检索结果-内蒙古大学图书馆

2024 International Symposium on Intelligent Signal Processing and Communication systems, ISPACS 2024

作者： Riku, Kurihara Matsushima, Kousuke Advanced Engineering Course National Institute of Technology Kurume College Kurume Japan Department of Control and Information Systems Engineering National Institute of Technology Kurume College Kurume Japan

ISBN: (纸本)9798350389210

The Perspective-n-Point (PnP) problem is a fundamental challenge in engineering that plays a crucial role in fields such as computer vision and augmented reality. This problem aims to estimate the position and orientation (pose) of a camera from known 3D points and their corresponding 2D projections on the image plane. With recent technological advancements, application areas such as autonomous vehicles, drones, and robotics are demanding increasingly faster and more accurate camera pose estimation. To address this challenge, we have introduced an improved Sparrow Search Algorithm (SSA) with the capability to dynamically restrict the search area. While the conventional SSA demonstrated excellent optimization capabilities, it faced efficiency issues when searching in high-dimensional spaces, such as those encountered in PnP problems. Our enhancement enables the algorithm to leverage information obtained during the search process to gradually narrow down the search area, thereby more efficiently locating the optimal solution. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mobile Generalized Category Discovery for Road Damage Detection

Mobile Generalized Category Discovery for Road Damage Detect...

引用

2024 International Symposium on Intelligent Signal Processing and Communication systems, ISPACS 2024

作者： Rintaro, Akashi Matsushima, Kousuke Advanced Engineering Course National Institute of Technology Kurume College Kurume Japan Department of Control and Information Systems Engineering National Institute of Technology Kurume College Kurume Japan

ISBN: (纸本)9798350389210

In recent years, there has been a considerable amount of research conducted on the topic of road damage detection using deep learning techniques, with the aim of supporting the safe driving of mobility vehicles. To date, convolutional neural networks and supervised learning with large datasets have been employed for road damage detection, demonstrating high classification accuracy. However, all images in the dataset must be manually labeled. Moreover, images cannot be classified into classes that are not included in the training dataset. The real world presents a vast array of damage types, and the unlabeled input images encompass both known and unknown classes. This renders the system unsuitable for use in providing safe driving support for mobility. Considering this background, Generalized Category Discovery (GCD) has been put forth as a potential solution, aiming to achieve accurate classification in a comprehensive setting where both known and unknown classes are present in unlabeled data. The purpose of this study is to propose a novel model for GCD with the aim of providing safe driving assistance for mobility. The model is based on the pre-trained MobileViT. To validate its performance, this paper examines its performance on the general CIFAR-10 and CIFAR-100 datasets and on a road damage-specific dataset, and discusses the challenges encountered. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Lens Visual SLAM with Integrated Moving Object Removal using Unsupervised Models 1

Multi-Lens Visual SLAM with Integrated Moving Object Removal...

引用

1st International Conference on Robotics, engineering, Science, and Technology, RESTCON 2024

作者： Hara, Ryoichirou Matsushima, Kousuke Kurume College Advanced Engineering Course National Institute of Technology Fukuoka Japan Kurume College National Institute of Technology Department of Control and Information Systems Engineering Fukuoka Japan

ISBN: (纸本)9798350348842

In advanced Driver-Assistance systems (ADAS), SLAM (Simultaneous Localization and Mapping) technology is required to accurately estimate the position and orientation of onboard cameras. Compared to LiDAR SLAM, Visual SLAM has the advantage of collecting rich environmental information at a lower cost. However, the accuracy of the estimated pose and map construction is greatly reduced by moving objects in the camera scene. To solve this problem, a multi-camera SLAM has been proposed, which works robustly in dynamic environments by using multiple cameras to acquire more feature points from omnidirectional environmental information. In this paper, we propose a robust SLAM system based on a multi-camera SLAM system combined with object detection and semantic segmentation networks. We then evaluate the robustness of the proposed method by comparing it to SLAM systems that do not remove moving objects. Experimental results showed that the Absolute Trajectory Error and the Relative Position Error performed better than conventional SLAM by masking moving objects. It also showed that more static objects were detected and constructed in the map. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Monocular 3D Object Detection for Safe Driving Assistance

Uncertainty-aware Monocular 3D Object Detection for Safe Dri...

