检索结果-内蒙古大学图书馆

4th International Conference on Wireless Communications and applications, ICWCA 2020

作者： Sun, Hetao Zhong, Jianyong Jiaxing Vocational and Technical College Jiaxing314036 China

ISBN: (纸本)9789811651670

The online car is the product of the "Interonline+ " era. As a new city intelligent transportation mode, it breaks the old interest pattern and the barrier of taxi industry based on franchise. In recent years, the number of online car Hailing has increased sharply. However, due to the lack of effective supervision means, security problems have gradually emerged, such as rape, robbery, intentional injury, intimidation, abuse of passengers and other incidents. In order to solve this problem, this project proposes an intelligent security system for online car Hailing based on machine vision, constructs an advanced machine vision solution framework, and introduces graphics and image processing technology and machine learning abnormal behavior intelligent warning model. At the same time, combined with the embedded technology, it can automatically warn the abnormal behavior in the online car Hailing and quickly access the manual intervention and alarm, so as to timely detect the security threats and potential dangers in the process of taking the bus, so as to realize the purpose of protecting the safety of the online car Hailing passengers. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Fast and Flexible Turret Based Automated vision Inspection (AVI) to Inspect 6 Sides of Small Discrete Components 1

引用

11th International Conference on Robotics, vision, Signal processing and Power applications, RoViSP 2021

作者： Loo, Kean Li Saw, Chong Keat Ibrahim, M.H. Micro Modular System Sdn. Bhd. Bayan Lepas11900 Malaysia School of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru80990 Malaysia

ISBN: (数字)9789811681295

ISBN: (纸本)9789811681288

Smart devices components come in a variety of shapes, sizes and texture. To perform a high throughput inspection on all the six sides of the surface of the component is challenging due to tolerances of product dimension and the multiple planes on its surface. The image acquisition system for surface inspection comprises of a CMOS camera, telecentric lens, LED light source and motorized actuator. HALCON vision library was used for image processing. One of the most important requirements of an effective Automated vision Inspection (AVI) is consistent part presentation. Thus, to perform the positioning correction we propose two position recognition method using 2D-metrology and Smallest Rectangle Segmentation. The result of the position recognition was fed to XY rotary table for offset correction before picked up by turret fingers. Actuators for camera focusing were added to increase the flexibility of the system to inspect various component sizes. The Exposure End event of a modern CMOS camera was used for parallelization to optimize the machine vision cycle time. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Support Vector machine-based approach for Recognizing Bonsai Species using Leaf image 18

Support Vector Machine-based approach for Recognizing Bonsai...

引用

18th IEEE International Colloquium on Signal processing and applications (CSPA)

作者： Aminuddin, Raihah Maskan, Farizul Azlan Jalil, Ummu Mardhiah Abdul Fesol, Siti Feirusz Ahmad Ibrahim, Shafaf Univ Teknol MARA Fac Comp & Math Sci Melaka Branch Jasin Campus Melaka Malaysia Protech Synergy Sdn Bhd Petaling Jaya Selangor Malaysia

ISBN: (纸本)9781665485296

Recognition of Bonsai plant is one of the most challenging task. This is because most of the people have less knowledge about Bonsai especially for a beginner. For those who new to this field, it might be hard for them to recognize and identify the species of Bonsai because of its similarity in terms of shape, colour and etc. The incorrect identification of species, may resulting in damaging the Bonsai plant. Furthermore, different species of Bonsai may have different ways to take care of it. Therefore, the information about the Bonsai need to be accessible with the recognition of the species. As a solution, the aims of this project is to develop a system for recognising three species of Bonsai: 1) Adenium, 2) Red Japanese Maple and 3) Natal Plum by using its leaf. The project implemented a Rapid Application Development (RAD) Model as the methodology. There are four phases in RAD: 1) Planning, 2) Design, 3) Implementation and 4) Finalization. In pre-processed phase, feature extraction of the leaf is using colour moment and Gray-Level Co- occurrence Matrix (GLCM) were used for extracting the colour of the leaf. The species of Bonsai has been classified using Support Vector machine-based approach and the system has been successfully recognize the species of Bonsai with accuracy of 98.2%.

关键词： bonsai support vector machine machine learning leaf recognition

来源：评论

学校读者我要写书评

暂无评论

A Rate-Distortion-Classification approach for lossy image compression

引用

DIGITAL SIGNAL processing 2023年第1期141卷

作者： Zhang, Yuefeng Beijing Inst Comp Technol & Applicat Beijing Peoples R China

In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized the significance of considering semantic distortion in compressed images. To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion -Classification (RDC) model for lossy image compression, offering a unified framework to optimize the trade-off between rate, distortion, and classification accuracy. The RDC model is extensively analyzed both statistically on a multi-distribution source and experimentally on the widely used MNIST dataset. The findings reveal that the RDC model exhibits desirable properties, including monotonic non-increasing and convex functions, under certain conditions. This work provides insights into the development of human-machine friendly compression methods and Video Coding for machine (VCM) approaches, paving the way for end-to-end image compression techniques in real-world applications. & COPY;2023 Elsevier Inc. All rights reserved.

