检索结果-内蒙古大学图书馆

3rd European Conference on Smart Sensing and Context

作者： Molyneaux, David Gellersen, Hans Schiele, Bernt Univ Lancaster Dept Comp Lancaster LA1 4YW England Tech Univ Darmstadt Dept Comp Sci Petersenstr 30 D-64289 Darmstadt Germany

ISBN: (纸本)9783540887928

We evaluate an approach for mobile smart objects to cooperate with projector-camera systems to achieve interactive projected displays on their surfaces without changing their appearance or function. Smart objects describe their appearance directly to the projector-camera system, enabling vision-based detection based on their natural appearance. This detection is a significant challenge, as objects differ in appearance and appear at varying distances and orientations with respect to a tracking camera. We investigate four detection approaches representing different appearance cues and contribute three experimental studies analysing the impact on detection performance, firstly of scale and rotation, secondly the combination of multiple appearance cues and thirdly the use of context information from the smart object. We find that the training of appearance descriptions must coincide with the scale and orientations providing the best detection performance, that multiple cues provide a clear performance gain over a single cue and that context sensing masks distractions and clutter, further improving detection performance.

关键词： Cooperative Augmentation Smart Objects vision-based detection Natural Appearance Multi-Cue detection

来源：评论

学校读者我要写书评

暂无评论

vision-based Fall detection using Confidence Prediction and Motion Analysis

Vision-based Fall Detection using Confidence Prediction and ...

引用

作者： Ros, Dara University of Cincinnati

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

There are many research interests in human activity recognition, especially fall which is the major cause of serious injury for the elderly. Different technologies have been developed to detect falls, and fortunately, advancement in computer vision has attracted researchers to apply sophisticated systems for action recognition, posture estimation, and fall detection. The vision-based approach provides a non-invasive and reliable solution for fall detection among these various technologies. The overall goal of this thesis is to propose automatic human fall detection frameworks using confidence prediction and motion analysis. This thesis is composed of two pieces of work. The first work introduces a confidence-based fall detection system using multiple surveillance cameras. First, a model for predicting the confidence of fall detection on a single camera is constructed using a set of simple yet useful features. Then, the detection results from multiple cameras are fused based on their confidence levels. The proposed confidence prediction model can be easily implemented and integrated with single-camera fall detectors, and the proposed system improves the accuracy of fall detection through effective data fusion. Secondly, a flexible fall detection framework based on detecting a human object and analyzing the object's motion is proposed. Unlike many state of the art that require predefined thresholds to detect a fall, the proposed framework localizes and tracks a person in videos via object detection and motion analysis over a time window with appropriate length. As fall events may not look the same from different view angles, a multi-view fall dataset is used to train the proposed detection method. The framework is flexible for different use cases as it could incorporate unique object detection methods and work on videos captured from different angles. The proposed framework has produced promising detection results on several other datasets that outperform two traditio

关键词： Fall detection Motion analysis vision-based detection Confidence prediction

来源：评论

学校读者我要写书评

暂无评论

Sensing and responding to the changes of geometric surfaces in flexible manufacturing and assembly

引用

ENTERPRISE INFORMATION SYSTEMS 2014年第2期8卷 225-245页

作者： Bi, Z. M. Kang, Bongsu Indiana Univ Purdue Univ Dept Engn Ft Wayne IN 46805 USA

A flexible manufacturing system is capable of dealing with changes and uncertainties occurring in a manufacturing environment. A rigid automation system adapts changes through reconfiguration or manual modification of its control programmes. In contrast, an advanced system responds to the changes autonomously or with a minimal manual intervention. One critical technology for a flexible manufacturing system is to detect or predict the changes and uncertainties and take them into account for the control of the manufacturing system. In this paper, an intelligent manufacturing system is proposed to accommodate product geometric variants autonomously by integrating a 3D vision system into manufacturing processes. The proposed system is capable of acquiring vision sensor data, detecting the geometric changes, and modifying the control programmes of the machine in response to the changes. In this innovative work, a new method for converting the raw vision sensor data into a surface model of the product is presented. A new surface reconstruction algorithm is proposed to generate the surface model directly from the raw 3D point-cloud data of a product. In addition, an advanced programming algorithm that uses acquired surface models to automatically update robot programmes for a new task with minimal manual intervention is presented.

