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

Automatic Mapping of Football Team Formation Using Computer Vision.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automatic Mapping of Football Team Formation Using Computer Vision./
作者:	Trastelis, Filimon
面頁冊數:	1 online resource (70 pages)
附註:	Source: Masters Abstracts International, Volume: 84-08.
Contained By:	Masters Abstracts International84-08.
標題:	Football. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30203346click for full text (PQDT)
ISBN:	9798371942609

Automatic Mapping of Football Team Formation Using Computer Vision.
Trastelis, Filimon

Automatic Mapping of Football Team Formation Using Computer Vision. - 1 online resource (70 pages)

Source: Masters Abstracts International, Volume: 84-08.

Thesis (M.S.)--University of Piraeus (Greece), 2022.

Includes bibliographical references

The integration of artificial intelligence in the area of sports is showing an upward trend the past few years. There is now a vast amount of generated data that can be processed and transformed into useful information in various aspects of a high demand sport such as football. In this thesis, primary target is the extraction and visualization of tactical statistics from broadcast videos of football matches. Continuous video frames are being processed and analyzed, in order to detect players positions and project both teams formations on a static top view of a football field. The emerging knowledge from the results can be valuable for the examination of the tactical team's performance during the game. Deep learning methods from the area of computer vision are applied to fulfill the tasks of players identification and camera pose estimation. A state of the art data set is used for the evaluation of different frameworks and the whole procedure is validated using image sequences acquired from Greek football matches. Ground truth data were generated manually for the two main tasks and the predicted results were compared with them to measure their accuracy.

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

Mode of access: World Wide Web

ISBN: 9798371942609Subjects--Topical Terms:

643161
Football.
Index Terms--Genre/Form:

542853
Electronic books.

Automatic Mapping of Football Team Formation Using Computer Vision.
LDR:05323nmm a2200385K 4500 001 2355822
005 20230523083442.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798371942609
035 $a (MiAaPQ)AAI30203346
035 $a (MiAaPQ)Piraeus14683
035 $a AAI30203346
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
066 $c (S
100 1 $6 880-01 $a Trastelis, Filimon $3 3696279
245 1 0 $a Automatic Mapping of Football Team Formation Using Computer Vision.
264 0 $c 2022
300 $a 1 online resource (70 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: 84-08.
500 $a Advisor: Μαγκλογιάννης, Ηλίας ; Maglogiannis, Ilias.
502 $a Thesis (M.S.)--University of Piraeus (Greece), 2022.
504 $a Includes bibliographical references
520 $a The integration of artificial intelligence in the area of sports is showing an upward trend the past few years. There is now a vast amount of generated data that can be processed and transformed into useful information in various aspects of a high demand sport such as football. In this thesis, primary target is the extraction and visualization of tactical statistics from broadcast videos of football matches. Continuous video frames are being processed and analyzed, in order to detect players positions and project both teams formations on a static top view of a football field. The emerging knowledge from the results can be valuable for the examination of the tactical team's performance during the game. Deep learning methods from the area of computer vision are applied to fulfill the tasks of players identification and camera pose estimation. A state of the art data set is used for the evaluation of different frameworks and the whole procedure is validated using image sequences acquired from Greek football matches. Ground truth data were generated manually for the two main tasks and the predicted results were compared with them to measure their accuracy.
520 $a Η ενσωμάτωση της τεχνητής νοημοσύνης στον χώρο του ποδοσφαίρου παρουσιάζει ανοδική τάση τα τελευταία χρόνια. Υπάρχει πλέον ένας τεράστιος όγκος παραγόμενων δεδομένων που μπορούν να υποβληθούν σε επεξεργασία και να μετατραπούν σε χρήσιμες πληροφορίες σε διάφορες πτυχές ενός αθλήματος υψηλής ζήτησης όπως το ποδόσφαιρο. Στην παρούσα διπλωματική εργασία, πρωταρχικός στόχος είναι η εξαγωγή και οπτικοποίηση στατιστικών από βίντεο ποδοσφαιρικών αγώνων. Συνεχή καρέ βίντεο υπόκεινται σε επεξεργασία και ανάλυση, προκειμένου να εντοπιστούν οι θέσεις των παικτών και να προβληθούν οι σχηματισμοί των δύο ομάδων σε μια στατική κάτοψη ενός γηπέδου ποδοσφαίρου. Η γνώση που προκύπτει από τα αποτελέσματα μπορεί να είναι πολύτιμη για την εξέταση της απόδοσης της ομάδας κατά τη διάρκεια του παιχνιδιού. Μέθοδοι βαθιάς μάθησης από τον τομέα της υπολογιστικής όρασης εφαρμόζονται για την διεκπεραίωση των διαδικασιών αναγνώρισης των παικτών και εκτίμησης της οπτικής γωνίας της κάμερας. Χρησιμοποιείται ένα σύνολο δεδομένων τελευταίας τεχνολογίας για την αξιολόγηση διαφορετικών τεχνικών και η όλη διαδικασία επικυρώνεται χρησιμοποιώντας ακολουθίες εικόνων που αποκτήθηκαν από αγώνες του ελληνικού ποδοσφαίρου. Τα πραγματικά δεδομένα δημιουργήθηκαν χειροκίνητα για τις δύο κύριες διαδικασίες και τα προβλεπόμενα αποτελέσματα συγκρίθηκαν με αυτά για να μετρηθεί η ακρίβειά τους.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Football. $3 643161
650 4 $a Cameras. $3 524039
650 4 $a Basketball. $3 629604
650 4 $a Video recordings. $3 575241
650 4 $a Calibration. $3 2068745
650 4 $a Pandemics. $3 3464080
650 4 $a Real time. $3 3562675
650 4 $a Sensors. $3 3549539
650 4 $a Neural networks. $3 677449
650 4 $a Color. $3 533870
650 4 $a Maps. $3 544078
650 4 $a Tournaments & championships. $3 3564484
650 4 $a Registration. $3 3682192
650 4 $a Algorithms. $3 536374
650 4 $a Soccer. $3 520214
650 4 $a Ice hockey. $3 3682532
650 4 $a Sports officiating. $3 639324
650 4 $a Semantics. $3 520060
650 4 $a Professional hockey. $3 3682533
650 4 $a Logic. $3 529544
650 4 $a Sports management. $3 3423935
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0395
690 $a 0430
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Piraeus (Greece). $3 3690333
773 0 $t Masters Abstracts International $g 84-08.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30203346 $z click for full text (PQDT)
880 1 $6 100-01/(S $a Τραστέλης, Φιλήμων.