检索结果-内蒙古大学图书馆

detection and Location of Safety Protective Wear in Power Substation Operation Using Wear-Enhanced YOLOv3 Algorithm

IEEE ACCESS 2021年 9卷 125540-125549页

作者： Zhao, Baining Lan, Haijuan Niu, Zhewen Zhu, Huiling Qian, Tong Tang, Wenhu South China Univ Technol Sch Elect Power Engn Guangzhou 510641 Peoples R China Schneider Elect Xiamen Switchgear Co Ltd Xiamen 361000 Peoples R China

Wearing personal safety protective equipment (PSPE) plays a key role in reducing electrical injuries to electrical workers. However, substation employees often ignore this regulation due to lack of safety awareness and discomfortable feeling of wearing PSPE. Therefore, it is necessary to develop a detection algorithm for PSPE and workers to build real-time video surveillance systems in power substations. In this paper, a wear-enhanced YOLOv3 method for real-time detection of PSPE and substation workers is proposed. The gamma correction is first applied as the preprocessing method to highlight the details of the operators and data augmentation is performed. Next, K-means++ algorithm replaces K-means in wear-enhanced YOLOv3 method to derive the most suitable prior bounding box size and lift the detection speed. Then, the proposed method can be quickly and effectively trained based on transfer learning. Finally, extensive experiments are carried out on a dataset of images about usage of safety helmets, insulating gloves and boots. Using the proposed method, the mean average precision is improved by over 2% and the frames per second is the highest compared with other typical object detection methods, which illustrates the effectiveness of the wear-enhanced YOLOv3 method for PSPE and workers detection.

关键词： Safety Substations Head Real-time systems Feature extraction Object detection Deep learning objects detection deep learning YOLOv3 power substation safety helmet

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Pedestrian Density Estimation Using Moving Sensors and Computer Vision Sensing the city

引用

ACM TRANSACTIONS ON SPATIAL ALGORITHMS AND SYSTEMS 2020年第4期6卷 1–20页

作者： Tokuda, Eric K. Lockerman, Yitzchak Ferreira, Gabriel B. A. Sorrelgreen, Ethan Boyle, David Cesar-Jr, Roberto M. Silva, Claudio T. Univ Sao Paulo Rua Matao 1010 BR-05508090 Sao Paulo SP Brazil NYU 2 MetroTech Ctr New York NY 11201 USA Carmera 1100 NE Campus Pkwy Suite 200 Seattle WA 98195 USA Carmera 20 Jay St Suite 312 New York NY 11201 USA

An understanding of person dynamics is indispensable for numerous urban applications, including the design of transportation networks and planning for business development. Pedestrian counting often requires utilizing manual or technical means to count individuals in each location of interest. However, such methods do not scale to the size of a city and a new approach to fill this gap is here proposed. In this project, we used a large dense dataset of images of New York City along with computer vision techniques to construct a spatio-temporal map of relative person density. Due to the limitations of state-of-the-art computer vision methods, such automatic detection of person is inherently subject to errors. We model these errors as a probabilistic process, for which we provide theoretical analysis and thorough numerical simulations. We demonstrate that, within our assumptions, our methodology can supply a reasonable estimate of person densities and provide theoretical bounds for the resulting error.

关键词： Computer vision objects detection urban computing simulation agent-based modelling

来源：评论

学校读者我要写书评

暂无评论

Frequency Modulated Continuous Wave RADAR for objects Mapping in Enclosed Spaces Using Smartphones and Arduino Components

引用

3D RESEARCH 2017年第2期8卷 1-13页

作者： Numhauser, Jonathan Bar-Magen Zalevsky, Zeev Bar Ilan Univ Fac Engn IL-52900 Ramat Gan Israel

Based on previous studies and using mobile portable device, we were able to realize a portable system capable of detecting metallic objects in a room surrounded by walls while also extracting the approximate position of such objects. Our hardware included only a smartphone device connected to several Arduino components and we were applying frequency-modulated continuous-wave electronics in each of the Arduino devices.

