Deepball: Deep neural-network ball detector

Jacek Komorowski , Grzegorz Kurzejamski , Grzegorz Sarwas

Abstract

The paper describes a deep network based object detector specialized for ball detection in long shot videos. Due to its fully convolutional design, the method operates on images of any size and produces ball confidence map encoding the position of detected ball. The network uses hypercolumn concept, where feature maps from different hierarchy levels of the deep convolutional network are combined and jointly fed to the convolutional classification layer. This allows boosting the detection accuracy as larger visual context around the object of interest is taken into account. The method achieves state-of-the-art results when tested on publicly available ISSIA-CNR Soccer Dataset.

Author Jacek Komorowski (FEIT / ICS)
Jacek Komorowski,,
- The Institute of Computer Science
, Grzegorz Kurzejamski (FoEE / ICIE)
Grzegorz Kurzejamski,,
- The Institute of Control and Industrial Electronics
, Grzegorz Sarwas (FoEE / ICIE)
Grzegorz Sarwas,,
- The Institute of Control and Industrial Electronics
Pages297-304
Publication size in sheets0.5
Book Cláudio Ana Paula, Bouatouch Kadi, Brazio Jose (eds.): VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 5, 2019, SciTePress, ISBN 978-989-758-354-4, 458 p.
DOIDOI:10.5220/0007348902970304
URL https://www.scitepress.org/PublicationsDetail.aspx?ID=E4Co8cpO2pQ=&t=1
Languageen angielski
File
VISAPP_2019_62.pdf 1.75 MB
Score (nominal)0
ScoreMinisterial score = 0.0, 18-07-2019, ChapterFromConference
Publication indicators Scopus Citations = 0
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back