000182800 001__ 182800
000182800 005__ 20190316235537.0
000182800 022__ $$a0932-8092
000182800 037__ $$aARTICLE
000182800 245__ $$aTracking Multiple Players using a Single Camera
000182800 269__ $$a2013
000182800 260__ $$bSpringer Verlag$$c2013
000182800 336__ $$aJournal Articles
000182800 520__ $$aIt has been shown that multi-people tracking could be successfullly formulated as a Linear Program to process the output of multiple fixed and synchronized cameras with overlapping fields of view. In this paper, we extend this approach to the more challenging single-camera case and show that it yields excellent performance, even when the camera moves. We validate our approach on a number of basketball matches and argue that using a properly retrained people detector is key to producing the probabilities of presence that are used as input to the Linear Program.
000182800 6531_ $$aMonocular Tracking
000182800 700__ $$0242722$$aBen Shitrit, Horesh$$g193130
000182800 700__ $$0244458$$aRaca, Mirko$$g202799
000182800 700__ $$0240254$$aFleuret, François$$g146262
000182800 700__ $$0240252$$aFua, Pascal$$g112366
000182800 773__ $$tMachine Vision and Applications
000182800 8564_ $$s6345540$$uhttps://infoscience.epfl.ch/record/182800/files/top.pdf$$yn/a$$zn/a
000182800 909C0 $$0252087$$pCVLAB$$xU10659
000182800 909CO $$ooai:infoscience.tind.io:182800$$pIC$$particle$$qGLOBAL_SET
000182800 917Z8 $$x112366
000182800 917Z8 $$x112366
000182800 917Z8 $$x112366
000182800 937__ $$aEPFL-ARTICLE-182800
000182800 973__ $$aEPFL$$rREVIEWED$$sSUBMITTED
000182800 980__ $$aARTICLE