期刊文献+

改进背景差分法的运动轨迹实时跟踪方法 被引量:1

Real Time Trajectory Tracking Method Based on Improved Background Difference Method
下载PDF
导出
摘要 运动轨迹跟踪是运动视频处理中的研究热点,传统运动轨迹跟踪方法误差大,实时性差,无法满足运动轨迹跟踪的实际应用要求,为了提高运动轨迹的跟踪精度,提出了改进背景差分法的运动轨迹实时跟踪方法。首先对当前运动轨迹跟踪的现状进行分析,找到各种运动轨迹跟踪方法的局限性,然后采集运动轨迹视频,对运动视频进行预处理,利用背景差分法对运动视频图像的目标进行检测,最后引入卡尔曼滤波算法对运动轨迹进行跟踪,并与其它运动轨迹跟踪方法进行了对比测试。测试结果表明,改进背景差分法的运动轨迹跟踪精度高,运动轨迹跟踪的实时性强,运动轨迹跟踪的整体效果要明显优于其它运动轨迹跟踪方法,可以应用于具体的运动轨迹管理中,具有较高的实际应用价值。 The research focus of motion video processing is motion tracking.The error of traditional motion tracking method is large,and the tracking real-time performance is poor,hence,it cannot meet the practical application requirements of motion trajectory tracking.In order to improve the tracking accuracy of motion trajectory,a real-time tracking method based on improved background difference method is proposed.Firstly,the current status of motion tracking is analyzed,and the limitations of various tracking methods are found.Then,the video of motion track is collected and preprocessed.The background difference method is used to detect the target in the video image.Finally,the Kalman filter method is introduced to track the motion track,and is compared with other tracking methods.The results show that the improved background difference method has high tracking accuracy,real-time performance,and the overall effect of motion track tracking is obviously better than other methods.It can be applied in specific motion track management and has high practical application value.
作者 马蕾 张忠秋 张娜娜 MA Lei;ZHANG Zhongqiu;ZHANG Nana(Information Engineering College,Xi’an Mingde Institute of Technology,Xi’an 710124,China)
出处 《微型电脑应用》 2021年第9期27-29,共3页 Microcomputer Applications
基金 陕西省教育厅专项科研计划项目(21JK0815)。
关键词 视频图像 跟踪效率 仿真测试 卡尔曼滤波算法 运动轨迹 背景差分法 video image tracking efficiency simulation test Kalman filter algorithm motion trajectory background difference method
  • 相关文献

参考文献13

二级参考文献83

  • 1杨丽娟,张白桦,叶旭桢.快速傅里叶变换FFT及其应用[J].光电工程,2004,31(B12):1-3. 被引量:99
  • 2刘锡民,刘立人,孙建锋,郎海涛,潘卫清,赵栋.星间激光通讯中的精跟踪研究[J].物理学报,2005,54(11):5149-5156. 被引量:7
  • 3黄文杰,陈斌.一种快速图像处理的积分图方法[J].计算机应用,2005,25(B12):266-268. 被引量:13
  • 4齐苏敏,黄贤武,伊怀峰.基于各向异性核函数的均值漂移跟踪算法[J].电子与信息学报,2007,29(3):686-689. 被引量:6
  • 5Black M J,Jepson A D.Eigen Tracking:Robust matching and tracking of articulated objects using a view-based representation[J].International Journal of Computer Vision,1998,26(1):63-84. 被引量:1
  • 6Ross D A,Lim J,Lin R S,et al.Incremental learning for robust visual tracking[J].International Journal of Computer Vision,2015,77(1-3):125-141. 被引量:1
  • 7Mehmood K,Mrak M,Calic J,et al.Object tracking in surveillance videos using compressed domain features from scalable bitstreams[J].Signal Processing Image Communication,2009,24(10):814-824. 被引量:1
  • 8Allili M S,Ziou D.Object tracking in videos using adaptive mixture models and active contours[J].Neurocomputing,2008,71(10-12):2001-2011. 被引量:1
  • 9Nummiaro K,Koller-Meier E,Gool L V.Object tracking with an adaptive color-based particle filter[J].Lecture Notes in Computer Science,2002,2449(2):353-360. 被引量:1
  • 10Kamijo S,Nishida T,Satoh S,et al.Automated behavior and statistical analysis from traffic images based on precise vehicle tracking algorithm[C]∥Proceedings of IEEE 2002 the 5th International Conference on Intelligent Transportation Systems,IEEE,2002:920-925. 被引量:1

共引文献64

同被引文献9

引证文献1

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