引用

2024 International Symposium on Intelligent Signal Processing and Communication systems, ISPACS 2024

作者： Ida, Masahiko Matsushima, Kousuke Advanced Engineering Course National Institute of Technology Kurume College Fukuoka Japan Department of Control and Information Systems Engineering National Institute of Technology Kurume College Fukuoka Japan

ISBN: (纸本)9798350389210

Safety is of utmost importance when utilizing mobile vehicles. The introduction of safe driver assistance and automated driving systems will not only solve this problem, but also reduce road accidents and make driving smoother. To achieve these goals, 3D object detection is an essential technology and various methods have been proposed. Among these, monocular 3D object detection is an important technique and it is very difficult to identify the dimensions, direction and position of an object from a monocular image. Previous methods have predicted the dimensions directly from monocular images, resulting in poor accuracy of the dimensions in the depth direction. However, this paper proposes an indirect method for estimating the dimensions in the depth direction by predicting the volume of 3D bounding box. Detection accuracy for distant and partially visible objects is improved by using a loss function that uses uncertainty to account for the variability in predictions that occurs during learning. The proposed method has received an excellent evaluation on KITTI dataset. © 2024 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Investigation of system-driven talking approaches using depth and color image information for digital signage with speech user interface 13

Investigation of system-driven talking approaches using dept...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Takahashi, Kuuta Kawamoto, Shinichi Gunma College Advanced Production Systems Engineering Course Maebashi Japan Gunma College Department of Information and Computer Engineering Maebashi Japan

ISBN: (纸本)9798350355079

In recent decades, digital signages have been widely used. Specifically, digital signages that have a purpose of either providing information or advertising, it is important to direct people's attention toward that information. Conventionally, some approaches to attract viewer's attention include using animation and audible information such as playing background music or a flashing a catchphrase. However, language information has not been implemented in these approaches. In this study, we propose a method to call out a specific person to the front of a digital signage by using color images and depth information. By calling out a specific person by using this method, it is expected for this person to have an awareness that they are a target intended by a digital signage. In this study, we conducted experiments that use utterances based on a person's position, distance from a digital signage, clothing colors, or a pair of two features. Based on the study results, we confirm that a pair of features, that is, clothing color and depth, is the most effective to call out a specific person to the front of a digital signage © 2024 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Relay Selection and Power control for Mobile Underwater Acoustic Communication Networks: A Dual-Thread Reinforcement Learning Approach

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2024年第2期9卷 1-1页

作者： Dai, Jun Li, Xinbin Han, Song Yu, Junzhi Liu, Zhixin Key Lab of Industrial Computer Control Engineering of Hebei Province China Department of Advanced Manufacturing and Robotics College of Engineering State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China

This paper deals with a cooperation communication problem (relay selection and power control) for mobile underwater acoustic communication networks. To achieve satisfactory transmission capacity, we propose a reinforcement-learning-based cooperation communication scheme to efficiently resist the highly dynamic communication links and strongly unknown time-varying channel states caused by the mobility of Autonomous Underwater Vehicles (AUVs). Firstly, a particular Markov decision process is developed to model the dynamic relay selection process of mobile AUV in the unknown scenario. In the developed model, an experimental statistical-based partition mechanism is proposed to cope with the greatly increasing dimension of the state space caused by the mobility of AUV, reducing the search optimization difficulty. Secondly, a dual-thread reinforcement learning structure with actual and virtual learning threads is proposed to efficiently track the superior relay action. In the actual learning thread, the proposed improved probability greedy policy enables the AUV to strengthen the exploration for the reward information of potential superior relays on the current state. Meanwhile, in the virtual learning thread, the proposed upper-confidence-bound-index-based uncertainty estimation method can estimate the action-reward level of historical states. Consequently, the combination of actual and virtual learning threads can efficiently obtain satisfactory Q value information, thereby making superior relay decision-making in a short time. Thirdly, a power control mechanism is proposed to reuse the current observed action-reward information and transform the multiple unknown parameter nonlinear joint power optimization problem into a convex optimization problem, thereby enhancing network transmission capacity. Finally, simulation results verify the effectiveness of the proposed scheme. IEEE

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Classification of Road Damage Images Considering the Discovery of Unknown Classes 7

Classification of Road Damage Images Considering the Discove...

