• norsk
    • English
  • English 
    • norsk
    • English
  • Login
View Item 
  •   Home
  • Sentraladministrasjonen
  • Publikasjoner fra Cristin
  • View Item
  •   Home
  • Sentraladministrasjonen
  • Publikasjoner fra Cristin
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Using 3D Convolutional Neural Networks for Real-time Detection of Soccer Events

Rongved, Olav Andre Nergård; Hicks, Steven; Thambawita, Vajira L B; Stensland, Håkon Kvale; Zouganeli, Evi; Johansen, Dag; Riegler, Michael Alexander; Halvorsen, Pål
Peer reviewed, Journal article
Accepted version
Thumbnail
View/Open
Extended_IEEE_ISM_2020_journal_version___soccer_event_detection-2.pdf (6.332Mb)
URI
https://hdl.handle.net/11250/3036038
Date
2021
Metadata
Show full item record
Collections
  • Publikasjoner fra Cristin [4163]
  • TKD - Institutt for informasjonsteknologi [1039]
  • TKD - Institutt for maskin, elektronikk og kjemi [265]
Original version
https://doi.org/10.1142/S1793351X2140002X
Abstract
Developing systems for the automatic detection of events in video is a task which has gained attention in many areas including sports. However, there are still a number of shortcomings with current systems, such as high latency and determining proper timing boundaries for events detected, making it challenging to operate at the live edge. In this paper, we present an algorithm to detect events in soccer videos in real time, using 3D convolutional neural networks. We run and evaluate our algorithm based on on three different real-world soccer data sets from SoccerNet, the Swedish elite series Allsvenskan, and the Norwegian elite series Eliteserien. Overall, the results show that we can detect highly relevant events with high recall, low latency, and accurate time estimation. Rapid response matters most for us, but we compare our results with current state-of-the-art that has less strict timing requirements. We conclude that our algorithm can detect most events in real-times, but still can be improved with slightly better precision. In addition to the presented algorithm, we perform an extensive ablation study on how the different parts of the training pipeline affect the final results.
Publisher
World Scientific Publishing
Series
International Journal of Semantic Computing (IJSC);Volume 15, Issue 02
Journal
International Journal of Semantic Computing (IJSC)
Copyright
© World Scientific Publishing Company

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit
 

 

Browse

ArchiveCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDocument TypesJournalsThis CollectionBy Issue DateAuthorsTitlesSubjectsDocument TypesJournals

My Account

Login

Statistics

View Usage Statistics

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit