一种基于均值移位的红外目标跟踪新方法

均值移位算法是一种搜索与样本点分布最相近模式的非参数统计方法．在彩色序列图像目标跟踪中，均值移位算法是一种有效的方法．但在红外目标跟踪中，由于单一灰度特征空间缺乏描述红外目标的信息，使得基于均值移位算法的红外目标跟踪不稳健．为了克服这个缺点，提出了构造级联灰度空间的红外目标跟踪新方案．同时，对于不同的红外图像序列使用不同的方法产生级联灰度空间．实验结果表明该方法对于红外小目标以及强杂波背景目标的跟踪是有效和稳健的．

NOVEL INFRARED OBJECT TRACKING METHOD BASED ON MEAN SHIFT

The mean shift algorithm is a nonparametric statistical method for seeking the nearest mode of a point sample distribution. In the color image sequence, the mean shift algorithm is an efficient method for tracking object. However, there is a singular grey space for representing the infrared object in the infrared object tracking scenario. Due to the lack of the information for the object representation, the object tracking based on the mean shift algorithm may be lost in the infrared sequence. To overcome this disadvantage, a new scheme that is to construct a cascade grey space is proposed. Moreover, for the different infrared image sequence, different strategies are used to generate different cascade grey spaces. The experimental results of two different infrared image sequences show our new scheme is efficient and robust for the infrared small object tracking and infrared object in the severe clutter background tracking.