检索结果-内蒙古大学图书馆

作者： Mercuri, Matteo University of Illinois at Chicago

学位级别：M.S., Master of Science/Master of Surgery

The present work focuses on learning how to use the hardware and software of a Time-of-Flight camera and then creating C++ programs that try to lay the basis for future ones that would be implemented in bigger applications that are able to tackle and solve the most common problems related to 3D machine vision. All the code and programs present in the thesis are born and developed with the key idea in mind that they can provide a foundation for future work as the starting point for more complex projects related to 3D computer vision and thus be implemented in applications such as bin-picking, autonomous driving, quality inspection and so on. The C++ programs developed in this thesis, along with smaller questions, address four main problems in the field of computer vision: Registration, CAD model creation, Segmentation and Object Recognition. Registration consists of aligning various 3D point clouds taken from different points of view of the same object so as to reconstruct a full 3D model of the object. CAD model creation is usually the step following Registration and it consists in creating a 3D mesh of the registered object. This mesh can be exported in AutoCAD or any other 3D CAD software to perform further studies and analysis on the object. Segmentation consists of dividing point clouds in multiple parts and pieces, which can be then studied independently. Finally, the last topic studied and developed in the thesis is Object Recognition, which consists in the ability to locate and recognize objects from a 3D point cloud.

关键词： Time-of-Flight 3D machine vision vision algorithms Object Recognition

来源：评论

学校读者我要写书评

暂无评论

Gear fault diagnosis research based on GAF-TFR-2DCV with small sample size

引用

AIN SHAMS ENGINEERING JOURNAL 2025年第5期16卷

作者： Wang, Zhe Shen, Jiaxing Zhang, Xingyuan Yu, Yinghua Wang, Yan Zhu, Hu Zhang, Lianglu Liaoning Tech Univ Sch Mech Engn Fuxin 123000 Peoples R China Liaoning Tech Univ Res Inst Technol & Equipment Exploitat & Utilizat Fuxin 123000 Peoples R China

To solve the problem of insufficient precision of gear fault diagnosis with small sample size, an adaptive floating convolutional sequence pattern neural network recognition method based on the combination of simplified Gramian Angle field and time-frequency feature images is proposed. One-dimensional data is converted to twodimensional real-time data by simplifying Gramian Angle field. The time domain data and time frequency data are mixed enhanced by fast Fourier transform to obtain feature enhanced image-like data. The feature-enhanced image dataset generated by this method has a high degree of intra-group consistency in data features, which is beneficial to fault identification. The adaptive floating convolutional sequence model is used to construct neural network to identify image-like data and improve the accuracy of gear fault diagnosis with small samples. Moreover, the diagnosis method has strong robustness and high engineering application value.

关键词： Gear fault diagnosis Gramian angle field Time-frequency diagram Convolutional Neural Networks vision algorithms

来源：评论

学校读者我要写书评

暂无评论

Boosting visual servoing performance through RGB-based methods

ROBOTIC INTELLIGENCE AND AUTOMATION

引用

ROBOTIC INTELLIGENCE AND AUTOMATION 2023年第4期43卷 468-475页

作者： Fei, Haolin Wang, Ziwei Tedeschi, Stefano Kennedy, Andrew Univ Lancaster Sch Engn Lancaster England Welding Inst Ltd Cambridge England Univ Lancaster Sch Engn Lancaster England

PurposeThis paper aims to evaluate and compare the performance of different computer vision algorithms in the context of visual servoing for augmented robot perception and autonomy. Design/methodology/approachThe authors evaluated and compared three different approaches: a feature-based approach, a hybrid approach and a machine-learning-based approach. To evaluate the performance of the approaches, experiments were conducted in a simulated environment using the PyBullet physics simulator. The experiments included different levels of complexity, including different numbers of distractors, varying lighting conditions and highly varied object geometry. FindingsThe experimental results showed that the machine-learning-based approach outperformed the other two approaches in terms of accuracy and robustness. The approach could detect and locate objects in complex scenes with high accuracy, even in the presence of distractors and varying lighting conditions. The hybrid approach showed promising results but was less robust to changes in lighting and object appearance. The feature-based approach performed well in simple scenes but struggled in more complex ones. Originality/valueThis paper sheds light on the superiority of a hybrid algorithm that incorporates a deep neural network in a feature detector for image-based visual servoing, which demonstrates stronger robustness in object detection and location against distractors and lighting conditions.

关键词： vision algorithms RGB-based methods Robot perception

来源：评论

学校读者我要写书评

暂无评论

A Method Supporting Hardware Implementation of Vector Quantization Module in HoG Algorithm 31

A Method Supporting Hardware Implementation of Vector Quanti...

引用

31st International Conference on Mixed Design of Integrated Circuits and System (MIXDES)

作者： Dlugosz, Zofia Talaska, Tomasz Dlugosz, Rafal Bydgoszcz Univ Sci & Technol Fac Telecommun Comp Sci & Elect Engn Kaliskiego 7 PL-85796 Bydgoszcz Poland Aptiv Serv Poland Ul Podgorki Tynieckie 2 PL-30399 Krakow Poland

ISBN: (纸本)9798350375701;9788363578268

In this work, we dealt with topics related to computer vision, with particular focus on solutions aimed at ensuring computational efficiency. One of the algorithms often used in computer vision is Histogram of Oriented Gradients (HoG), often used in object detection in video sequences. In many applications, this algorithm should be able to run in real time, simultaneously on devices with low computing power. In this work, we attempted to implement one of its key stages at the level of digital specialized circuits (also suitable for integrated circuit realization). At this stage, it is determined which of the bins the vector calculated on the basis of previously calculated gradients for the x and y coordinates belongs to. We presented solutions for different numbers of bins, but also solutions that can be considered more general, i.e. allowing to change the number of bins.

