To solve the problem that the traditional tracking algorithm cannot be used to effectively distinguish the image edges from the infrared dim-small targets, an improved infrared dim-small target tracking algorithm based on guided image filtering and kernelized correlation filtering (KCF) is proposed. Six groups of infrared dim-small target image array are adopted in the experiment, the obtained results are compared with that by the classical tracking algorithms. The experimental results indicate that the proposed algorithm has a better performance than the traditional algorithms on both subjective view and objective evaluating indicators, and the proposed algorithm possesses a higher tracking accuracy and a better real time performance.