检索结果-内蒙古大学图书馆

A Survey of computer vision Detection, Visual SLAM algorithms, and Their Applications in Energy-Efficient Autonomous Systems

引用

ENERGIES 2024年第20期17卷 5177页

作者： Chen, Lu Li, Gun xie, Weisi Tan, Jie Li, Yang Pu, Junfeng Chen, Lizhu Gan, Decheng Shi, Weimin Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu 611731 Peoples R China Yangtze Normal Univ Sch Elect Informat Engn Chongqing 408100 Peoples R China Chongqing Univ Sch Microelect & Commun Engn Chongqing 400044 Peoples R China

Within the area of environmental perception, automatic navigation, object detection, and computer vision are crucial and demanding fields with many applications in modern industries, such as multi-target long-term visual tracking in automated production, defect detection, and driverless robotic vehicles. The performance of computer vision has greatly improved recently thanks to developments in deep learning algorithms and hardware computing capabilities, which have spawned the creation of a large number of related applications. At the same time, with the rapid increase in autonomous systems in the market, energy consumption has become an increasingly critical issue in computer vision and SLAM (Simultaneous Localization and Mapping) algorithms. This paper presents the results of a detailed review of over 100 papers published over the course of two decades (1999-2024), with a primary focus on the technical advancement in computer vision. To elucidate the foundational principles, an examination of typical visual algorithms based on traditional correlation filtering was initially conducted. Subsequently, a comprehensive overview of the state-of-the-art advancements in deep learning-based computer vision techniques was compiled. Furthermore, a comparative analysis of conventional and novel algorithms was undertaken to discuss the future trends and directions of computer vision. Lastly, the feasibility of employing visual SLAM algorithms in the context of autonomous vehicles was explored. Additionally, in the context of intelligent robots for low-carbon, unmanned factories, we discussed model optimization techniques such as pruning and quantization, highlighting their importance in enhancing energy efficiency. We conducted a comprehensive comparison of the performance and energy consumption of various computer vision algorithms, with a detailed exploration of how to balance these factors and a discussion of potential future development trends.

关键词： computer vision object detection visual tracking energy efficiency visual SLAM deep learning driverless robotic vehicles

来源：评论

学校读者我要写书评

暂无评论

Towards new-generation of intelligent welding manufacturing: A systematic review on 3D vision measurement and path planning of humanoid welding robots

引用

MEASUREMENT 2025年 242卷

作者： Chi, Peng Wang, Zhenmin Liao, Haipeng Li, Ting Wu, xiangmiao Zhang, Qin South China Univ Technol Sch Mech & Automot Engn Guangzhou 510641 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 511400 Peoples R China

In recent years, intelligent welding technology has emerged as a prominent focus within the welding domain, amalgamating a diverse array of sophisticated technologies, including robotics, computer vision, artificial intelligence, and sensor systems. This integration heralds unprecedented levels of automation in welding processes, endowing them with heightened efficiency, precision, and cognitive capabilities. Notably, scholarly attention has been dedicated to the realms of intelligent welding manufacturing and welding robotics. However, a discernible lacuna exists in the form of a comprehensive review elucidating the pivotal technologies underpinning welding robots, while research about autonomous mobile welding robots appears to have encountered a developmental impasse. In response, this study undertakes a systematic literature review to scrutinize the core technologies of humanoid welding robots (HWR), positing their elevated research prospects within the milieu of next-generation intelligent welding manufacturing. This study explores the hardware of humanoid welding robots as an emerging technology, drawing on current advancements in humanoid robotics. The key technologies relevant to both humanoid and welding robots are also examined, highlighting their integration and potential applications. Initially, the discourse delves into hand-eye calibration methodologies, delineating a multifaceted approach predicated upon a multi-coordinate system tailored to HWR. Subsequently, the significance of visual-based pose estimation and three-dimensional (3D) reconstruction techniques is underscored, given their instrumental role in furnishing HWR with environmental cognition, a discourse expounded meticulously. Additionally, meticulous scrutiny is accorded to mobile robot path planning and dual-robot trajectory planning methodologies, pivotal for orchestrating welding operation sequences tailored to HWR. To assess the job completion and potential applications of HWR, this pa

关键词： Humanoid welding robot 3D target measurement Hand-eye calibration Visual-based 3D reconstruction Trajectory planning

来源：评论

学校读者我要写书评

暂无评论

Advancements in machine learning techniques for threat item detection in x-ray images: a comprehensive survey

