A particle filter deals with the state estimation problem for not only linear models with Gaussian noise but also for the non-linear models with non-Gaussian noise and receives great attention from many engineering fields. In the implementation of the particle filter, a resampling scheme is used to decrease the degeneracy phenomenon and improve estimation performance. Unfortunately, however, it comes out at the cost of the undesired the particle deprivation problem. In order to overcome this problem of the particle filter, we propose a novel filtering method called the genetic filter. Then the proposed filter, we embed the genetic algorithm into the particle filter and overcome the problems of particle filter. . Finally, the genetic filter is applied to the estimation problem of a moving train and its effectiveness is illustrated through computer simulation.