关键词： enterprise information system flexible manufacturing system automation vision-based detection surface reconstruction marching algorithms ITK/VTK

来源：评论

学校读者我要写书评

暂无评论

Door-Density-Aware Path Planning

引用

IEEE ACCESS 2024年 12卷 136880-136888页

作者： Vikram, Charan Mirihagalla, M. K. Dojitha M. Yeo, Matthew S. K. Zeng, Zimou Borusu, Charan Satya Chandra Sairam Muthugala, M. A. Viraj J. Elara, Mohan Rajesh Singapore Univ Technol & Design Engn Prod Dev Pillar Cluny Rd Singapore 487372 Singapore Univ Moratuwa Dept Elect & Telecommun Engn Moratuwa 10400 Sri Lanka

Doors are part of the building infrastructure that mobile robots have to pass through to reach zones on the other side. If robots were to clear these obstacles, they would require human assistance, advanced end-effectors, and complex control systems, making it challenging for robots. Therefore, a robot deployed in an environment should be capable of minimizing the passing through doors as well as path distance to improve overall efficiency. This paper proposes a novel Door-Density-Aware (DDA) path planning method. A vision-based door-detecting framework based on YOLOv8 has been developed to tag the door locations in a robot's navigation map. The proposed DDA path planner uses a door-tagged map to plan an efficient path considering the cost of moving through doors and the path distance. Genetic Algorithm (GA) and Gray Wolf Optimization (GWO) have been considered for solving this optimization problem. According to the experimental results, the proposed method can effectively detect and tag doors in the navigation map and plan efficient paths. In summary, the proposed DDA path planner with GA outperformed other approaches, achieving cost reductions of 66%, 34%, 49%, and 60% compared to random selection, DDA with GWO, GA minimizing only distance, and GWO minimizing only distance, respectively.

关键词： Robot sensing systems Robot kinematics Navigation Path planning Optimization Genetic algorithms Computer vision Door density path planning optimization vision-based detection

来源：评论

学校读者我要写书评

暂无评论

A doubt-confirmation-based visual detection method for foreign object debris aided by assembly models

引用

TRANSACTIONS OF THE CANADIAN SOCIETY FOR MECHANICAL ENGINEERING 2023年第4期47卷 508-520页

作者： Kong, Feifei Zhao, Delong Du, Fuzhou Beihang Univ Sch Mech Engn & Automat 37 Coll Rd Beijing Peoples R China

Foreign object debris (FOD) impacts significantly on the quality control during product assembly because it usually causes product failure. The vision-based method as a nondestructive and efficient technology has become an important approach to FOD detection. However, it faces two important challenges: (1) inexhaustible types (almost any object can become FOD) and (2) unpredictable locations (FOD can appear almost anywhere on surface of a product). Therefore, this paper proposes an FOD visual detection method based on doubt-confirmation strategy and aided by assembly models. Firstly, a coarse-to-fine method is designed for feature extraction and registration to align the test image with the reference image. Then, to solve the unpredictable location problem, different types of suspected FOD are extracted from the test image by a combined method of supervision and nonsupervision. Finally, to solve the inexhaustible type problem, an image comparison method based on a Histogram of Line Direction Angle is proposed, and re-recognition rules of suspected FOD established to complete the final discrimination. Experiments are conducted on a product with complex shape, and the results demonstrate the effectiveness and efficiency of our approach.

关键词： foreign object debris digital model aid vision-based detection doubt-confirmation strategy

来源：评论

学校读者我要写书评

暂无评论

Integrating vision and Learning-based Method for Dexterous Grasping 29

Integrating Vision and Learning-based Method for Dexterous G...

引用

29th International Conference on Automation and Computing (ICAC)

作者： Sampath, Suhas Kadalagere Wang, Ning Wu, Hao Liu, Cunjia Jiang, Jingjing Yang, Chenguang Univ West England Fac Engn & Technol Bristol Avon England Antobot Ltd Cambridge England Loughborough Univ Dept Aeronaut & Automot Engn Loughborough Leics England Univ Liverpool Dept Comp Sci Liverpool Merseyside England

ISBN: (纸本)9798350360882;9798350360899

Robotic grasping and manipulating objects with varying properties pose significant challenges. This paper presents an approach integrating vision-based object detection using You Only Look Once (YOLO, version 8) with learning from demonstration (LfD) for dexterous robotic grasping. The YOLOv8 network accurately detects and localizes objects, providing 3D coordinates for positioning a dexterous hand. A Long Short-Term Memory (LSTM) network, trained on teleoperated data, learns to adaptively adjust grasping forces and finger positions based on object properties and real-time feedback. Experimental results demonstrate high success rates in securely grasping diverse objects while modulating forces within safe limits, achieving human-like dexterity. Integrating vision, learning techniques, and adaptive force control enables enhanced robotic automation while minimizing product damage.

关键词： Dexterous robotic grasping vision-based detection YOLOv8 learning from demonstration LSTM adaptive grasping

来源：评论

学校读者我要写书评

暂无评论

vision-based UAV Landing on the Moving Vehicle

Vision-based UAV Landing on the Moving Vehicle

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Lee, Hanscob Jung, Scokwoo Shim, David Hyunchul Korea Adv Inst Sci & Technol Dept Aerosp Engn Daejeon South Korea

ISBN: (纸本)9781467393331

This paper describes the tracking guidance for the autonomous UAV landing and the vision-based detection of the marker on the moving vehicle with the real-time image processing system. The detection of the marker is based on the color detection algorithm with morphological filter and the tracking guidance is based on the relative distance between the UAV and the vehicle. In order to track and land on the moving vehicle, we have built the integrated system on the UAV platform that conducts the landing mission with the on-board image processing system. The flight test was performed with the moving vehicle in the outdoor environment, and we validated the algorithm for the vision-based autonomous landing.