关键词： FMCW radar Imaging objects detection Hybrid radar Enclosed space imaging Mobile devices Swarm logic

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of dangerous events for underground surveillance

Automatic detection of dangerous events for underground surv...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance

作者： Spirito, M Regazzoni, CS Marcenaro, L Univ Genoa Dept Biophys & Elect Engn I-16145 Genoa Italy

ISBN: (纸本)0780393856

This paper describes automatic video sequences processing techniques for detecting suspect and dangerous situations within public transportations. Proposed surveillance system is able to raise different kind of warnings and alarms on the basis of the particular detected situation. Algorithms used for objects detection and tracking will be described in details and performances will be discussed in relation with alarm conditions that are showed in the sequences that have been made available for this conference. An empty reference image is used for object extraction through image difference. In order to Perform background updating a high level module is implemented taking into account the detected objects and their classification tags. The system has been tested on several sequences showing dangerous events due to human behaviors in a underground station.

关键词： alarm systems feature extraction image sequences object detection surveillance tracking transportation video signal processing automatic detection automatic video sequences processing dangerous events object extraction objects detection public transporta Object detection automatic detection extraction of object Alarm Systems Video signal processing image sequences Feature extraction flat(mining) transport tracking Alarm

来源：评论

学校读者我要写书评

暂无评论

Representing and updating objects' identities in semantic SLAM 23

Representing and updating objects' identities in semantic SL...

引用

23rd International Conference on Information Fusion (FUSION)

作者： Tslil, Or Elbaz, Amit Feiner, Tal Carmi, Avishy Ben Gurion Univ Negev Dept Mech Engn Beer Sheva Israel

ISBN: (纸本)9780578647098

Simultaneous localization and mapping (SLAM) deals with localizing and mapping in unknown environment. Semantic SLAM incorporates an additional layer of objects identities and their relationships. Here we suggest representing the identity of an object in semantic SLAM as a probability distribution over the object's traits, such as labels, colors, shapes, materials, etc. objects' identities are estimated by integrating measurements from different sensors and are distinguished based on the discrepancy between the underlying probability distributions as quantified by the Bhattacharyya distance. The semantic mapping scheme is tested both in simulation and experiment using a ground robot.

关键词： Semantic SLAM Bhattacharyya distance objects detection

来源：评论

学校读者我要写书评

暂无评论

Utilization of Directional Properties of Optical Flow for Railway Crossing Occupancy Monitoring

Utilization of Directional Properties of Optical Flow for Ra...

引用

3rd International Conference on IT Convergence and Security (ICITCS)

作者： Sitar, Zdenek Dobrovolny, Martin Univ Pardubice Fac Elect Engn & Informat Dept Informat Technol Pardubice Czech Republic

ISBN: (纸本)9781479928453

This article deals with the obstacle detection on a railway crossing (clearance detection). detection is based on the optical flow estimation and classification of the flow vectors by K-means clustering algorithm. For classification of passing vehicles is used optical flow direction determination. The optical flow estimation is based on a modified Lucas-Kanade method.

关键词： railway crossing monitoring objects detection background estimation K-means clustering Matlab direction of optical flow velocity vectors

来源：评论

学校读者我要写书评

暂无评论

The Design of objects Bounding Boxes Non Maximum Suppression and Visualization Module Based on FPGA 23

The Design of Objects Bounding Boxes Non Maximum Suppression...

引用

23rd IEEE International Conference on Digital Signal Processing (DSP)

作者： Liang, Feng Yang, Shaofei Mai, Tinrui Yang, Yichen Xi An Jiao Tong Univ Sch Microelect Xian Shaanxi Peoples R China

