Object tracking method based on hybrid particle filter and sparse representation

In order to solve the problem of complex environmental impact like illumination variation, appearance change and partial occlusion during the object tracking in the sequence images, a hybrid particle filter tracking method based on the global and local information was proposed. The Local Binary Patterns (LBP) textual feature was imported into the particle filter algorithm which uses local information of the target via sparse coding on local patches and combines the global information to determine the tracking object. In the procedure, the robustness of the tracking algorithm was improved since the template is updated on the time. Experimental results show that the proposed tracking algorithm exhibited good result in the presence of complex background and partial occlusion.