检索结果-内蒙古大学图书馆

Frontiers in Science and Engineering 2021年第7期1卷 1-9页

作者： Xiaoya Yang Miaolei Deng Hui Gao Dexian Zhang

Under the background of anti-terrorism globalization, the prevention and control of violent terrorism poses new challenges to the field of artificial intelligence. This paper first summarizes the relevant knowledge of deep learning, then analyzes the crowd behavior analysis model based on deep learning, the detection and identification model of sensitive personnel and dangerous goods based on deep learning, the object behavior analysis and target tracking model based on deep learning, then suggested deficiencies and amendments. Finally, the anti-terrorism prevention and control work based on deep learning is summarized, the shortcomings are put forward, and the prospect is given.

关键词： Deep Learning Convolutional Neural Networks Artificial Intelligence object detection and recognition Behavior Analysis Target Tracking

来源：评论

学校读者我要写书评

暂无评论

Indoor Navigation Systems for Visually Impaired Persons: Mapping the Features of Existing Technologies to User Needs

引用

SENSORS 2020年第3期20卷 636-636页

作者： Plikynas, Darius Zvironas, Arunas Budrionis, Andrius Gudauskis, Marius Vilnius Gediminas Tech Univ Dept Business Technol & Entrepreneurship LT-10223 Vilnius Lithuania Univ Hosp North Norway Norwegian Ctr E Hlth Res N-9019 Tromso Norway

Currently, several outdoor navigation and orientation electronic traveling aid (ETA) solutions for visually impaired (VI) people are commercially available or in active development. This paper's survey of blind experts has shown that after outdoor navigation, the second most important ETA feature for VI persons is indoor navigation and orientation (in public institutions, supermarkets, office buildings, homes, etc.). VI persons need ETA for orientation and navigation in unfamiliar indoor environments with embedded features for the detection and recognition of obstacles (not only on the ground but also at head level) and desired destinations such as rooms, staircases, and elevators. The development of such indoor navigation systems, which do not have Global Positioning System (GPS) locational references, is challenging and requires an overview and evaluation of existing systems with different navigation technologies. This paper presents an evaluation and comparison of state-of-the-art indoor navigation solutions, and the research implications provide a summary of the critical observations, some insights, and directions for further developments. The paper maps VI needs in relation to research and development (R&D) trends using the evaluation criteria deemed most important by blind experts.

关键词： visually impaired blind indoor navigation object detection and recognition electronic travelling aid assistive device

来源：评论

学校读者我要写书评

暂无评论

Car detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3 1

Car Detection using Unmanned Aerial Vehicles: Comparison bet...

引用

1st International Conference on Unmanned Vehicle Systems-Oman (UVS)

作者： Benjdira, Bilel Khursheed, Taha Koubaa, Anis Ammar, Adel Ouni, Kais Prince Sultan Univ Riyadh Saudi Arabia Gaitech Robot Shanghai Peoples R China Polytech Inst Porto INESC CISTER TECISEP Porto Portugal Al Imam Mohamed bin Saud Univ Riyadh Saudi Arabia Univ Carthage Res Lab Smart Elect Tunis Tunisia Univ Carthage Natl Engn Sch Carthage ICT SEICTLR18ES44 Tunis Tunisia

ISBN: (纸本)9781538693681

Unmanned Aerial Vehicles are increasingly being used in surveillance and traffic monitoring thanks to their high mobility and ability to cover areas at different altitudes and locations. One of the major challenges is to use aerial images to accurately detect cars and count-them in real-time for traffic monitoring purposes. Several deep learning techniques were recently proposed based on convolution neural network (CNN) for real-time classification and recognition in computer vision. However, their performance depends on the scenarios where they are used. In this paper, we investigate the performance of two state-of-the art CNN algorithms, namely Faster R-CNN and YOLOv3, in the context of car detection from aerial images. We trained and tested these two models on a large car dataset taken from UAVs. We demonstrated in this paper that YOLOv3 outperforms Faster R-CNN in sensitivity and processing time, although they are comparable in the precision metric.

关键词： Car detection convolutional neural networks You Only Look Once Faster R-CNN unmanned aerial vehicles object detection and recognition

来源：评论

学校读者我要写书评

暂无评论

Indoor Electronic Traveling Aids for Visually Impaired: Systemic Review 6

Indoor Electronic Traveling Aids for Visually Impaired: Syst...

引用

6th Annual Conference on Computational Science and Computational Intelligence (CSCI)

作者： Plikynas, Darius Zvironas, Arunas Gudauskis, Marius Vilnius Gediminas Tech Univ Vilnius Lithuania

ISBN: (纸本)9781728155845

Visually impaired persons need electronic traveling aids (ETA) for detection and recognition of obstacles, and navigation to desired destinations not only in outdoor but also in the indoor environments as well. Without clear GPS signals, it is technologically challenging, however. This paper provides a brief systemic overview and evaluation of current technological R&D approaches for indoor navigation. We assessed the selected indoor navigation prototypes estimating navigation technologies, sensors, computational devices, and feedback type. The evaluation and comparison of the state-of-the-art indoor navigation solutions and research implications provide the summary of observations, which are critically assessed. Our systemic review also provides some technological clues for the developers.

