Visual tracking of multiple targets is a key step in surveil- lance scenarios, far from being solved due to its intrinsic ill-posed nature. In this paper, a comparison of Multi- Hypothesis Kalman Filter and Particle Filter-based track- ing is presented. Both methods receive input from a novel online background subtraction algorithm. The aim of this work is to highlight advantages and disadvantages of such tracking techniques. Results are performed using public challenging data set (PETS 2009), in order to evaluate the approaches on significant benchmark data.
A Comparison of Multi Hypothesis Kalman Filter and Particle Filter for Multi-target Tracking / L., Bazzani; Bloisi, Domenico Daniele; V., Murino. - ELETTRONICO. - (2009), pp. 47-54. (Intervento presentato al convegno Eleventh IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009) tenutosi a Miami, Florida nel 2009).
A Comparison of Multi Hypothesis Kalman Filter and Particle Filter for Multi-target Tracking
BLOISI, Domenico Daniele;
2009
Abstract
Visual tracking of multiple targets is a key step in surveil- lance scenarios, far from being solved due to its intrinsic ill-posed nature. In this paper, a comparison of Multi- Hypothesis Kalman Filter and Particle Filter-based track- ing is presented. Both methods receive input from a novel online background subtraction algorithm. The aim of this work is to highlight advantages and disadvantages of such tracking techniques. Results are performed using public challenging data set (PETS 2009), in order to evaluate the approaches on significant benchmark data.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.