联合轮廓法在低分辨率视频下的多目标追踪  

Multiple objects tracking in low resolution based on joint contour method

作　　者：程光[1] 罗予频[1] 王宏宝[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《计算机工程与应用》2007年第2期64-66,共3页Computer Engineering and Applications

摘　　要：相似目标间的遮挡一直是多目标追踪问题中的难点。针对这个问题提出了联合轮廓法。这种方法在使用粒子滤波器的基础上,通过对遮挡目标集的外轮廓建模来确定处于遮挡关系中目标的状态,从而进一步得到目标的轨迹。算法在实验中显示了良好的鲁棒性,并且计算复杂度与遮挡目标的个数成二次多项式关系。Tracking multiple similar objects is a challenging task,expecially in resolution,because of occlusion between objects. The Joint Contour Method（JCM） based on the particle filter is proposed to solve the problem of partial occlusion in this paper.It is a method to determine the object status by modeling the contour of the set of objects in occlusion.The computational complexity of JCM increases second-degree polynomially with the number of objects.The experiments demonstrate the robustness of the method.

关 键 词：多目标追踪 粒子滤波器 联合轮廓法 主动形状模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]