引用本文: | 梁浩哲,黄魁华,李国辉,等.基于运动相似性的监控轨迹聚合分析[J].国防科技大学学报,2011,33(5):103-109.[点击复制] |
LIANG Haozhe,HUANG Kuihua,LI Guohui,et al.Aggregation Analysis of Surveillance Trajectory Based on Motion Similarity[J].Journal of National University of Defense Technology,2011,33(5):103-109[点击复制] |
|
|
|
本文已被:浏览 6560次 下载 4992次 |
基于运动相似性的监控轨迹聚合分析 |
梁浩哲, 黄魁华, 李国辉, 张军 |
(国防科技大学 信息系统工程重点实验室,湖南 长沙 410073)
|
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。 |
关键词: 轨迹聚合 核密度估计 隐马尔科夫模型 视频监控 |
DOI: |
投稿日期:2011-05-06 |
基金项目: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) |
|
Aggregation Analysis of Surveillance Trajectory Based on Motion Similarity |
LIANG Haozhe, HUANG Kuihua, LI Guohui, Zhang Jun |
(Science and Technology on Information Systems Engineering Laboratory, National Univ. of Defense Technology, Changsha 410073, China)
|
Abstract: |
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. |
Keywords: trajectory aggregation kernel density estimation hidden Markov model visual surveillance |
|
|
|
|
|