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

Generating Tennis Player by the Predicting Movement Using 2D Pose Estimation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Generating Tennis Player by the Predicting Movement Using 2D Pose Estimation./
作者:	Al Shami, Ali Kareem.
面頁冊數:	1 online resource (75 pages)
附註:	Source: Masters Abstracts International, Volume: 84-03.
Contained By:	Masters Abstracts International84-03.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29325396click for full text (PQDT)
ISBN:	9798841734000

Generating Tennis Player by the Predicting Movement Using 2D Pose Estimation.
Al Shami, Ali Kareem.

Generating Tennis Player by the Predicting Movement Using 2D Pose Estimation. - 1 online resource (75 pages)

Source: Masters Abstracts International, Volume: 84-03.

Thesis (M.Sc.)--University of Colorado Colorado Springs, 2022.

Includes bibliographical references

People's bodies move differently to perform different actions. In order to recognize or predict human actions in videos, we need to understand the movements of people's bodies. We believe that estimating pose (positions of body joints) is an excellent approach that we can use in sports for action recognition and prediction. This thesis discusses learning to predict the positions of the human body's key points based on past positions using a deep learning-based approach. We generate an automated tennis player by predicting the future movements of the second player based on the coordinates of the 2D key joints for the two players, using the Yolo v3 model for object detection and the Openpose model for 2D pose estimation in short videos. The dataset has been created using YouTube videos. It contains the coordinates of the bounding boxes, the coordinates of the key joints for two players in a single tennis game, and the tennis ball's coordinates using the TrackNet model. We train the sequence model on our dataset to predict future movement using different artificial neural network architectures. We obtain good results with low error by training the model on data from two prior frames and predicting the third using a four-layers sequence model.

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

Mode of access: World Wide Web

ISBN: 9798841734000Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Tennis playerIndex Terms--Genre/Form:

542853
Electronic books.

Generating Tennis Player by the Predicting Movement Using 2D Pose Estimation.
LDR:02602nmm a2200397K 4500 001 2355794
005 20230523083434.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798841734000
035 $a (MiAaPQ)AAI29325396
035 $a AAI29325396
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Al Shami, Ali Kareem. $3 3696239
245 1 0 $a Generating Tennis Player by the Predicting Movement Using 2D Pose Estimation.
264 0 $c 2022
300 $a 1 online resource (75 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: 84-03.
500 $a Advisor: Kalita, Jugal.
502 $a Thesis (M.Sc.)--University of Colorado Colorado Springs, 2022.
504 $a Includes bibliographical references
520 $a People's bodies move differently to perform different actions. In order to recognize or predict human actions in videos, we need to understand the movements of people's bodies. We believe that estimating pose (positions of body joints) is an excellent approach that we can use in sports for action recognition and prediction. This thesis discusses learning to predict the positions of the human body's key points based on past positions using a deep learning-based approach. We generate an automated tennis player by predicting the future movements of the second player based on the coordinates of the 2D key joints for the two players, using the Yolo v3 model for object detection and the Openpose model for 2D pose estimation in short videos. The dataset has been created using YouTube videos. It contains the coordinates of the bounding boxes, the coordinates of the key joints for two players in a single tennis game, and the tennis ball's coordinates using the TrackNet model. We train the sequence model on our dataset to predict future movement using different artificial neural network architectures. We obtain good results with low error by training the model on data from two prior frames and predicting the third using a four-layers sequence model.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Sports management. $3 3423935
650 4 $a Bioinformatics. $3 553671
650 4 $a Biomechanics. $3 548685
653 $a Tennis player
653 $a Movement prediction
653 $a 2D pose estimation
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0464
690 $a 0648
690 $a 0715
690 $a 0430
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Colorado Colorado Springs. $b College of Engineering and Applied Science-Computer Science. $3 3344166
773 0 $t Masters Abstracts International $g 84-03.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29325396 $z click for full text (PQDT)