the images to remove noise and unwanted artefacts. We then use labelled and unlabelled data to train a deep learning algorithm to accurately classify and predict human behaviour. To account for imprecise information, we incorporate probabilistic models into the algorithm to allow it to make predictions with uncertainty. To evaluate the performance of our proposed approach, we use standard metrics, such as precision, recall, and F1 score, and compare our results to existing methods. We also identify the limitations of existing approaches and propose new methods for interpreting and understanding images that can improve their accuracy and reliability. Our proposed approach has the potential to provide a more accurate and robust method for interpreting and understanding images of human behaviour in monitoring systems. It can be used in various applications like traffic monitoring, security systems, and surveillance. Our results demonstrate the importance of incorporating imprecise information into deep learning algorithms to improve their performance and highlight the potential for future research in this area. © 2023 IEEE.

关键词： autonomous car computer vision pedestrian safety smart city

来源：评论

学校读者我要写书评

暂无评论

The capabilities of developing eye tracking for AR systems on the base of a microcontroller Raspberry Pi® 6

The capabilities of developing eye tracking for AR systems o...

引用

Conference on Optics, Photonics and Digital Technologies for Imaging Applications vi

作者： Shlyamova, E. E. Ezhova, K. V. Fedorenko, D. A. ITMO Univ 49 Kronverksky Pr St Petersburg 197101 Russia

ISBN: (数字)9781510634794

ISBN: (纸本)9781510634794

This paper focuses on eye tracking technology in application to augmented reality systems and considers the method and the algorithm for detecting the iris and calculating the coordinate of its centre. The algorithm was successfully tested on a prototype. The material base of the prototype for testing the algorithms was Raspberry Pi microcomputer and camera module. The software part of the system was Python programming language and OpenCV library for image processing.

关键词： Eye tracking Iris detection Augmented reality image processing Raspberry Pi

来源：评论

学校读者我要写书评

暂无评论

Hybrid Embedded-systems-Based Approach to in-Driver Drunk Status Detection Using image processing and Sensor Networks

引用

IEEE SENSORS JOURNAL 2021年第14期21卷 15729-15740页

作者： Rosero-Montalvo, Paul D. Felix Lopez-Batista, vivian Hernan Peluffo-Ordonez, Diego Univ Salamanca Dept Comp Sci & Automat Salamanca 37007 Spain Univ Tecn Norte Dept Appl Sci Ibarra 100105 Ecuador Univ Yachay Tech Sch Math & Computat Sci Urcuqui 100119 Ecuador Mohammed VI Polytech Univ Modeling Simulat & Data Anal MSDA Res Program Ben Guerir 43150 Morocco Corp Univ Autonoma Narino Dept Engn Pasto 520006 Colombia

Car drivers under the influence of alcohol is one of the most common causes of road traffic accidents. To tackle this issue, an emerging, suitable alternative is the use of intelligent systems-traditionally based on either sensor networks or artificial vision-that are aimed to prevent starting the car when drunk status on the car driver is detected. In such vein, this paper introduces a system whose main objective is identifying a person having alcohol in the blood through supervised classification of sensor-generated and computer-vision-based data. To do so, some drunk-status criteria are considered, namely: the concentration of alcohol in the car environment, the facial temperature of the driver and the pupil width. Specifically, for data acquisition purposes, the proposed system incorporates a gas sensor, temperature sensor and a digital camera. Acquired data are analyzed into a two-stages machine learning system consisting of feature selection and supervised classification algorithms. Both acquisition and analysis stages are to be performed into a embedded system, and therefore all procedures and algorithms are designed to work at low-computational resources. As a remarkable outcome, due mainly to the incorporation of feature selection and relevance analysis stages, proposed approach reaches a classification performance of 98% while ensures adequate operation conditions for the embedded system.

关键词： Classification algorithms computer vision drunk detection intelligent system sensors

来源：评论

学校读者我要写书评

暂无评论

processing of global solar irradiance and ground-based infrared sky images for solar nowcasting and intra-hour forecasting applications

引用

SOLAR ENERGY 2023年 264卷

作者： Terren-Serrano, Guillermo Martinez-Ramon, Manel Univ Calif Santa Barbara Environm Studies Dept Santa Barbara CA 93106 USA Univ Calif Santa Barbara Environm Markets Lab emLab Santa Barbara CA 93106 USA Univ New Mexico Dept Elect & Comp Engn Albuquerque NM 87131 USA

Shadows from moving clouds in the troposphere impact the energy generated by photovoltaic systems. intra-hour solar forecast can be used to regulate solar energy dispatch. This investigation develops a data processing method for cloud dynamic feature extraction from raw sky images and Global Solar Irradiance (GSI) measurements that can be integrated into solar forecasting algorithms to reduce the operational supervision of hardware. Sky images and GSI measurements are acquired from a low-cost long-wave infrared radiometric camera and a pyranometer. This sky imager is mounted on a solar tracker that maintains the Sun in the center of sky images throughout the day. Multiple processing methods are proposed here that take advantage of a hybrid approach to approximate the optimal parameters of physical models using computationally inexpensive machine learning models. A signal processing method removes cyclostationary biases in high-resolution clear sky index values found when detrending GSI measurements using the clear sky GSI. image processing methods are then used to remove the effects of atmospheric radiation and the Sun's direct radiation from infrared sky images, plus the radiation effect emitted by debris on the sky imager's germanium outdoor lens. The result is an adaptive solar forecasting algorithm that can reduce the operational cost of power grids with the high participation of solar energy in the generation mix.

