Multi-cue fusion is an effective means to solve the tracking problem under many complex conditions. Therefore, a multi-cue fusion particle filter tracking method is proposed, in which the target can be adaptive fragmented. The target model is built based on the color distribution of the target, which can improve the adaptability of the initial description. During the tracking process, the multi-cue fusion particle filter can dynamically adjust the weights of fragments according to the reliability of them, which can improve the flexibility of the tracker to deal with some complex circumstances, such as dramatic light change, target posture change and occluded by other objects. Experimental results show that the proposed method can accurately track the target effectively on many kinds of complex circumstances.