Study of multi-targets tracking algorithm based on proposed particle filtering

Aiming at data correlation and estimation problems in particle filtering multi-targets tracking, classical particle filtering is extended into multi-targets state estimation in the given several observation process. Gibbs sampling is regarded as the methods of estimation and allocation correlation vector. Target state vector and association probability was jointly estimated without list, trim, threshold and other algorithms. This avoids merger drawbacks. Test is running in real video sequence. Stable tracking is realized under the complex tracking conditions. Experiments show that algorithms have strong the ability of solving data association problems.