國立虎尾科技大學 |

Occupancy Tracking in a Building Using Convolutional Neural Networks.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Occupancy Tracking in a Building Using Convolutional Neural Networks./
作者:	Ortiz, Paul.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	80 p.
附註:	Source: Masters Abstracts International, Volume: 83-12.
Contained By:	Masters Abstracts International83-12.
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29069132
ISBN:	9798819371930

Occupancy Tracking in a Building Using Convolutional Neural Networks.
Ortiz, Paul.

Occupancy Tracking in a Building Using Convolutional Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 80 p.

Source: Masters Abstracts International, Volume: 83-12.

Thesis (M.S.E.E.)--New Mexico State University, 2022.

This item must not be sold to any third party vendors.

Tracking building occupancy has become an important topic due to recentadvances in smart devices. The ability to provide a reliable occupancy count in abuilding can improve smart device functionality, as well as improve the powerefficiency of their operation. This thesis presents a solution to tracking buildingoccupancy using the security cameras that are present in most commercialbuildings. This analysis was performed using a convolutional neural networkvthat ascertains the total occupancy of a building using computer vision andtrajectory calculation methods. The specific building this was tested in was astandard office and laboratory building on a college campus that experiences amoderate amount of traffic. The following thesis provides an analysis of whatspecific data was extracted from the video feed and how this data is translatedinto an occupancy count. A brief discussion on speeding up the network andhow the convolutional neural network was configured and a method to take theextracted data from the video feed and visualize it over a map of the building isdescribed. The resulting occupancy count was relatively accurate to theexpected occupancy of that building size and the occupant trajectories overlaidon the floor plan showing decent approximations of what path the occupantstook.

ISBN: 9798819371930Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Camera

Occupancy Tracking in a Building Using Convolutional Neural Networks.
LDR:02438nam a2200373 4500 001 1104595
005 20230619080057.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798819371930
035 $a (MiAaPQ)AAI29069132
035 $a AAI29069132
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ortiz, Paul. $3 1413466
245 1 0 $a Occupancy Tracking in a Building Using Convolutional Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 80 p.
500 $a Source: Masters Abstracts International, Volume: 83-12.
500 $a Advisor: Boucheron, Laura E.
502 $a Thesis (M.S.E.E.)--New Mexico State University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Tracking building occupancy has become an important topic due to recentadvances in smart devices. The ability to provide a reliable occupancy count in abuilding can improve smart device functionality, as well as improve the powerefficiency of their operation. This thesis presents a solution to tracking buildingoccupancy using the security cameras that are present in most commercialbuildings. This analysis was performed using a convolutional neural networkvthat ascertains the total occupancy of a building using computer vision andtrajectory calculation methods. The specific building this was tested in was astandard office and laboratory building on a college campus that experiences amoderate amount of traffic. The following thesis provides an analysis of whatspecific data was extracted from the video feed and how this data is translatedinto an occupancy count. A brief discussion on speeding up the network andhow the convolutional neural network was configured and a method to take theextracted data from the video feed and visualize it over a map of the building isdescribed. The resulting occupancy count was relatively accurate to theexpected occupancy of that building size and the occupant trajectories overlaidon the floor plan showing decent approximations of what path the occupantstook.
590 $a School code: 0143.
650 4 $a Electrical engineering. $3 596380
653 $a Camera
653 $a Machine learning
653 $a Occupancy
653 $a Smart device
653 $a Tracking
690 $a 0544
710 2 $a New Mexico State University. $b Electrical and Computer Engineering. $3 1413467
773 0 $t Masters Abstracts International $g 83-12.
790 $a 0143
791 $a M.S.E.E.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29069132