An improved particle filter algorithm for Target Tracking

In order to track the object effectively in the real complex environment, the paper proposes an algorithm which fuses the color and edge feature to establish the object observation model. Color histogram which is not sensitive to the scale, rotation and deformation is a global description of the target and it is suitable to apply to tracking of the shelter and non-rigid object. However, particle filter tracking algorithm based on color cannot track the object correctly when in the condition of illumination changes and similar color clutters. Edge direction histogram contains some information about the structure of space, it can complement the information of the object when we create the observation model. Experiment results show that, the fusion algorithm can effectively overcome the similar color interference, occlusion, rotation, illumination and other issues, and improves the tracking accuracy, and has highly robust.