Object tracking method based on improved particle swarm optimization

To overcome the limitations of inertia weight adjustment mechanism when the particle swarm optimization algorithm is applied to object tracking, an improved particle swarm optimization object tracking algorithm is proposed. Firstly, the object and the parameters in particle swarm optimization algorithm are initialized. Secondly, the inertia weight adjustment mechanism is improved by using the evolution rate of particle, and the inertia weight is achieved by taking the conditions of different particles in each generation into consideration. Then the speed, the position, the individual optimum and the global optimum of the particles are updated simultaneously while the next iteration is proceeding. Finally, the area which has the largest similarity function value is defined as the object by comparing the fitness value of each particle with the others. Experimental results indicate that the method reduces the iterations to obtain the same fitness value, and improves the operation efficiency by 42.9% in comparison with the particle swarm optimization object tracking method which uses self-adapted inertia weight adjustment mechanism. The accurate positioning of the object is achieved in the case of the similarity function presenting “multimodal”, and the method is well adapted to the situation when partial occlusion occurs in object tracking.