Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Combined data association and evolving particle filter for tracking of multiple articulated objects.
AU - Bhaskar, Harish
AU - Mihaylova, Lyudmila
N1 - e-ISSN: 1687-5281
PY - 2011/3/15
Y1 - 2011/3/15
N2 - This paper proposes an approach for tracking multiple articulated targets using a combined data association and evolving population particle filter. A visual target is represented as a pictorial structure using a collection of parts together with a model of their geometry. Tracking multiple targets in video involves an iterative alternating scheme of selecting valid measurements belonging to a target from a clutter or other measurements that all fall within a validation gate. An algorithm with extended likelihood probabilistic data association and evolving groups of populations of particles representing a multiple-part distribution is designed. Variety in the particles is introduced using constrained genetic operators both in the sampling and resampling steps. We explore the effect of various model parameters on system performance and show that the proposed model achieves better accuracy than other widely used methods on standard datasets.
AB - This paper proposes an approach for tracking multiple articulated targets using a combined data association and evolving population particle filter. A visual target is represented as a pictorial structure using a collection of parts together with a model of their geometry. Tracking multiple targets in video involves an iterative alternating scheme of selecting valid measurements belonging to a target from a clutter or other measurements that all fall within a validation gate. An algorithm with extended likelihood probabilistic data association and evolving groups of populations of particles representing a multiple-part distribution is designed. Variety in the particles is introduced using constrained genetic operators both in the sampling and resampling steps. We explore the effect of various model parameters on system performance and show that the proposed model achieves better accuracy than other widely used methods on standard datasets.
KW - sequential Momte Carlo methods
KW - multiple articulated objects
KW - tracking
KW - evolving population
KW - genetic algorithms
U2 - 10.1155/2011/642532
DO - 10.1155/2011/642532
M3 - Journal article
VL - 2011
SP - 1
EP - 12
JO - EURASIP Journal on Image and Video Processing
JF - EURASIP Journal on Image and Video Processing
SN - 1687-5176
ER -