引用

INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL 2024年第4期13卷 40页

作者： Singh, Archana Dhiraj Acad Sci & Innovat Res AcSIR Ghaziabad 201002 India CSIR Cent Elect Engn Res Inst CSIR CEERI Pilani 333031 India

x-ray security screening is crucial in detecting prohibited objects and explosive materials within passenger luggage, thus ensuring the safety of airports, railway stations, and aircraft. Modern x-ray imaging systems and advanced object detection technologies enhance the overall efficiency of security screening processes by enabling the detection of dangerous items through intelligent algorithms. Indeed, recent developments in computer vision and machine learning techniques have revolutionized the field of x-ray image-based analysis, making it significantly easier to process and interpret x-ray images. This comprehensive literature survey explores the methodologies, advancements, and challenges associated with object detection by applying deep learning techniques, particularly those based on convolutional neural networks and transformers. In this paper, a taxonomy-based approach has been adopted to comprehensively elucidate the existing landscape of x-ray imaging-based algorithms for security applications and the recent strides made in computer vision technologies. Our study looks at supervised and unsupervised learning methods for CNN and transformer-based architectures, mainly focusing on tasks like image classification, object detection, instance segmentation, and anomaly detection. Furthermore, we establish a performance benchmark and delineate the evaluation criteria applied. This endeavor also entails meticulously exploring well-established x-ray datasets commonly employed to train and evaluate x-ray security imaging algorithms. This study also analyzes the available deep learning techniques, along with the problem statement, benchmark datasets, corresponding references, and their performance metric details in terms of the best-reported scores. Drawing insights from current deep learning trends and anticipating future advancements, this paper culminates in discussing the contemporary state of x-ray security imagery.

关键词： Survey Deep learning Taxonomy x-ray imaging Object detection computer vision

来源：评论

学校读者我要写书评

暂无评论

Comparison of Indoor Position Recognition Accuracy Using Grid Pattern Tracking Autonomous Mobile Robot

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2025年 1-14页

作者： Kim, Ki-Hyun Choi, Sang-Yule Choi, Jae-Hoon Kim, Jung-Ju Hoseo Univ Dept Automot ICT Cheonan South Korea Induk Univ Dept Mechatron Engn Seoul South Korea Hoseo Univ Dept Robot Cheonan South Korea Hoseo Univ Dept Intelligent Robot Cheonan South Korea

Existing studies on indoor position recognition employ diverse evaluation methods, which complicates direct accuracy comparisons across techniques. To address this issue, this study proposes a novel framework for evaluating the accuracy of indoor position recognition methods. The proposed framework evaluates accuracy by using the position recognition results of a grid-pattern-tracking autonomous mobile robot (GPT-AMR) as a benchmark. To validate the proposed evaluation method, a comparative analysis was conducted on four position recognition algorithms: (1) a computer vision-based algorithm, (2) a Bluetooth Low Energy (BLE)-based trilateration algorithm, (3) a BLE-based adaptive trilateration algorithm, and (4) a least squares method (LSM)-based algorithm. Experimental results demonstrated that the proposed evaluation method, which employs GPT-AMR, offers improved speed, accuracy, and practical applicability compared to conventional approaches. Furthermore, this method enables objective comparisons and evaluations of a wide range of indoor position recognition technologies, including both computer vision- and BLE-based algorithms, using a standardized criterion. Future research will focus on systematically validating the generalizability of the proposed method across different indoor environments and operational conditions. This study aims to advance indoor position recognition technology for autonomous mobile robots (AMRs) and improve their applicability in various service robotics domains.

关键词： Autonomous mobile robot Indoor position recognition Bluetooth low energy Trilateration Least squares method Adaptive trilateration

来源：评论

学校读者我要写书评

暂无评论

A computer vision Algorithm for Path Planning in Mobile robots 22

A Computer Vision Algorithm for Path Planning in Mobile Robo...

引用

22nd IEEE Conference on Pervasive and intelligent Computing

作者： Ruggieri, Claudio Russo, Miriana Santoro, Corrado Santoro, Federico Fausto STMicroelect Syst Res & Applicat I-95121 Catania Italy Univ Catania Dept Math & Informat Catania Italy

ISBN: (纸本)9798331522759;9798331522742

In robotics, route planning is essential to ensure the safe and efficient movement of robots within the workplace. This process involves determining a trajectory, usually a series of points in the workspace, to achieve a specific goal. It is essential to consider criteria such as reducing the length of the route, the number of manoeuvres and the avoidance of obstacles. Route planning techniques generally require modelling the environment, representing both the structure and the obstacles (fixed or mobile), and the implementation of algorithms that generate the trajectory through the free areas of the environment. This approach often includes constructing a graph of possible trajectories and using minimum path search algorithms, such as A*. This article presents a route planning algorithm that uses Voronoi diagrams and uses artificial vision algorithms. In addition, a case study is described in which the proposed technique is applied to guide an automated system through a maze drawn on a whiteboard by a user.

