欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对视频目标的跟踪过程中目标之间遮挡和人体自遮挡的难题,提出一种基于运动轨迹的视频目标跟踪算法。介绍跟踪算法中常用的基于特征概率密度统计的Mean-shift跟踪算法原理,阐述所提算法。与Mean-shift算法做实验对比,对比结果表明,对于无遮挡和有遮挡情况下的目标跟踪,该算法在准确率方面比Mean-shift跟踪算法更高,具有更强的实用性。
英文摘要：
Aiming at the fact that problems emerge during video target tracking process,such as,the block between the targets and the human self-occlusion.A trajectory based video target tracking algorithm was proposed.A brief introduction of the tracking algorithm principles of statistical characteristics probability density based Mean-shift tracking algorithm was given,and the proposed algorithm was elaborated specifically,and through experimental comparison with Mean-shift algorithm,the proposed algorithm was verified to be better than Mean-shift algorithm in terms of the accuracy for the targets without shelter and sheltered targets and has stronger practicality.
同期刊论文项目
同项目期刊论文
期刊信息
位置：