关键词： Data compression Computer vision Convex optimization Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fast Correction and Stitching Algorithm for Fisheye images

Fast Correction and Stitching Algorithm for Fisheye Images

引用

image processing, Computer vision and machine Learning (ICICML), International Conference on

作者： Qian Li Shantao Song Ruixue Liu Eugene Levin Shandong Provincial Key Laboratory of Robot and Manufacturing Automation Technology Institute of Automation Qilu University of Technology (Shandong Academy of Sciences) Jinan China Department of Biomedical Data Science School of Applied Computational Sciences Meharry Medical College Nashville Tenn USA

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

Fisheye cameras, with their ultra-wide-angle field of view, can capture a larger scene in a single shot compared to traditional lenses. This capability makes them highly valuable in areas such as security surveillance, panoramic photography, autonomous driving, and robot navigation. However, building an efficient and accurate visual system is crucial for realizing these applications. This paper proposes an improved algorithm based on fisheye image correction and stitching. First, a fast fisheye image distortion correction method is introduced to eliminate the severe distortion caused by the fisheye lens. Then, the o-FAST algorithm is used for feature point detection, ensuring rotational invariance of the feature points, and the KNN algorithm is employed for initial matching. On this basis, the PROSAC algorithm is applied to remove incorrect matches and compute the homography matrix between images. Finally, seamless image stitching is achieved using a gradual weighted fusion method. The research results demonstrate that this method significantly improves both image quality and computational efficiency, making it effective for generating and processing panoramic images. Experimental results further confirm that the method enhances stitching accuracy while also increasing processing speed, showcasing its high practical value.

关键词： Accuracy Surveillance Robot vision systems Visual systems Distortion Feature extraction Cameras Security image stitching Lenses

来源：评论

学校读者我要写书评

暂无评论

Research on Unmarked Motion Action Recognition Technology Based on Computer vision

Research on Unmarked Motion Action Recognition Technology Ba...

引用

image processing, Electronics and Computers (IPEC), Asia-Pacific Conference on

作者： Lun Zhao Shandong Vocational College of Science and Technology Weifang China

ISBN: (数字)9798350374407

ISBN: (纸本)9798350374414

The main purpose of this study is to explore the issues of real-time, accurate, and unmarked recognition of sports movements in recent years. By reviewing the relevant research on machine learning or deep learning for specific sports or target actions based on computer vision image data input, the aim is to provide references for the application of unmarked motion capture technology in the field of sports motion recognition. The research employed a literature review methodology, conducting searches in six databases, namely Web of Science, PubMed, Scopus, Google Scholar, IEEE Xplore, and China National Knowledge Infrastructure (CNKI), covering publications from January 2000 to June 2020. Through boolean logic operations on the retrieved literature, key information such as first author/publication year, types/targets of motion, participant information, camera parameters, image feature extraction techniques, action recognition algorithms, evaluation methods for action recognition quality, training and validation methods for image data, and performance metrics for action recognition were extracted. After screening, a total of 23 articles were included in the study. The findings revealed that $39 \%$ of the studies utilized machine learning algorithms based on support vector machines, while $35 \%$ employed deep learning algorithms based on convolutional neural networks. Commonly used evaluation metrics for action recognition quality included classification accuracy, confusion matrix, and displacement error. The development of computer vision motion capture, models, and algorithms demonstrated promising applications in areas such as action technique recognition and sports performance analysis. Traditional machine learning algorithms like support vector machines and principal component analysis remain dominant in action recognition technology; however, in certain scenarios, the performance of deep learning algorithms surpassed that of traditional machine learning methods.

关键词： Deep learning Support vector machines Computer vision machine learning algorithms image recognition Cameras Feature extraction Motion capture Real-time systems Sports

来源：评论

学校读者我要写书评

暂无评论

A study on real-time image processing applications with edge computing support for mobile devices 25

A study on real-time image processing applications with edge...