ISBN: (纸本)9781538668122;9781538668115

The objects detection results are marked with bounding boxes in image. There are lots of redundant bounding boxes in detection results. Generally, the non-maximum suppression (NMS) method is used to remove redundant bounding boxes in detection results to improve accuracy of detection. Opencv is usually used to complete visualization of objects bounding boxes. We compare time of NMS and bounding boxes visualization implemented in FPGA and software in server. The results in hardware performs better. objects detection has high requirements for real-time performance. Parallel computing capabilities of hardware makes it better than software to implement object detection algorithm and related peripheral algorithms in FPGA. FPGA is a good solution for embedded applications of objects detection. In this paper, we build a FPGA based objects detection system on YOLO, which is a kind of object detection algorithm based on deep learning and we complete the design and verification of hack-end processing module in the system, including NMS module to remove redundant objects bounding boxes and bounding boxes visualization module. We make some changes for the NMS algorithm implementation in hardware. Two modules work together to process 100x61 images including 98x20 object bounding boxes. The remaining bounding boxes what we want after removing redundant hounding boxes are used for display, which ultimately takes 680 s.

关键词： objects detection non-maximum suppression FPGA bounding boxes visualization

来源：评论

学校读者我要写书评

暂无评论

Colour-based Lips Segmentation Method using Artificial Neural Networks 6

Colour-based Lips Segmentation Method using Artificial Neura...

引用

6th International Conference on Information and Communication Systems (ICICS)

作者： Hassanat, Ahmad B. A. Alkasassbeh, Mouhammd Al-Awadi, Mouhammd Alhasanat, Esra'a A. A. Mutah Univ IT Dept Mutah Al Karak 61710 Jordan

ISBN: (纸本)9781479973491

A colour-based technique for lip segmentation is presented throughout this work. Basically, we make use of colour spaces to categorize pixels as either lip or non-lip using artificial neural networks. This study clearly shows how a novel method for fusion of the existing colour spaces practically produces better results than individual colour spaces. More accuracy in dealing with face images under many different conditions has been achieved. Comparing this work with other researchers' work using the same databases, we found that our method, which involves the fusion of different colour information that comes from different colour models, outperforms other methods.

关键词： colour information artificial intelligence computer vision image segmentation objects detection

来源：评论

学校读者我要写书评

暂无评论

Screw and wrench orientation estimation using the artificial vision in the NAO humanoid robot

Screw and wrench orientation estimation using the artificial...

引用

2nd International Congress of Engineering Mechatronics and Automation (CIIMA)

作者： Pena, Carlos Hoyos, Jose Prieto, Flavio Ayala, Jorge Garzon-Castro, Claudia Univ Nacl Colombia Fac Ingn Cundinamarca Colombia Univ La Sabana Fac Ingn Cundinamarca Colombia

ISBN: (纸本)9781479924707

Industrial robots are having major involvement in assembly lines, where they are able to identify, classify and even grasp objects and place them in non-default locations;furthermore, assembling pieces autonomously. We describe step by step the image processing to determine the objects orientation located in the field of view of the NAO robot, initial step in posterior developments in task execution using those objects. The processing stages described are: RGB color space segmentation, interest points detection and objects orientation estimation with respect to a reference frame. The results are compared with measures obtained using a commercial image processing software. The absolute error is less than 1.5 degrees in the objects orientation angles, which is considered acceptable due to the size of the processed objects. The introduced methodology is a first step in the execution of assembling tasks or handling of tools by a robotic platform, where the artificial vision has a relevant place in the identification, location and orientation of the objects.

关键词： Image processing objects detection image segmentation humanoid robots robotic vision systems

来源：评论

学校读者我要写书评

暂无评论

Particle detection of Complex Images Based on Convolutional Neural Network 41

Particle Detection of Complex Images Based on Convolutional ...

引用

第41届中国控制会议

作者： Yuting Ge Yi Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Particle detection plays important roles in industrial and medical image ***-learning based methods can only deal with the particle images with simple backgrounds and sparse *** most neural network based methods can also hardly to deal with overlapping objects and small particles,besides,the huge amount of parameters of these methods also has a great demand for annotated data,which is difficult to ***,we use bright pixels to represent the spatial position of particles,and artificially divid the sizes of particles into multiple intervals.A feature representation called Light-spots Maps is proposed to replace the bounding box and pixel classifications in our detection *** Light-weight networks based on ResNets is used to transform the particle images into Light-spots maps to detect the particle *** experiments,we prove the effectiveness of our method.

关键词： objects detection Particles detection Convolutional Neural Network

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：