关键词： visually impaired people indoor navigation electronic travelling aid object detection and recognition assistive device

来源：评论

学校读者我要写书评

暂无评论

Intelligent Surveillance System for Abandoned Luggage 26

Intelligent Surveillance System for Abandoned Luggage

引用

26th IEEE Signal Processing and Communications Applications Conference (SIU)

作者： Altunay, Damla Gul Karademir, Naciye Topcu, Okan Direkoglu, Cem Orta Dogu Tekn Univ Bilgisayar Muhendisligi Bolumu Kuzey Kibris Kampusu Kalkanli Kuzey Kibris Turkey Orta Dogu Tekn Univ Elekt Elekt Muhendisligi Bolumu Kuzey Kibris Kampusu Kalkanli Kuzey Kibris Turkey

ISBN: (纸本)9781538615010

In this paper, an automatic method based on computer vision for the detection of abandoned luggage/bag in public spaces is proposed. First, with the background subtraction and foreground modeling technique, objects that were not present in the previous frames and have appeared later on as a static object are detected and then whether they are luggage or not are determined using the Faster Region Proposal Convolutional Neural Network (Faster R-CNN) technique. At the same time, the person closest to the luggage is identified and defined as the owner. After that, the event analysis phase is being started. If the identified person is not in the luggage area within a certain period of time (e.g. 30 seconds), the luggage is defined as "abandoned" with a bounding box. The assessments show that the proposed approach is effective and rapid.

关键词： Surveillance systems video processing object detection and recognition event recognition

来源：评论

学校读者我要写书评

暂无评论

Smart e-stick for Visually Impaired using Video Intelligence API

Smart e-stick for Visually Impaired using Video Intelligence...

引用

IEEE Bombay Section Signature Conference (IBSSC)

作者： Priyanka Ambawane Devshree Bharatia Piyush Rane Department of Computer Engineering Maharashtra Institute Of Technology Pune India Department of Computer Engineering Dhole Patil College Of Engineering Pune India

ISBN: (纸本)9781538674765

The visually impaired need to confront several problems while performing their daily activities. Independent navigation becomes one of the major problems in their social life. This issue further deteriorates when they travel across new unknown environments. This paper provides an efficient solution for the visually impaired in the form of a hardware automated stick based on Google's Cloud Video Intelligence API. This system uses real time video processing to analyze the obstacles or objects coming in the path of the blind and provides feedback in the form of voice messages. Hence the system facilitates real time navigation in both indoor and outdoor environments. Also the cost effectiveness and the versatility of the system make it more adaptive and easy to use.

关键词： Video Intelligence API (Application Programming Interface) smart blind stick label detection object detection and recognition text recognition shot change detection Google's text-to-speech engine (gTTS) Printed text recognition Visually Impaired Persons API Application programming interfaces AXIAL POWER INDICATOR American Petroleum Institute Intelligence Voicemail Videotapes Cost Effectiveness

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning object recognition in Multi-Spectral UAV imagery 5

Deep-Learning Object Recognition in Multi-Spectral UAV image...

引用

Conference on Optics, Photonics, and Digital Technologies for Imaging Applications V

作者： Knyaz, Vladimir Zheltov, Sergey State Res Inst Aviat Syst GosNIIAS 7 Victorenko Str Moscow Russia MIPT Moscow Russia

ISBN: (数字)9781510618855

ISBN: (纸本)9781510618855

The application area of unmanned aerial vehicles increases significantly recent years due to progress in hardware and algorithms for data acquisition and processing. object detection and classification (recognition) in imagery acquired by unmanned aerial vehicle are the key tasks for many applications, and usually in practice an operator solves these tasks. Growing amount of data of different types and of different nature provides the possibility for deep machine learning which nowadays shows high level results for object detection and recognition. Two key problems are to be solved for applying deep learning for object recognition task when dealing with multi-spectral imagery: (a) availability of representative dataset for neural network training and testing and (b) effective way of multi-spectral data fusion during neural network training. The paper proposes the approaches for solving these problems. For creating a representative dataset synthetic infra-red images are generated using several real infra-red images and 3D model of a given object. An technique for realistic infra-red texturing based on accurate infra-red image exterior orientation and 3D model pose estimation is developed. It allows in automated mode to produce datasets of required volume for deep learning and automatically generate ground truth data for neural network training and testing. Two approaches for multi-spectral data fusion for object recognition are developed and evaluated: data level fusion and results level fusion. The results of the evaluation of both techniques on generated multi-spectral dataset are presented and discussed.

