摘要
为提高城市智能交通综合管理能力,提出了基于视频分析的运动车辆检测与跟踪方法。在城市交通干道路面环境中,根据运动目标与道路背景统计特性的差异,基于贝叶斯概率准则,提出一个自适应背景更新算法,检测分离运动车辆目标前景,采用卡尔曼滤波器实现对视频序列中车辆目标的运动检测与实时跟踪,并对在重庆某交通干道的交通流视频进行检测。试验结果表明:该方法在常规视频分辨率下能实现实时处理视频,平均检测准确率为94%,具有较好的实时性与鲁棒性,能够实现城市交通环境中各类运动车辆的检测与跟踪。
In order to improve the comprehensive management ability of intelligent transportation systems in cities, a detecting and tracking method of moving vehicle was presented by using video analysis. Considering the pavement environment of urban transport artery and the difference between moving object and the statistical characteristics for road background, an adaptive background updating algorithm was realized based on Bayesian probability criterion, from which foreground image was extracted. Motion detection and real-time tracking were realized for target vehicle in video sequence based on Kalman filter. The traffic flow video collected from a certain urban transport artery of Chongqing was detected by using the proposed method. Experimental result indicates that the video with normal resolution can be processed in time by using the method, and the average detecting accuracy is 94 %, so the proposed method has good real-time performance and robustness, and meets the requirement of real- time detecting and tracking vehicles in urban traffic arteries. 2 tabs, 5 figs, 15 refs.
出处
《交通运输工程学报》
EI
CSCD
北大核心
2012年第4期107-113,共7页
Journal of Traffic and Transportation Engineering
基金
国家自然科学基金项目(61004118)
重庆市自然科学基金项目(cstc2011jjA40030)
关键词
智能交通系统
交通流
检测方法
自适应背景
车辆跟踪
贝叶斯算法
卡尔曼滤波
intelligent transportation system
traffic flow
detecting method
adaptive background
vehicle tracking
Bayesian algorithm
Kalman filter