关键词： HoG algorithm vector quantization real time systems hardware implementation vision algorithms

来源：评论

学校读者我要写书评

暂无评论

Toy vision-Guided 3D Robotic Arm in JavaScript

引用

COMPUTING IN SCIENCE & ENGINEERING 2018年第1期20卷 43-49页

作者： DiPierro, Massimo Depaul Univ Comp Chicago IL 60604 USA

Modern JavaScript has the power to access the capabilities of the underlying architecture in a simple and portable manner and without installing third-party libraries. This article shows how a one-page web application can be built that connects to the camera, processes the video stream, extracts images, and detects motion. The detected motion is then used to control a 3D robotic arm rendered using Web Graphics Library within the same page. Although the scope of this paper is purely didactic, the framework can easily be extended and used in a classroom setting for experimentation with different vision algorithms.

关键词： Control Engineering Computing Image Motion Analysis Internet Java Manipulators Object Detection Robot vision Video Streaming vision algorithms Classroom Setting Web GL Detected Motion Video Stream One Page Web Application Java Script Toy vision Guided 3 D Robotic Arm Streaming Media Manipulators Computer Languages Robot vision Systems Browsers Libraries Web GL vision algorithms The Rise Of Java Script Image Extraction Motion Detection 3 D Robotic Arm Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

vision SYSTEM SUPPORTING THE PILOT IN VARIABLE LIGHT CONDITIONS

引用

EKSPLOATACJA I NIEZAWODNOSC-MAINTENANCE AND RELIABILITY 2019年第1期21卷 60-67页

作者： Szczerba, Piotr Rzucidlo, Pawel Szczerba, Zygmunt Drupka, Grzegorz Rzeszow Univ Technol Fac Mech Engn & Aeronaut Al Powstancow Warszawy 12 PL-35959 Rzeszow Poland

The aim of this study is to demonstrate the applicability of contemporary optoelectronic systems supported by image processing algorithms in aviation. Optoelectronic systems can support the pilot's work or the work of an Unmanned Aerial Vehicle (UAV) operator after being installed in the cockpit of the pilot or in a ground station. The origin of the problem is related to the aspects of safe operation of the aircraft in the conditions of dynamically, changing ambient light observed by the aircraft pilot or operator monitoring the monitor at the ground station and observing the image from the camera installed on the UAV The proposed solution is to help avoid situations in which the pilot's/operators situational awareness deteriorates due to strong optical phenomena.

关键词： indicator pilot operator ground station UAV operation optical phenomena vision algorithms adaptive algorithms reliability of operations

来源：评论

学校读者我要写书评

暂无评论

Verification of the Relative Distance Measurement Method for Pico-satellites in Constellation

引用

IFAC-PapersOnLine 2018年第12期51卷 100-105页

作者： Nebylov, A. Padron, A. Medina Knyazhsky, A. State University of Aerospace Instrumentation 67 Bolshaya Morskaya Saint-Petersburg190000 Russia Polytechnique de Montréal Département Génie électrique 2900 Edouard-Monpetit MontrealQCH3T 1J4 Canada

This paper considers the optical relative navigation method for the small satellites, describes the algorithms of the image processing and calculating the relative distance and orientation. Different methods and approaches exist but need to be adapted or improved based on robust algorithms for both detection and range of multiple space crafts. Originality of the solution is to extend optical with image processing and vision algorithms to space relative navigation, some experimental and preliminary results are also reported at the article. © 2018

关键词： Image processing Optical data processing Satellites Motion parameters pico satellited Relative distances Relative motion Relative navigation Robust algorithm vision algorithms

来源：评论

学校读者我要写书评

暂无评论

Black Ice Detection System Using Kinect 30

Black Ice Detection System Using Kinect

引用

30th Annual IEEE Canadian Conference on Electrical and Computer Engineering (IEEE CCECE)

作者： Abdalla, Younis E. Iqbal, M. T. Shehata, M. Mem Univ Fac Engn St John NF Canada

ISBN: (纸本)9781509055388

An ice detection system is designed using an imaging sensor which has a forward field of a view direction. The proposed system solves the problem of detecting the Black Ice on various surfaces using a depth imaging sensor based on Kinect device. In some places where ice cannot be seen easily from a distance, especially in low visibility, by a human eye, it would be highly dangerous and causes slip. The designed system can detect the forming ice at a distance from 82cm up to 1.52m from the camera. Ice detection system has been tested in five different backgrounds: wood, glass, ceramic, plastic and concrete, and indeed it showed high proficiency.

关键词： Black Ice Detection vision algorithms Depth Sensor Application

来源：评论

学校读者我要写书评

暂无评论

Black Ice detection system using Kinect

Black Ice detection system using Kinect

引用

IEEE Canadian Conference on Electrical and Computer Engineering

作者： Younis E. Abdalla M. T. Iqbal M. Shehata Faculty of Engineering Memorial University St. John's NL Canada

关键词： Black Ice Detection vision algorithms Depth Sensor Application

来源：评论

学校读者我要写书评