|
|||||
|
|
| 交通视频中的Kalman滤波的多车辆跟踪算法 | |
| 引用本文： | 贲晛烨,王科俊,李阳,谢滨姣.交通视频中的Kalman滤波的多车辆跟踪算法[J].应用科技,2011,38(3):1-4,11. |
| 作者姓名： | 贲晛烨 王科俊 李阳 谢滨姣 |
| 作者单位： | 1. 哈尔滨工业大学,交通科学与工程学院,黑龙江,哈尔滨,150090 2. 哈尔滨工程大学,自动化学院,黑龙江,哈尔滨,150001 3. 一汽轿车股份有限公司,产品部,吉林,长春,130011 4. 哈尔滨学院,理学院,黑龙江,哈尔滨,150036 |
| 基金项目： | 国家"863"高科技基金资助项目 |
| 摘 要： | 提出了一种交通视频中的Kalman滤波的多车辆跟踪算法.该算法利用Kalman滤波器反馈控制系统估计运动状态进行预测和修正,并为运动目标建立模型;利用当前车辆的信息对下一帧目标的位置进行预测,以便缩小目标的搜索范围和搜索时间,从而快速跟踪车辆.利用车辆的外接矩形框大小、质心等特征对车辆进行特征匹配,为交通视频中的车辆建立对应关系,利用新的系统参数更新模型,获得车辆的轨迹,如此反复,从而实现对车辆的跟踪.实验结果表明,此算法运算速度很快,对于车辆这样的快速运动目标,也具有较好的跟踪效果. |
| 关 键 词： | 交通视频 Kalman滤波 多车辆跟踪 参数更新 |
Multiple vehicle tracking algorithm based on Kalman filter in traffic video |
|
| BEN Xianye,WANG Kejun,LI Yang,XIE Binjiao.Multiple vehicle tracking algorithm based on Kalman filter in traffic video[J].Applied Science and Technology,2011,38(3):1-4,11. | |
| Authors: | BEN Xianye WANG Kejun LI Yang XIE Binjiao |
| Institution: | BEN Xianye1,WANG Kejun2,LI Yang3,XIE Binjiao4(1.School of Transportation Science and Engineering,Harbin Institute of Technology,Harbin 150090,China,2.College of Automation,Harbin Engineering University,Harbin 150001,3.FAW Car Co.,Ltd,Changchun 130011,4.School of Science,Harbin University,Harbin 150036,China) |
| Abstract: | A novel method of multiple vehicles tracking algorithm based on Kalman filter in traffic video is proposed in this paper.The Kalman filter is applied to the feedback control system to predict and modify the motion state,as well as to build models for moving objects.The current information of the vehicle is used to forecast its position in the next frame so as to reduce the searching scope and searching time for this object,thus the vehicle can be tracked quickly.The features such as the size of out-connecte... |
| Keywords: | traffic video Kalman filter multiple vehicles tracking parameters updating |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |