In traditional particle filter based TBD algorithm,a large number of particle probability distributions are required to predict the target position at the next moment,which increases the computational complexity.If a small number of particles are used,it can also lead to a decrease in tracking accuracy.In this paper,the traditional par-ticle filter TBD by adding the feature extraction was modified,in which the feature extraction is used to classify the target scope and clutter scope before target tracking to narrow down the scope of particle generation.The simulation results showed that the modified particle filter algorithm had significantly improved tracking performance compared to traditional particle filter algorithms.When the algorithm was applied to radar measured data,it also has good re-sults with engineering application value.
NETL
NSTL
万方数据