引用

25th IEEE/ACM International Symposium on Distributed Simulation and Real Time applications (DS-RT)

作者： Mattia, Gabriele Proietti Beraldi, Roberto Sapienza Univ Rome Dept Comp Control & Management Engn Antonio Ruber Rome Italy

ISBN: (纸本)9781665433266

Different libraries allow performing computer vision tasks, e.g., object recognition, in almost every mobile device that has a computing capability. In modern smartphones, such tasks are compute-intensive, energy hungry computation running on the GPU or the particular machine Learning (ML) processor embedded in the device. Task offloading is a strategy adopted to move compute-intensive tasks and hence their energy consumption to external computers, in the edge network or in the cloud. In this paper, we report an experimental study that measure under different mobile computer vision set-ups the energy reduction when the inference of an image processing is moved to an edge node, and the capability to still meet real-time requirements. In particular, our experiments show that offloading the task - in our case real-time object recognition - to a possible next-to-the-user node allows saving about the 70% of battery consumption while maintaining the same frame rate (fps) that local processing can achieve.

关键词： Performance evaluation Computer vision image processing image edge detection machine learning Particle measurements Real-time systems

来源：评论

学校读者我要写书评

暂无评论

image processing using Cloud for Surveillance 23

Image Processing using Cloud for Surveillance

引用

Proceedings of the 5th International Conference on Information Management & machine Intelligence

作者： Shivam Tiwari Aarhee Phukan T R Vedhavathy Department of Networking and Communications SRM Institute of Science and Technology India Department of Networking and Communication SRM Institute of Science and Technology India

ISBN: (纸本)9798400709418

In the era of digitization and big data, the world is inundated with an ever-growing volume of visual content, be it images or videos. As organizations strive to harness the potential of these multimedia data sources, there is an increasing need for advanced image processing techniques that can automate the analysis and extraction of valuable information. Amazon Web Services (AWS) Rekognition emerges as a powerful solution in this landscape, offering a comprehensive system for image and video analysis through the lens of machine learning and computer vision. This paper delves into the realm of image processing using AWS Rekognition, unveiling the transformative capabilities of this cloud-based service and its applications in various domains. As we embark on this journey, we will explore the principles, methodologies, and real-world implications of leveraging AWS Rekognition for image analysis.

关键词： AWS Rekognition

来源：评论

学校读者我要写书评

暂无评论

Design of Multi View Natural Language Query System on machine vision

Design of Multi View Natural Language Query System on Machin...

引用

Power Electronics, Computer applications (ICPECA), IEEE International Conference on

作者： Quanrong Fang Amazon (China) Investment Co. Ltd Beijing China

In various fields such as medical imaging, object detection, and video surveillance, multi view natural language query systems utilize image data to provide a more comprehensive perspective, allowing users to intuitively query and obtain information. Due to the lack of a deep understanding of natural language in the hard coded matching rule method, the query results do not match the user's intentions and are difficult to meet practical application needs. Therefore, this article introduces machine vision algorithms for optimization and improvement. This article first discusses the system architecture of four modules: data input and preprocessing, visual feature extraction, natural language understanding and matching, and result generation and feedback. Then, the application of machine vision technology in the system was analyzed using two calculation formulas: grayscale conversion and binarization, and natural language processing technology was briefly discussed. Subsequently, a context understanding module was added to construct a multi view natural language query system based on machine vision. Finally, two sets of simulation experiments were conducted to draw the following conclusion: compared with traditional methods, the overall average improvement in image recognition accuracy indicators is about 14.3%, while the overall average improvement in response speed indicators is about 26.5%. This research system can effectively process images from different perspectives and match them with natural language queries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Authentication and Verification in Human-Robot Cooperative Robotic Cells using Stereo vision and Gesture Control

Authentication and Verification in Human-Robot Cooperative R...

引用

International image processing, applications and Systems Conference (IPAS)

作者： Gábor Kovács Tamás Szirányi Machine Perception Research Laboratory HUN-REN Institute for Computer Science and Control Budapest Hungary

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

The integration of human-robot interaction (HRI) technologies with industrial automation has become increasingly essential for enhancing productivity and safety in manufacturing environments. In this paper, we propose a novel approach to address these challenges by using stereo vision and gesture control in cooperative robotic cells. Our system enables seamless authentication of operators and real-time verification of task execution, ensuring compliance with established protocols and safety *** features of our system include its gesture-based operation with gesture recognition algorithms, allowing operators to interact with robotic systems intuitively and efficiently. By leveraging stereo vision, our system accurately tracks the operators’ movement within the workspace, facilitating precise task execution and object *** present a detailed description of our system architecture, experimental configuration, and real-world performance assessment. Our results demonstrate the effectiveness and feasibility of our approach in enhancing operational efficiency, ensuring quality, and improving the overall user experience in industrial automation.

关键词： Automation Service robots Tracking Human-robot interaction Authentication Systems architecture User experience Real-time systems Stereo vision Safety

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：