关键词： Unmanned aerial vehicles object detection and recognition deep learning multi-spectral dataset feature detection

来源：评论

学校读者我要写书评

暂无评论

FPGA-based multi-robot tracking

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2017年 107卷 146-161页

作者： Irwansyah, Arif Ibraheem, Omar W. Hagemeyer, Jens Porrmann, Mario Rueckert, Ulrich Bielefeld Univ CITEC Cognitron & Sensor Syst Grp Inspirat 1 D-33619 Bielefeld Germany

Vision-based robot tracking is commonly used for monitoring and debugging in single- and multi-robot environments. Currently, most of the existing vision-based multi-robot tracking systems are based on implementations on general purpose computers. These solutions are not feasible for embedded applications requiring high resource efficiency or high robustness as well as for use-cases with large frame sizes, multiple cameras and a large number of robots to be tracked. Field Programmable Gate Array (FPGAs)-based hardware accelerators can be used to efficiently handle compute-intensive applications like vision processing due to their high inherent parallelism. In this paper, we present an FPGA-based architecture for multi-robot tracking using multiple GigE Vision cameras. A complete system is implemented, comprising a multi-camera frame grabber and IP cores for image preprocessing, edge filtering, and circle detection. The robot localization is based on shape-based object detection. The proposed design is scalable in terms of the number of cameras and robots. It detects the locations of multiple robots simultaneously using single or multiple cameras without sacrificing the performance. Our implementation can process video frames from multiple cameras for multi-robot localization with precision and recall rates of 98%. It supports a maximum total video resolution of 2048x2048 with 152 frames per second. A speed-up of more than 30 is achieved as compared to a multi-threaded OpenCV implementation on a 3.2 GHz desktop quad-core CPU. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Reconfigurable systems FPGA object detection and recognition Multi-camera Multi-robot systems Image processing Vision processing Circular Hough transform

来源：评论

学校读者我要写书评

暂无评论

object Localization in Handheld Thermal Images for Fireground Understanding 39

引用

Conference on Thermosense - Thermal Infrared Applications XXXIX

作者： Vandecasteele, Florian Merci, Bart Jalalvand, Azarakhsh Verstockt, Steven Univ Ghent IMEC ELIS Dept IDLab Sint Pieternieuwstr 41 B-9000 Ghent Belgium Univ Ghent Dept Flow Heat & Combust Mech Sint Pieternieuwstr 41 B-9000 Ghent Belgium

ISBN: (纸本)9781510609297;9781510609303

Despite the broad application of the handheld thermal imaging cameras in fire fighting, its usage is mostly limited to subjective interpretation by the person carrying the device. As remedies to overcome this limitation, object localization and classification mechanisms could assist the fireground understanding and help with the automated localization, characterization and spatio-temporal (spreading) analysis of the fire. An automated understanding of thermal images can enrich the conventional knowledge-based fire fighting techniques by providing the information from the data and sensing-driven approaches. In this work, transfer learning is applied on multilabeling convolutional neural network architectures for object localization and recognition in monocular visual, infrared and multispectral dynamic images. Furthermore, the possibility of analyzing fire scene images is studied and their current limitations are discussed. Finally, the understanding of the room con figuration (i.e., objects location) for indoor localization in reduced visibility environments and the linking with Building Information Models (BIM) are investigated.

关键词： Thermal fire analysis object detection and recognition convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Some aspects of crystal centering during X-ray high-throughput protein crystallography experiment

Some aspects of crystal centering during X-ray high-throughp...

引用

International Conference on Synchrotron and Free Electron Laser Radiation - Generation and Application (SFR)

作者： Gaponov, Yu. A. Matsugaki, N. Sasajima, K. Igarashi, N. Wakatsuki, S. Novosibirsk State Univ Dept Atmospher Res Pirogova 2 Novosibirsk 630090 Russia High Energy Accelerator Res Org Struct Biol Res Ctr 1-1 Oho Tsukuba Ibaraki 3050801 Japan Stanford Univ Stanford CA 94305 USA

A set of algorithms and procedures of a crystal loop centering during X-ray high-throughput protein crystallography experiment has been designed and developed. A simple algorithm of the crystal loop detection and preliminary recognition has been designed and developed. The crystal loop detection algorithm is based on finding out the crystal loop ending point (opposite to the crystal loop pin) using image cross section (digital image column) profile analysis. The crystal loop preliminary recognition procedure is based on finding out the crystal loop sizes and position using image cross section profile analysis. The crystal loop fine recognition procedure based on Hooke-Jeeves pattern search method with an ellipse as a fitting pattern has been designed and developed. The procedure of restoring missing coordinate of the crystal loop is described. Based on developed algorithms and procedures the optimal auto-centering procedure has been designed and developed. A procedure of optimal manual crystal centering (Two Clicks Procedure) has been designed and developed. Developed procedures have been integrated into control software system PCCS installed at crystallography beamlines Photon Factory BL5A and PF-AR NW12, KEK. (C) 2016 The Authors. Published by Elsevier B.V.

关键词： X-ray crystallography high-throughput protein crystallography control system SR object detection and recognition Linux

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：