将均值漂移算法和粒子滤波算法分别做出改进后进行有效结合,在非遮挡和不严重遮挡情况下,采用改进的均值漂移算法,在严重遮挡情况下,采用改进的粒子滤波算法,并在遮挡结束后验证正确的跟踪是否得到恢复,提出有效的分块检测遮挡算法,遮挡期间颜色模板不更新,实验结果表明该算法具有较好的实时性和鲁棒性,能有效实现复杂场景下的目标跟踪。 The mean shift algorithm and the particle filter algorithm are respectively improved and combined effectively. Under the condition of non-occlusion and non-occlusion, an improved mean shift algorithm is adopted. In the case of serious occlusion, the improved particle filter algorithm is used and the occlusion After the verification, whether the correct tracking is restored or not is proposed, an effective block detection occlusion algorithm is proposed, and the color template is not updated during occlusion. Experimental results show that the proposed algorithm has better real-time performance and robustness and can effectively achieve the target under complex scenarios track.