关键词： path planning robotic systems virtual environment voronoi diagrams opencv

来源：评论

学校读者我要写书评

暂无评论

A Review of Vehicle Detection techniques for intelligent Vehicles

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第8期34卷 3811-3831页

作者： Wang, Zhangu Zhan, Jun Duan, Chunguang Guan, xin Lu, Pingping Yang, Kai Jilin Univ State Key Lab Automobile Simulat & Control Changchun 130022 Peoples R China

Robust and efficient vehicle detection is an important task of environment perception of intelligent vehicles, which directly affects the behavior decision-making and motion planning of intelligent vehicles. Due to the rapid development of sensor and computer technology, the algorithm and technology of vehicle detection have been updated rapidly. But, there are few reviews on vehicle detection of intelligent vehicles, especially covering all kinds of sensors and algorithms in recent years. This article presents a comprehensive review of vehicle detection approaches and their applications in intelligent vehicle systems to analyze the development of vehicle detection, with a specific focus on sensor types and algorithm classification. First, more than 300 research contributions are summarized in this review, including all kinds of vehicle detection sensors (machine vision, millimeter-wave radar, lidar, and multisensor fusion), and the performance of the classic and latest algorithms was compared in detail. Then, the application scenarios of vehicle detection with different sensors and algorithms were analyzed according to their performance and applicability. Moreover, we also systematically summarized the methods of vehicle detection in adverse weather. Finally, the remaining challenges and future research trends were analyzed according to the development of intelligent vehicle sensors and algorithms.

关键词： Vehicle detection Feature extraction intelligent vehicles Deep learning Semantics Machine vision Image color analysis Deep learning information fusion intelligent vehicle sensors vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Evaluation of mobile autonomous robot in trajectory optimization

引用

COMPUTING 2023年第12期105卷 2725-2745页

作者： Palacios, Rodrigo Henrique Cunha Bertoncini, Joao Paulo Scarabelo Uliam, Gabriel Henrique Oliveira Mendonca, Marcio de Souza, Lucas Botoni Fed Technol Univ Parana Dept Comp Ave Alberto Carazzai 1640Ctr BR-86300000 Cornelio Procopio PR Brazil Fed Technol Univ Parana Dept Elect Engn Ave Alberto Carazzai 1640Ctr BR-86300000 Cornelio Procopio PR Brazil

The demand for mobile robotics applications has grown considerably in recent years, especially due to the advent of industry 4.0, which has as one of its pillars the autonomous robotics field, the subject of this research. In this context, autonomous mobile robots must interact with the world to achieve their goals. One of the main challenges regarding mobile robots is the navigation problem: a robot can face several problems according to the type of sensor that is chosen in each application. The use of computer vision as a navigation tool in robotics represents an interesting alternative for controlling the movement of a mobile robot, and represent several vision techniques that gained more space in the last few years. Therefore, this work's research proposes the development of a control center to assist navigation and location of mobile robots in closed environments using the global view technique. In addition to computer vision, wireless communication (WiFi) between the exchange and the robots has been investigated to date. The results obtained in the initial steps of the project's development were promising, in which data from an autonomous robot is compared with a human-guided robot. Through the algorithm developed for the project, it was possible to transform the collected data into the robot's kinematics necessary to take the correct path to the destination using multivalued logic as a control algorithm. The optimization of the trajectory between the origin and the destination is performed using the A* and Dijkstra algorithms for calculating the shortest path.

