東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Smart Cities and a Modern Approach t...

Ghyabi, Mehrdad,

FindBook

Google Book

Amazon

博客來

Smart Cities and a Modern Approach to Structural Health Monitoring: Autonomous Visual Sensing and Decision Making /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Smart Cities and a Modern Approach to Structural Health Monitoring: Autonomous Visual Sensing and Decision Making // Mehrdad Ghyabi.
作者:	Ghyabi, Mehrdad,
面頁冊數:	1 electronic resource (209 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
Contained By:	Dissertations Abstracts International86-02B.
標題:	Automotive engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31237547
ISBN:	9798383619186

Smart Cities and a Modern Approach to Structural Health Monitoring: Autonomous Visual Sensing and Decision Making /
Ghyabi, Mehrdad,

Smart Cities and a Modern Approach to Structural Health Monitoring: Autonomous Visual Sensing and Decision Making /Mehrdad Ghyabi. - 1 electronic resource (209 pages)

Source: Dissertations Abstracts International, Volume: 86-02, Section: B.

A smart city, in the context of infrastructure, can be defined as an urban area utilizing diverse sensing systems for autonomous data collection, processing, and decision-making to ensure safety, serviceability, and resiliency. Large-scale machine vision approaches recently emerged as a preferable alternative for achieving autonomy in data acquisition and processing, surpassing conventional structural sensing methods. This dissertation offers insights into an integrated infrastructure monitoring and operations framework for a smart city, focusing on machine vision-based data acquisition and denoising. Four key aspects are explored. Firstly, the research investigates vision-based data collection as a practical structural health monitoring (SHM) sensing approach. Techniques for vision-based response measurement are studied and compared in field setups, quantifying their efficiency by contrasting results with those recorded by conventional sensors. Secondly, the study explores the utilization of redundancies present in signals coming from different vison-based displacement measurement techniques and the use of a deep learning-based data fusion approach to enhance the signal-to-noise ratio (SNR) in measurements. The third study addresses challenges introduced when mounting a digital camera on an unmanned aerial vehicle (UAV), creating additional relative displacements. An approach utilizing a 3D targeting system in combination with camera pose estimation is developed and tested in lab and field experiments. The final part is focused on the fundamental concepts of ontology and its potential applications, discussing how ontology facilitates sensor data flow and its integration, structural data modeling, and knowledge sharing in SHM systems. A sample ontological model showcases the potential of using ontology to realize the digital twin concept for SHM in a smart city.

English

ISBN: 9798383619186Subjects--Topical Terms:

2181195
Automotive engineering.
Subjects--Index Terms:

Infrastructure

Smart Cities and a Modern Approach to Structural Health Monitoring: Autonomous Visual Sensing and Decision Making /
LDR:03438nmm a22004573i 4500 001 2429333
005 20250430100801.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798383619186
035 $a (MiAaPQD)AAI31237547
035 $a AAI31237547
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Ghyabi, Mehrdad, $e author. $0 (orcid)0000-0003-2652-426X $3 3817117
245 1 0 $a Smart Cities and a Modern Approach to Structural Health Monitoring: Autonomous Visual Sensing and Decision Making / $c Mehrdad Ghyabi.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (209 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
500 $a Advisors: Lattanzi, David Committee members: Urgessa, Girum; Kosecka, Jana; Esmaeili, Behzad.
502 $b Ph.D. $c George Mason University $d 2024.
520 $a A smart city, in the context of infrastructure, can be defined as an urban area utilizing diverse sensing systems for autonomous data collection, processing, and decision-making to ensure safety, serviceability, and resiliency. Large-scale machine vision approaches recently emerged as a preferable alternative for achieving autonomy in data acquisition and processing, surpassing conventional structural sensing methods. This dissertation offers insights into an integrated infrastructure monitoring and operations framework for a smart city, focusing on machine vision-based data acquisition and denoising. Four key aspects are explored. Firstly, the research investigates vision-based data collection as a practical structural health monitoring (SHM) sensing approach. Techniques for vision-based response measurement are studied and compared in field setups, quantifying their efficiency by contrasting results with those recorded by conventional sensors. Secondly, the study explores the utilization of redundancies present in signals coming from different vison-based displacement measurement techniques and the use of a deep learning-based data fusion approach to enhance the signal-to-noise ratio (SNR) in measurements. The third study addresses challenges introduced when mounting a digital camera on an unmanned aerial vehicle (UAV), creating additional relative displacements. An approach utilizing a 3D targeting system in combination with camera pose estimation is developed and tested in lab and field experiments. The final part is focused on the fundamental concepts of ontology and its potential applications, discussing how ontology facilitates sensor data flow and its integration, structural data modeling, and knowledge sharing in SHM systems. A sample ontological model showcases the potential of using ontology to realize the digital twin concept for SHM in a smart city.
546 $a English
590 $a School code: 0883
650 4 $a Automotive engineering. $3 2181195
650 4 $a Environmental engineering. $3 548583
653 $a Infrastructure
653 $a Computer vision
653 $a Data fusion
653 $a Deep learning
653 $a Unmanned aerial vehicle
653 $a Structural health monitoring
690 $a 0543
690 $a 0775
690 $a 0800
690 $a 0540
710 2 $a George Mason University. $b Civil and Infrastructure Engineering. $e degree granting institution. $3 3817118
720 1 $a Lattanzi, David $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-02B.
790 $a 0883
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31237547