引用

7th International Conference on Automation, control and Robots, ICACR 2023

作者： Nagamatsu, Hiroki Matsushima, Kousuke Kurume College National Institute of Technology Advanced Engineering Course Fukuoka Japan Kurume College National Institute of Technology Department of Control and Information Systems Engineering Fukuoka Japan

ISBN: (纸本)9798350302882

In this paper, we propose a classification method for road damage images considering mobile devices. In the general deep learning approach, it is difficult to find unknown classes. Therefore, we address the problem of Novel Class Discovery (NCD). In addition, mobile devices have limited resources. Thus, we need to reduce the number of parameters in the neural network. To solve these problems, We propose to use lightweight vision transformers (ViTs) for the encoder part of UNified Objective Function (UNO), an unsupervised learning method. Furthermore, we show the effectiveness of ViT by comparing our method to convolutional neural networks (CNNs) with a similar number of parameters. © 2023 IEEE.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of the performance of robotic assembly systems considering the usage of tools or jigs for the task-board task in the WRS 2018

引用

advanced Robotics 2023年第20期37卷 1329-1346页

作者： Dobashi, Hiroki Ogawa, Koki Shibata, Mizuho Uemura, Wataru Yokokohji, Yasuyoshi Faculty of Systems Engineering Wakayama University Wakayama Japan Graduate School of Systems Engineering Wakayama University Wakayama Japan Department of Robotics Faculty of Engineering Kindai University Higashi-Hiroshima Japan Electronics Information and Communication Engineering Course Faculty of Advanced Science and Technology Ryukoku University Otsu Japan Department of Mechanical Engineering Graduate School of Engineering Kobe University Kobe Japan

A task-board task is a task in which robots perform a set of fundamental assembly operations related to the assembly of a specific product such as inserting a part into another part, tightening bolts and nuts, attaching flexible parts, etc. In the task-board task competition in the industrial robotics category of the World Robot Summit (WRS) 2018, 15 teams from around the world performed the task. In our previous work, we observed recorded videos of the competition frame by frame and manually investigated the performance of robotic systems of the top four teams, focusing only on whether robots contact target parts. In this paper, we introduce frame sets to represent mainly contact states between robots, tools, or jigs and target parts to be handled for such a frame-by-frame analysis of the recorded videos, and based on the frame sets, we analyze the performance of robotic assembly systems of other teams as well as the top four teams in the task-board task competition in the WRS 2018, considering the usage of tools or jigs. © 2023 Informa UK Limited, trading as Taylor & Francis Group and The Robotics Society of Japan.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Formation Tracking control of Heterogeneous Multi-Agent systems With Intermittent Communications and Directed Switching Networks

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 294-296页

作者： Yuhan Wang Zhuping Wang Hao Zhang Huaicheng Yan the Shanghai Research Institute for Intelligent Autonomous Systems Tongji University the National Key Laboratory of Autonomous Intelligent Unmanned Systems the Frontiers Science Center for Intelligent Autonomous System of Ministry of Education the College of Electronic and Information Engineering the Department of Control Science and Engineering Tongji University the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education the School of Information Science and Engineering East China University of Science and Technology

Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present so... 详细信息

关键词： Switches Topology Observers Formation control Event detection Switched systems Multi-agent systems control theory Autonomous systems Stability

来源：评论

学校读者我要写书评

暂无评论

Remote control of Cart Platform for Alter Ego Robot by Gaze Input 13

Remote Control of Cart Platform for Alter Ego Robot by Gaze ...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Mori, Kai Shibasato, Koki Kumamoto College Electronics and Information Systems Engineering Course 2659-2 Suya Kumamoto Koshi Japan Kumamoto College Department of Control and Information Systems Engineering 2659-2 Suya Kumamoto Koshi Japan

ISBN: (纸本)9798350355079

In general, people with severe physical challenges have difficulty getting into an electric wheelchair. Therefore, an "alter ego robot"is proposed in order to realize telepresence of the challenged person. In this research, a system that uses an electric wheelchair as basic research for the cart platform of the alter ego robot is developed and enables an operator to teleoperate the robot by using gaze input even when the operator is in a supine position. In the proposed system, there are extended display and an eye tracker in the operator side. Accordingly, a new interface is devised so that the operator can use the system naturally with gaze input. This system aims to improve the quality of life of physically challenged persons. © 2024 IEEE.

关键词： Wheelchairs

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：