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

Deep Learning for Touchless Human-Computer Interaction Using 3D Hand Pose Estimation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Learning for Touchless Human-Computer Interaction Using 3D Hand Pose Estimation./
作者:	Khaleghi, Leyla.
面頁冊數:	1 online resource (98 pages)
附註:	Source: Masters Abstracts International, Volume: 84-01.
Contained By:	Masters Abstracts International84-01.
標題:	Internet of Things. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29178524click for full text (PQDT)
ISBN:	9798835552184

Deep Learning for Touchless Human-Computer Interaction Using 3D Hand Pose Estimation.
Khaleghi, Leyla.

Deep Learning for Touchless Human-Computer Interaction Using 3D Hand Pose Estimation. - 1 online resource (98 pages)

Source: Masters Abstracts International, Volume: 84-01.

Thesis (M.Sc.)--Queen's University (Canada), 2022.

Includes bibliographical references

This thesis focuses on hand pose estimation (HPE) as a crucial component for humancomputer interaction (HCI), for example in gesture-based control for physical or virtual/augmented reality devices. We start by introducing an inexpensive and robust proof-of-concept mechanism for a practical gesture-based control system, which has been implemented and tested on a robotic wheel loader. To explore the feasibility and practicality of such a system, we resort to off-the-shelf equipment and models. Using an RGB camera and laptop, the system processes hand gestures in real-time in order to control a loader in construction zones. After designing four different hand gestures for controlling the loader, we collected 26000 images and trained a neural network to recognize the hand gestures. Prior to hand gesture recognition, we performed robust hand landmark detection through the use of an off-the-shelf solution. With the proposed hand gesture recognition system, we successfully controlled a loader to excavate a rock pile.Next in this thesis, we present a number of open problems in the area of HPE. Despite the significant progress in HPE in recent years, the accuracy and robustness of these methods still suffer from self-occlusion, as well as sensitivity to variations in camera viewpoints and environments. We thus focus on multi-view and video-based 3D HPE for developing a more robust system. Given the scarcity of multi-view and video-based datasets, we created a large synthetic multi-view video-based dataset of 3D hand poses. Over 402,000 synthetic hand images generated across 4,560 videos in our dataset. These videos were simultaneously captured from six different angles with complex backgrounds and varying levels of dynamic lighting. Next, we implemented a neural pipeline consisting of image encoders for obtaining visual embeddings of the hand, recurrent learners for learning jointly from multi-view information over time (videos), and graph networks with U-Net architectures for estimating the final 3D poses. The results of our studies demonstrate the added value of each component of our method as well as the benefits of including both temporal and sequential contextual information in the dataset. Finally we focus on the aggregate of contextual information across time and camera views, and use self-attention transformers for learning sequential contexts (time/view) for 3D HPE. Throughout our experiments, this method performed well for both temporal and angular sequence varieties. The method also achieved state-of-the-art results on our proposed dataset and a publicly available sequential dataset.

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

Mode of access: World Wide Web

ISBN: 9798835552184Subjects--Topical Terms:

3538511
Internet of Things.
Index Terms--Genre/Form:

542853
Electronic books.

Deep Learning for Touchless Human-Computer Interaction Using 3D Hand Pose Estimation.
LDR:03871nmm a2200349K 4500 001 2354430
005 20230414084755.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798835552184
035 $a (MiAaPQ)AAI29178524
035 $a (MiAaPQ)QueensUCan_197429996
035 $a AAI29178524
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Khaleghi, Leyla. $3 3694783
245 1 0 $a Deep Learning for Touchless Human-Computer Interaction Using 3D Hand Pose Estimation.
264 0 $c 2022
300 $a 1 online resource (98 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: 84-01.
500 $a Advisor: Etemad, Ali.
502 $a Thesis (M.Sc.)--Queen's University (Canada), 2022.
504 $a Includes bibliographical references
520 $a This thesis focuses on hand pose estimation (HPE) as a crucial component for humancomputer interaction (HCI), for example in gesture-based control for physical or virtual/augmented reality devices. We start by introducing an inexpensive and robust proof-of-concept mechanism for a practical gesture-based control system, which has been implemented and tested on a robotic wheel loader. To explore the feasibility and practicality of such a system, we resort to off-the-shelf equipment and models. Using an RGB camera and laptop, the system processes hand gestures in real-time in order to control a loader in construction zones. After designing four different hand gestures for controlling the loader, we collected 26000 images and trained a neural network to recognize the hand gestures. Prior to hand gesture recognition, we performed robust hand landmark detection through the use of an off-the-shelf solution. With the proposed hand gesture recognition system, we successfully controlled a loader to excavate a rock pile.Next in this thesis, we present a number of open problems in the area of HPE. Despite the significant progress in HPE in recent years, the accuracy and robustness of these methods still suffer from self-occlusion, as well as sensitivity to variations in camera viewpoints and environments. We thus focus on multi-view and video-based 3D HPE for developing a more robust system. Given the scarcity of multi-view and video-based datasets, we created a large synthetic multi-view video-based dataset of 3D hand poses. Over 402,000 synthetic hand images generated across 4,560 videos in our dataset. These videos were simultaneously captured from six different angles with complex backgrounds and varying levels of dynamic lighting. Next, we implemented a neural pipeline consisting of image encoders for obtaining visual embeddings of the hand, recurrent learners for learning jointly from multi-view information over time (videos), and graph networks with U-Net architectures for estimating the final 3D poses. The results of our studies demonstrate the added value of each component of our method as well as the benefits of including both temporal and sequential contextual information in the dataset. Finally we focus on the aggregate of contextual information across time and camera views, and use self-attention transformers for learning sequential contexts (time/view) for 3D HPE. Throughout our experiments, this method performed well for both temporal and angular sequence varieties. The method also achieved state-of-the-art results on our proposed dataset and a publicly available sequential dataset.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Internet of Things. $3 3538511
650 4 $a Human-computer interaction. $3 560071
650 4 $a Virtual reality. $3 527460
650 4 $a Neural networks. $3 677449
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Web studies. $3 2122754
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0984
690 $a 0646
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Queen's University (Canada). $3 1017786
773 0 $t Masters Abstracts International $g 84-01.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29178524 $z click for full text (PQDT)