Abstract: Spatiograms outperform the traditional color histogram，which contain color information and spatial layout of these colors for the target.In particle filters framework，a normal random drift model is utilized to describe the state model;a similarity function of spatiograms is used as the probability model for observation.A target tracking algorithm is proposed using particle filters based on spatiograms.Experimental results indicate that the proposed algorithm has better robustness than the traditional particle filters based on color histogram.

Key words: spatiograms, particle filters, target tracking

摘要： 空间直方图融合了目标的颜色信息和颜色的空间分布信息，比传统的颜色直方图更具有目标鉴别能力。在基于粒子滤波算法的目标跟踪系统框架中，采用简单的随机漂移模型表示系统状态模型，通过空间直方图的相似度定义来建立系统观测概率模型，提出一种基于空间直方图的粒子滤波目标跟踪算法。实验结果表明，相比传统的基于颜色直方图的粒子滤波算法，提出的算法具有更好的鲁棒性。

关键词: 空间直方图, 粒子滤波, 目标跟踪