关键词： image processing Long-wave infrared Machine learning Sky imaging Sun tracking

来源：评论

学校读者我要写书评

暂无评论

image Edge Detection Methods in Perimeter Security systems Using Distributed Fiber Optical Sensing

引用

SENSORS 2022年第12期22卷 4573-4573页

作者： Dejdar, Petr Zaviska, Pavel Valach, Sobeslav Munster, Petr Horvath, Tomas Brno Univ Technol Fac Elect Engn & Commun Dept Telecommun Tech 12 Brno 61600 Czech Republic Czech Opt Solut Sro Vavreckova 5262 Zlin 76001 Czech Republic

This paper aims to evaluate detection algorithms for perimeter security systems based on phase-sensitive optical time-domain reflectometry (Phi-OTDR). Our own designed and developed sensor system was used for the measurement. The main application of the system is in the area the perimeter fencing intrusion detection. The system is unique thanks to the developed motherboard, which contains a field-programmable gate array (FPGA) that takes care of signal processing. This allows the entire system to be integrated into a 1U rack chassis. A polygon containing two different fence types and also cable laid underground in a plastic tube was used for testing. Edge detection algorithms using the Sobel and Prewitt operators are considered for post-processing. The comparison is made based on the signal-to-noise ratio (SNR) values calculated for each event. Results of algorithms based on edge detection methods are compared with the conventional differential method commonly used in Phi-OTDR systems.

关键词： edge detection intruder detection phase-OTDR signal-to-noise ratio vibration sensing

来源：评论

学校读者我要写书评

暂无评论

InCrowd-vi: A Realistic visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation

arXiv

引用

arXiv 2024年

作者： Bamdad, Marziyeh Hutter, Hans-Peter Darvishy, Alireza Institute of Applied Information Technology Zurich University of Applied Sciences Switzerland Department of Informatics University of Zurich Switzerland

Simultaneous localization and mapping (SLAM) techniques can be used to navigate the visually impaired, but the development of robust SLAM solutions for crowded spaces is limited by the lack of realistic datasets. To address this, we introduce InCrowd-vi, a novel visual-inertial dataset specifically designed for human navigation in indoor pedestrian-rich environments. Recorded using Meta Aria Project glasses, it captures realistic scenarios without environmental control. InCrowd-vi features 58 sequences totaling a 5 km trajectory length and 1.5 hours of recording time, including RGB, stereo images, and IMU measurements. The dataset captures important challenges such as pedestrian occlusions, varying crowd densities, complex layouts, and lighting changes. Ground-truth trajectories, accurate to approximately 2 cm, are provided in the dataset, originating from the Meta Aria project machine perception SLAM service. In addition, a semi-dense 3D point cloud of scenes is provided for each sequence. The evaluation of state-of-the-art visual odometry (VO) and SLAM algorithms on InCrowd-vi revealed severe performance limitations in these realistic scenarios. Under challenging conditions, systems exceeded the required localization accuracy of 0.5 meters and the 1% drift threshold, with classical methods showing drift up to 5-10%. While deep learning-based approaches maintained high pose estimation coverage (>90%), they failed to achieve real-time processing speeds necessary for walking pace navigation. These results demonstrate the need and value of a new dataset to advance SLAM research for visually impaired navigation in complex indoor environments. The dataset and associated tools are publicly available at https://***/. Copyright © 2024, The Authors. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Transform-Based Quality Assessment for Enhanced image 44

Transform-Based Quality Assessment for Enhanced Image

引用

Conference Applications of Digital image processing XLIV

作者： Voronin, V. Semenishchev, E. Zelensky, A. Tokareva, O. Cenc, Y. Agaian, S. Moscow State Univ Technol STANKIN Ctr Cognit Technol & Machine Vis Moscow Russia Don State Tech Univ Lab Math Methods Image Proc & Intelligent Comp Vi Rostov Na Donu Russia Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China CUNY Dept Comp Sci New York NY 10021 USA

ISBN: (数字)9781510645233

ISBN: (纸本)9781510645233;9781510645226

images captured in bad weather suffer from low contrast and faint color. Recently, plenty of enhanced algorithms have been proposed to improve visibility and restore color. The goal of image quality assessment is to predict the perceptual quality for improving imaging systems' performance. We proposed a no-reference image quality enhancement measure using hypercomplex Fourier transform for color images. The main idea is that enhancing the contrast of an image would create more high-frequency content in the enhanced image than the original image. An increase in the magnitude of higher frequency coefficients indicates an enhancement in contrast to the image's luminance content. To test the performance of the proposed algorithm, the public database TID2013 is used. The Pearson rank-ordered correlation coefficient is utilized to measure and compare the proposed quality measure's performance with state-of-the-art approaches.

关键词： quality measure frequency-domain transform no-reference (NR) image quality enhanced image

来源：评论

学校读者我要写书评

暂无评论

Golub Kahan Based Methods for Partial Multidimensional Singular Value Decomposition

Golub Kahan Based Methods for Partial Multidimensional Singu...

引用

IEEE International Conference on Dependable systems, Services and Technologies (DESSERT)

作者： Anas El Hachimi Mustapha Hached Khalide Jbilou Ahmed Ratnani UM6P Vanguard Center Mohammed VI Polytechnic University Green City Morocco Université du Littoral ULCO Calais France Laboratoire P. Painlevé Université de Lille Villeneuve d’Ascq France Laboratoire LMPA Université du Littoral ULCO Calais France Mohammed VI Polytechnic University Green City Morocco

关键词：

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：