基于运动相似性的监控轨迹聚合分析  

Aggregation Analysis of Surveillance Trajectory Based on Motion Similarity

作　　者：梁浩哲[1] 黄魁华[1] 李国辉[1] 张军[1] 

机构地区：[1]国防科技大学信息系统工程重点实验室,湖南长沙410073

出　　处：《国防科技大学学报》2011年第5期103-109,共7页Journal of National University of Defense Technology

基　　金：国家自然科学基金资助项目(60902093);国防科技大学优秀研究生创新基金资助项目(S080501)

摘　　要：对于监控轨迹序列集,提出一种使用运动特征发现其潜在语义内容的方法。在特征统计估计阶段,将轨迹曲线中的拐点特征加入到核密度估计过程中,得到准确平滑的方向多性态分布;使用隐马尔科夫模型估计轨迹子类中存在的串行或并行空间模式。最后以运动特征分布为基础,提出一种基于运动相似性的轨迹层次聚合模型。实验结果表明,该模型可以有效地分析轨迹序列集的潜在结构,反映了场景中存在的运动区域信息。For surveillance trajectory,a potential semantic content discovering method based on motion features was investigated.In the phase of feature estimation,precise and smooth multi-modal distribution of direction was obtained by combining inflection points of trajectory curve with the kernel density estimation.Then sequential and concurrent temporal patterns of trajectory sub-class were modeled by Hidden Markov Model.With motion feature distribution,a hierarchical trajectory aggregation model based on motion similarity was proposed.Experimental results show that the model can be used to discover potential structure of trajectory set which reflect the motion region information of surveillance scene.

关 键 词：轨迹聚合 核密度估计 隐马尔科夫模型 视频监控 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]