Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Recognition of soccer players after occlusions using temporal color signatures

: Müller, Thomas; Manger, Daniel; Metzler, Jürgen

Volltext urn:nbn:de:0011-n-1924597 (122 KByte PDF)
MD5 Fingerprint: 8e5e02e249e3a449ec2eac8624d17660
Erstellt am: 17.1.2012

Arabnia, H.R.:
International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. Proceedings. Vol.1 : Affiliated with WORLDCOMP '11; July 18 - 21, 2011, Las Vegas, Nevada, USA
Las Vegas: CSREA Press, 2011
ISBN: 1-60132-189-9
ISBN: 1-60132-190-2
ISBN: 1-60132-191-0
International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV) <15, 2011, Las Vegas/Nev.>
World Congress in Computer Science, Computer Engineering, and Applied Computing (WORLDCOMP) <2011, Las Vegas/Nev.>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
soccer; tracking; recognition; color signature

This paper deals with the automatic assignment of players' identities in images of sport scenes. The task to correctly assign a player id to one unique player over many frames remains a challenging task as the players usually wear nearly identical jerseys and therefore generate visually similar appearances. If low image resolutions prohibit a direct jersey number recognition, tiny visual differences between the players like shoe, hair or skin colors can still support the recognition process. We propose a novel system which gathers such visual differences of players over multiple frames and allows for a successful identification of players. Results are presented in the context of a merge and split handling module of a player tracking system where the recognition can significantly improve the correct assignment of players after ambiguous merge and split situations.