关键词： Mobile robotics computer vision Artificial intelligence Image processing Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Experiments with cooperative robots that can detect object's shape, color and size to perform tasks in industrial workplaces

引用

INTERNATIONAL JOURNAL OF intelligent ROBOTICS AND APPLICATIONS 2024年第1期8卷 179-192页

作者： Titu, Md Fahim Shahoriar Haque, S. M. Rezwanul Islam, Rifad Hossain, Akram Qayum, Mohammad Abdul Khan, Riasat North South Univ Elect & Comp Engn Dhaka Bangladesh

Automation and human-robot collaboration are increasing in modern workplaces such as industrial manufacturing. Nowadays, humans rely heavily on advanced robotic devices to perform tasks quickly and accurately. Modern robots with computer vision and artificial intelligence are gaining attention and popularity rapidly. This paper demonstrates how a robot can automatically detect an object's shape, color, and size using computer vision techniques and act based on information feedback. In this work, a powerful computational model for a robot has been developed that distinguishes an object's shape, size, and color in real time with high accuracy. Then it can integrate a robotic arm to pick a specific object. A dataset of 6558 images of various monochromatic objects has been developed, containing three colors against a white background and five shapes for the research. The designed system for detection has achieved 99.8% success in an object's shape detection. Also, the system demonstrated 100% success in the object's color and size detection with the OpenCV image processing framework. On the other hand, the prototype robotic system based on Raspberry Pi-4B has achieved 80.7% accuracy for geometrical shape detection and 81.07%, and 59.77% accuracy for color recognition and distance measurement, respectively. Moreover, the system guided a robotic arm to pick up the object based on its color and shape with a mean response time of 19 seconds. The idea is to simulate a workplace environment where a worker will ask the robotic systems to perform a task on a specific object. Our robotic system can accurately identify the object's attributes (e.g., 100%) and is able to perform the task reliably (81%). However, reliability can be improved by using a more powerful computing system, such as the robotic prototype. The article's contribution is to use a cutting-edge computer vision technique to detect and categorize objects with the help of a small private dataset to shorten the trai

关键词： Automation Bounding box regression computer vision Detection Image processing Library OpenCV Robot

来源：评论

学校读者我要写书评

暂无评论

A review of the emotion recognition model of robots

引用

APPLIED INTELLIGENCE 2025年第6期55卷 1-33页

作者： Zhao, Mingyi Gong, Linrui Din, Abdul Sattar Univ Sains Malaysia Sch Elect & Elect Engn Engn Campus Nibong Tebal 14300 Penang Malaysia Univ Macau Fac Sci & Technol Macau Peoples R China

Being able to experience emotions is a defining characteristic of machine intelligence, and the first step in giving robots emotions is to enable them to accurately recognize and understand human emotions. The initial task to achieve this is to quantify abstract human emotions into concrete data. Combining this with deep learning techniques, a variety of machine models for recognizing human emotions can be constructed to achieve efficient human-robot interaction. Along this line of thought, this paper comprehensively combs through the development paths of emotion quantification, emotion modeling, and machine emotion recognition models based on various signals with practical examples. We focus on summarizing the machine emotion recognition models in recent years, classifying them into four broad categories according to the input signals: vision-based, language-based, physiological signal-based emotion recognition models and multimodal emotion recognition models for in-depth discussion, revealing the strengths and weaknesses of these models and potential application *** particular, this study identifies multimodal emotion recognition models as a key direction for future research, which significantly improve recognition accuracy and robustness by integrating multiple data sources. Finally, the article discusses the challenges and improvement directions for emotion recognition models, providing an important reference for promoting intelligent and emotional human-computer interaction. Figure 1. shows the framework of this paper.

关键词： Emotion recognition Artificial emotional intelligence Machine learning Social robots Human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in medical science: a review

引用

IRISH JOURNAL OF MEDICAL SCIENCE 2024年第3期193卷 1419-1429页

作者： Bindra, Simrata Jain, Richa Motilal Nehru Coll Dept Phys Benito Juarez Rd New Delhi 110021 India

Artificial intelligence (AI) is a technique to make intelligent machines, mainly by using smart computer programs. It is based on a statistical analysis of data or machine learning. Using machine learning, software algorithms are designed according to the desired application. These techniques are found to have the potential for advancement in the medical field by generating new and significant perceptions from the data generated using various types of healthcare tests. Artificial intelligence (AI) in medicine is of two types: virtual and physical. The virtual part decides the treatment using electronic health record systems using various sensors whereas the physical part assists robots to perform surgeries, implants, replacement of various organs, elderly care, etc. Using AI, a machine can examine various kinds of health care test reports in one go which could save the time, money, and increase the chances of the patient to be treated without any hassles. At present, artificial intelligence (AI) is used while deciding the treatment, and medications using various tools which could analyze x-rays, CT scans, MRIs, and any other data. During the COVID pandemic, there was a huge/massive demand for AI-supported technologies and many of those were created during that time. This study is focused on various applications of AI in healthcare.

关键词： Artificial intelligence (AI) computer vision Clustered regularly interspaced short palindromic repeats (CRISPR) Deep learning Machine learning MYCIN

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

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

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：