针对运动目标跟踪问题,提出一种利用视觉显著性和粒子滤波的目标跟踪算法。借鉴人类视觉注意机制的研究成果,根据目标的颜色、亮度和运动等特征形成目标的视觉显著性特征,与目标的颜色分布模型一起作为目标的特征表示模型,利用粒子滤波进行目标跟踪。该算法能够克服利用单一颜色特征所带来的跟踪不稳定问题,并能有效解决由于目标形变、光照变化以及目标和背景颜色分布相似而产生的跟踪困难问题,具有较强的鲁棒性。在多个视频序列中进行实验,并给出相应的实验结果和分析。实验结果表明,该算法用于实现运动目标跟踪是正确有效的。

Focusing on the problem of object tracking, an object-tracking algorithm based on visual saliency and particle filtering is proposed. Based on the research results of the human visual attention mechanism, this algorithm integrates features such as color, intensity and motion to generate the visual saliency feature. Both, the visual saliency feature and the color distribution model, are used as the representation model of the object. Particle filtering is used to track the object. This algorithm can overcome the instability brought by using a single color feature. It can also solve the difficulty caught by object shape changes, illumination variation, and the problems caused by target objects and background having similar color distributions. The algorithm has been tested on many video sequences. Experiment results and analysis are presented in this paper. The experimental results show that this algorithm is robust and it is effective and valid for object tracking.