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

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Investigating Machine Vision Dataset Quality for Near-Real Time Detection and Tracking on Unmanned Aerial Vehicles.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Investigating Machine Vision Dataset Quality for Near-Real Time Detection and Tracking on Unmanned Aerial Vehicles./
作者:	Blenk, Elizabeth Rose.
面頁冊數:	1 online resource (125 pages)
附註:	Source: Masters Abstracts International, Volume: 83-09.
Contained By:	Masters Abstracts International83-09.
標題:	Unmanned aerial vehicles. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28973086click for full text (PQDT)
ISBN:	9798780651840

Investigating Machine Vision Dataset Quality for Near-Real Time Detection and Tracking on Unmanned Aerial Vehicles.
Blenk, Elizabeth Rose.

Investigating Machine Vision Dataset Quality for Near-Real Time Detection and Tracking on Unmanned Aerial Vehicles. - 1 online resource (125 pages)

Source: Masters Abstracts International, Volume: 83-09.

Thesis (M.Sc.)--North Carolina State University, 2021.

Includes bibliographical references

The field of machine vision is continuously evolving to address new applications and overcome challenges. The application of near-real time object detection and tracking on an unmanned aerial vehicle at high altitudes is challenges with computational resources based on weight and camera vibration impacting image quality, fast moving environments and variability of target object in frame. This research explores the impacts of manipulating the training dataset on performance metrics and object predictions with the goal of better understanding how to construct a robust training dataset for successful deployment on a UAV. The research space is vast and several smaller studies were conducted to begin understanding how manipulating the training data affects the resulting model. The research conducted focused on dataset size, approaches to labeling objects, and image augmentation.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798780651840Subjects--Topical Terms:

3560267
Unmanned aerial vehicles.
Index Terms--Genre/Form:

542853
Electronic books.

Investigating Machine Vision Dataset Quality for Near-Real Time Detection and Tracking on Unmanned Aerial Vehicles.
LDR:02243nmm a2200373K 4500 001 2354125
005 20230324111205.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798780651840
035 $a (MiAaPQ)AAI28973086
035 $a (MiAaPQ)NCState_Univ18402039197
035 $a AAI28973086
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Blenk, Elizabeth Rose. $3 3694468
245 1 0 $a Investigating Machine Vision Dataset Quality for Near-Real Time Detection and Tracking on Unmanned Aerial Vehicles.
264 0 $c 2021
300 $a 1 online resource (125 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: Masters Abstracts International, Volume: 83-09.
500 $a Advisor: Lobaton, Edgar; Buckner, Gregory; Ferguson, Scott.
502 $a Thesis (M.Sc.)--North Carolina State University, 2021.
504 $a Includes bibliographical references
520 $a The field of machine vision is continuously evolving to address new applications and overcome challenges. The application of near-real time object detection and tracking on an unmanned aerial vehicle at high altitudes is challenges with computational resources based on weight and camera vibration impacting image quality, fast moving environments and variability of target object in frame. This research explores the impacts of manipulating the training dataset on performance metrics and object predictions with the goal of better understanding how to construct a robust training dataset for successful deployment on a UAV. The research space is vast and several smaller studies were conducted to begin understanding how manipulating the training data affects the resulting model. The research conducted focused on dataset size, approaches to labeling objects, and image augmentation.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Unmanned aerial vehicles. $3 3560267
650 4 $a Artificial intelligence. $3 516317
650 4 $a Neural networks. $3 677449
650 4 $a Aerospace engineering. $3 1002622
650 4 $a Engineering. $3 586835
650 4 $a Robotics. $3 519753
650 4 $a Transportation. $3 555912
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0538
690 $a 0537
690 $a 0771
690 $a 0709
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a North Carolina State University. $3 1018772
773 0 $t Masters Abstracts International $g 83-09.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28973086 $z click for full text (PQDT)