红外小目标跟踪易受到相似目标与背景的干扰，针对此问题提出一种融合灰度与速度线索的红外小目标跟踪算法。该算法通过快速时域高通滤波器滤除噪声并突出目标，利用主分量分析提取速度特征；以分层粒子滤波为框架，首先利用高通滤波图像灰度核函数加权直方图进行第1层粒子滤波，粗略地估计目标状态；然后利用速度线索进行第2层粒子滤波，精确地估计目标状态。实验结果表明，提出的红外小目标跟踪算法具有较强的抗干扰性能和较高的跟踪精度。

Infrared small target tracking is susceptible to similar target and background. To address this problem, an algorithm for infrared small target tracking based on gray and velocity cue integration is proposed. The algorithm enhances the target with high pass filter, and calculates velocity of target by principal component analysis. Target tracking is achieved by a cascade particle filter which consists of two stages of importance sampling. At the first stage, the states of target are crudely estimated with gray kernel histogram in high pass filter space. The velocity cues are used to precisely calculate the states of target in the second stage. The experimental results show that the proposed algorithm has stronger ability to resist to interference of noise, and significantly improves the tracking accuracy in comparison with existing tracking algorithms.