A spatio-velocity model based semantic event detection algorithm for traffic surveillance video
A spatio-velocity model based semantic event detection algorithm for traffic surveillance video作者机构：School of Instrument Science and Opto-Electro Engineering Beijing University Beijing China School of Software Beijing University Beijing China
出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)
年 卷 期：2010年第53卷第S1期
页 面：120-125页
核心收录：
学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0838[工学-公安技术]
主 题：trajectory clustering spatio-velocity statistic model event detection digital traffic
摘 要：Detection of vehicle events is a research hotspot in digital *** this paper,an approach is proposed to detect vehicle events with semantic analysis of traffic surveillance video using spatio-velocity statistic *** approach includes two successive phases:trajectory clustering and semantic events *** trajectory clustering,a statistic model of vehicle trajectories are presented,for which a spatio-velocity model is trained by analyzing the trajectories of moving vehicles in the *** on the trajectory,which represents both the position of the vehicle and its instantaneous velocity,a trajectory similarity measure is ***,an improved hierarchical clustering algorithm is adopted to cluster the trajectories according to different spatial and velocity *** each cluster,trajectories that are spatially close have similar velocities of motion and represent one type of activity *** the semantic events detection phase,statistic models of semantic regions in the scene are generated by estimating the probability density and velocity distributions of each type of activity ***,semantic events are detected by the proposed spatio-velocity statistic *** paper also presents experiments using real video sequence to verify the effectiveness of the proposed method.
维普期刊数据库
同方期刊数据库