Detection of the leading player in handball scenes using Mask R-CNN and STIPS (CROSBI ID 675788)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Pobar, Miran ; Ivašić-Kos, Marina
engleski
Detection of the leading player in handball scenes using Mask R-CNN and STIPS
In team sports scenes, recorded during training and lessons, it is common to have many players on the court, each with his own ball performing different actions. Our goal is to detect all players in the handball court and determine the leading player who performs the given handball technique such as a shooting at the goal, catching a ball or dribbling. This is a very challenging task for which, apart from an accurate object detector that is able to deal with cluttered scenes with many objects, partially occluded and with bad illumination, additional information is needed to determine the leading player. Therefore, we propose a leading player detector method combining the Mask R-CNN object detector and spatiotemporal interest points, referred to as MR-CNN+STIPs. The performance of the proposed leading player detector is evaluated on a custom sports video dataset acquired during handball training lessons. The performance of the detector in different conditions will be discussed.
Object detectors ; handball scenes ; Mask R-CNN ; spatiotemporal interest point – STIP tracking ; attention
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
110411V
2018.
nije evidentirano
objavljeno
978-151062748-2
10.1117/12.2522668
Podaci o matičnoj publikaciji
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018)
Verikas, A. ; Nikolaev, D.P. ; Radeva, P. ; Zhou, J.
München: SPIE
Podaci o skupu
11th International Conference on Machine Vision (ICMV 2018)
predavanje
01.11.2018-03.11.2018
München, Njemačka
Povezanost rada
Računarstvo, Informacijske i komunikacijske znanosti