关键词： Unmanned Aerial Vehicle (UAV) vision-based detection Morphological Filter Target Tracking Trajectory Guidance On-board Image Processing

来源：评论

学校读者我要写书评

暂无评论

Optical Flow Reckoning for Flame Disclosure in Dynamic Event Using Hybrid Technique

Optical Flow Reckoning for Flame Disclosure in Dynamic Event...

引用

International Conference On Soft Computing Systems (ICSCS)

作者： Kumar, Ankit Sujith, P. Veeramuthu, A. Sathyabama Univ Rajiv Gandhi Rd Madras 600119 Tamil Nadu India

ISBN: (纸本)9788132226710;9788132226697

Computational vision-based discovery has drawn critical consideration and the cam reconnaissance frameworks have gotten to be to show up all over. Along these lines, we propose a PC vision approach for flame fire identification to be utilized as an early-cautioning blaze checking framework. vision-based discovery is made out of three stages. First, preprocessing is important to make up for known wellsprings of variability, e.g., cam equipment and enlightenment. Besides, emphasis extraction is intended for the recognition of a particular focus on;a processing maps the crude information to a standard set of parameters to describe the target. At long last, characterization calculations utilize the processed peculiarities as information and settle on choice yields with respect to the target's vicinity. The regulated machine-learning-based characterization calculation, e.g., neural systems (NN) is deliberately prepared on an information set of gimmicks and the ground truth. While parts of preprocessing and grouping are viewed as, this paper concentrates on gimmick extraction: Spurred by the physical properties of flame and a set of novel optical stream characteristics which are intended for vision-based blaze discovery.

关键词： Preprocessing Neural network Blaze vision-based detection Classification Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Imagery based Parametric Classification of Correct and Incorrect Motion for Push-up Counter Using OpenPose 16

Imagery based Parametric Classification of Correct and Incor...

引用

16th IEEE International Conference on Automation Science and Engineering (CASE)

作者： Park, Ho-Jun Baek, Jang-Woon Kim, Jong-Hwan Pusan Natl Univ Dept Elect & Comp Engn Busan South Korea Korea Mil Acad Dept Civil Engn & Environm Sci Seoul South Korea Korea Mil Acad Mech & Syst Engn Dept Seoul South Korea

ISBN: (纸本)9781728169040

This paper presents a real-time approach to count push-ups using 2D video imagery. The proposed method uses OpenPose in each frame to extract multiple joints and links of a human body. Then, it analyzes key motion features linked to counting the push-ups. Taking in consideration the push-up rules of the Republic of Korea Army, five criteria are defined and used parametrically to discriminate both correct and incorrect push-ups. A total of 147,840 samples have been collected from 220 push- up videos each in two different viewpoints: half of the videos for modeling the proposed method and the other half for testing its performance. Finally, the results shows 90.00%, 87.82%, 97.86%, and 92.57% for accuracy, precision, recall, and F-measure, respectively, demonstrating its reliability in military physical tests.

关键词： Push-up counter vision-based detection Army Physical Fitness Test OpenPose

来源：评论

学校读者我要写书评

暂无评论

Centimeter-Scale Submarine Robot for Monitoring Coral Reef Ecosystem 21

Centimeter-Scale Submarine Robot for Monitoring Coral Reef E...

引用

21st IEEE International Conference on Mechatronics and Automation (IEEE ICMA)

作者： Li, Zongze Zhang, Yi He, Shujing Zhu, Xiyu Wei, Tanyong Hu, Chengzhi Southern Univ Sci & Technol Key Lab Biomimet Robot & Intelligent Syst Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Guangdong Prov Key Lab Adv Biomat Shenzhen 518055 Peoples R China

ISBN: (纸本)9798350388084;9798350388077

Monitoring coral reef ecosystem is of great importance for assessing their health and promoting conservation efforts to protect these valuable and vulnerable ecosystems. Underwater robots provide a feasible approach for long-term monitoring due to their compact size for navigating through narrow passages. However, existing underwater robots face limitations due to their large size, preventing them from entering narrow coral reef caves to gather information. To address this challenge, this paper proposes a highly integrated propeller-driven centimeter-scale submarine robot with a length of 4.4 cm for monitoring coral reef ecosystem. There are two propellers on two sides of the robot, facilitating lift motion, while an additional two propellers are mounted at the tail to enable forward propulsion and turning maneuvers. This robot can realize three degrees of freedom movement, such as circular motion at specific heights or cruising in a spiral paths under the control of external infrared signals. A kinematic and dynamic model is formulated to develop the control strategy. For object monitoring by the proposed submarine robot, distance and displacement measurement algorithms are developed based on a monocular camera. These algorithms have been experimentally evaluated, demonstrating a calculation error of less than 5%.

关键词： Submarine robot system design motion control vision-based detection coral reef ecosystem

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：