期刊文献+

基于m-best数据关联和小轨迹关联多目标跟踪算法 预览

Multi-target tracking based on m-best data association and tracklet association
在线阅读 下载PDF
分享 导出
摘要 视频多目标跟踪中目标较多时,联合概率数据关联算法计算量大,实时性差。由于遮挡等问题,联合概率数据关联算法得到的往往是目标的轨迹片段。针对上述问题,首先利用线性规划自适应迭代求解m个最优联合事件简化联合概率数据关联算法,然后提出基于Kalman滤波及外推法的双向运动预测计算轨迹间的距离矩阵,用近邻传播聚类对目标的轨迹片段进行关联。实验结果表明,本文提出的方法在目标多且容易发生遮挡的情况下仍能够实时有效的跟踪,提高了跟踪准确度,具有一定的抗干扰能力。 In the video multi-target tracking, the joint probability data association (JPDA) algorithm in-volves a potentially huge number terms ? which is weak for the real-time performance , when the number of the target is large. Moreover,targets are often undetected due to occlusion or other detector failures. The classic JPDA often gets the part trajectory of the objects, not the integrity trajectory. To solve these problems, a method based on m-best JPDA and tracklet association is proposed. Firstly, to reduce the computational com-plexity, the integer linear program is used to find the m-best hypotheses and simplify the JPDA algorithm. After that,the distances between each target trajectory are computed based on the motion evaluation by Kalman filter and the simply linearly extrapolation. The affinity propagation cluster algorithm is used to merge the tracklet of the ob-ject and get the fully trajectories. Experiments show that the proposed method still has the effective and real time per-formance when the number of target is large and occlusion is easy to happen.
作者 谷晓琳 周石琳 雷琳 GU Xiaolin, ZHOU Shilin, LEI Li n(College of Electronic Science and Engineering,National University of Defense Technology,Changsha 410073, China)
出处 《系统工程与电子技术》 CSCD 北大核心 2017年第7期1640-1646,共7页 Systems Engineering and Electronics
关键词 多目标跟踪 联合概率数据关联 线性规划 运动预测 近邻传播聚类 multi-target tracking joint probabilistic data association (JPDA) linear program motion evaluation affinity propagation cluster algorithm
作者简介 谷晓琳(1992-),女,硕士研究生,主要研究方向为计算机视觉与智能信息处理.E-mail:13739093781@163.com 周石琳(1965-),男,教授,博士,主要研究方向为智能信息处理与计算机视觉.E-mail:slzhoumail@163.com 雷琳(1980-),女,副教授,博士,主要研究方向为数字图像处理与信息融合.E-mail:alaleilin@163.com
  • 相关文献

参考文献3

二级参考文献21

共引文献8

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