A Co-inference Approach to Robust Visual Tracking

Visual trackan,g cou,ld be treeted as a param,eter estim.ation. problem, of target representastionbased on observations in im,age sequ.ences. A rich,er target represen,tation, would i n c w better ch,ances of successfd tracking in cluttered and dyn.a.m.ic en,viron,m,ents. However, th,e dim,ensionmlity of target's state space also increase.s m,&inlg tracking a formlidable estim,ation problem. I n this paper; the problem, of trncking and integmtin,g m,vltied in, n probabilistic fra,m,ework and torized graphical m,odel. Stmxtu.red of such gmphicnl m,odel factorizes diflerent m,odalities nn,d suggests 0.co-inference process am,on,g these m,odalities. A sequ.en,tial Mon,te Carlo a,lgorith,m. is propo.sed to give nn. eficien,t o,pproxim.ation of the co-inference based on the hportance sam,plin,g tech,n,ique. This nlgorith)m, is im,plem,ented in, real-ti,m,e at arou.nd 30Hz. Spec(fically, tro,ckin,g both position,, .sh,n,pe and color distribu.tion of a tnrget is investigated in, th,...

• Type: Conference
• Year: 2001
• Where: ICCV
• Authors: Ying Wu, Thomas S. Huang
• Keywords: Ation Problem, Computer Vision, Er Target Represen, Formlidable Estim, ICCV 2001, Rich, Tation