Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Part Affinity Field based Activity Recognition

 
: Golda, Thomas

:
Volltext urn:nbn:de:0011-n-6085663 (15 MByte PDF)
MD5 Fingerprint: 24da2489e6515eec88f05c282d96c21f
Erstellt am: 11.11.2020


Beyerer, Jürgen (Ed.); Zander, Tim (Ed.):
Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory 2019. Proceedings : July, 29 to August, 2, 2019, Triberg-Nussbach, Germany
Karlsruhe: KIT Scientific Publishing, 2020 (Karlsruher Schriften zur Anthropomatik 45)
ISBN: 978-3-7315-1028-4
DOI: 10.5445/KSP/1000118012
S.53-67
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation and Institute for Anthropomatics, Vision and Fusion Laboratory (Joint Workshop) <2019, Triberg-Nussbach>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

Abstract
This report presents work and results on Activity Recognition using Part AffinityFields for real-time surveillance applications. Starting with a short introductionto the motivation, this report gives a detailed overview over the key idea ofthe pursued approach and explains the basic ideas. In addition a variety ofexperiments on various subjects are presented, like i) the impact of the numberof input frames, ii) the impact of different simple dimensionality reductionapproaches, and iii) a comparison on how multi-class and binary problemformulation influence the performance.

: http://publica.fraunhofer.de/dokumente/N-608566.html