基于自适应背景的多特征融合目标跟踪  

Object tracking by fusing multiple features based on adaptive background information

作　　者：李睿[1] 刘昌旭[1] 年福忠[1] 

机构地区：[1]兰州理工大学计算机与通信学院,兰州730050

出　　处：《计算机应用》2013年第3期651-655,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61263019);甘肃省高等学校基本科研业务费资助项目(1114ZTC144)

摘　　要：针对基于单一特征的目标跟踪算法,在复杂情形下,很难准确跟踪目标的问题,提出一种基于自适应背景的多特征融合目标跟踪算法。该算法利用颜色和基于灰度共生矩阵纹理特征表征目标,在粒子滤波的框中,通过分析在不同特征下,粒子空间分布、权值分布,以及特征对背景的区分性,提出一种有效的融合系数计算方法;根据在跟踪过程中目标外观的变化情况,自适应更新目标模板。在不同场景下的实验结果表明:该算法在不降低实时性的前提下,抗背景干扰能力大幅度提高;在各种场景下,均具有良好的稳定性和鲁棒性。It is difficult for the object tracking algorithm based on single feature, to track the object in complex cases. Therefore, this paper proposed an algorithm fusing muhiple features for object tracking based on adaptive background information. The algorithm was based on the use of color feature and gray level co-occurrence matrix texture feature to represent the object. Under the frame of particle filter, it analyzed the particle space distribution, particle value distribution and ability to distinguish the background information with different feature. Then it presented an efficient fusion coefficient calculation. According to the object＇s appearance of changes in the process of tracking, it updated the object template adaptively. The experimental results in different settings show that this algorithm greatly improves the resistance to background interference, under the premise of not reducing the real-time. In all sorts of situations, it has good stability and robustness.

关 键 词：目标跟踪 粒子滤波 多特征融合 颜色特征 纹理特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]