Multi-target Tracking Of Time-varying Number Of Targets

Multiple target tracking is an important theoretical and practical problem.The researchers all over the world have been engaged in the area for the recent decades.Many substantial results have been achieved,which have been widely applied to military fields such as ballistic missile defense,air reconnaissance and early-warning,battlefield surveillance.And some civil fields such as intelligent vehicle system,air traffic control,traffic navigation and robot vision system,etc.However,with the high-technique developing quickly,the tracking environment has changed significantly.The traditional theory and technique of multi-target tracking cannot face the new challenges.More and more complex requirements of the theoretic development have been set forth by various applied systems such as: nonlinear measurement,unknown number of target,dense clutter environment and group targets.To solve these problems,this paper focused on the time-varying number of multi-target and group targets tracking algorithm under dense clutter environment.The main works of this paper are:(1)Proposed an adaptive two-stage nonlinear filtering algorithm for the situation that the measurement equation is nonlinear and the measurement noise is large.In this situation,particle filter is easily to divergence.Using the estimate value of the particle filter for the second stage filter will help to improve the precision and stability of the nonlinear filtering.(2)Data association problem is one of the most difficult problem facing in multi-target tracking.It can be converted into a 0-1 optimization problem with constraints.In this paper,an improved differential evolution algorithm was designed and can effectively solve the optimal data association problem.(3)In the framework of universal track initiation,a one-step delay track initiation with adaptive threshold algorithm was designed in order to make a very good track initiation effect under the dense clutter environment.Also,we improve the algorithm by adding the track initiation,observations complement,and track termination module.So after that,JPDA algorithm can be applied to track the multi-target with time varying number of targets.(4)Proposed a group targets tracking algorithm based on the central group targets tracking algorithm and the relative position vector data association algorithm.The center position of the group got by central group targets tracking algorithm can be used by relative position vector data association algorithm to make an accurate association for each target in the group.So that we can obtain a more accurate estimate of the individual target state information.On the basis of the algorithm,time-varying number of targets and the group targets can be tracked in the same framework.