期刊文献+

一种基于M-APF的实时UAV目标跟踪算法 被引量:5

Real Time UAV Target Tracking Method Based on M-APF
原文传递
导出
摘要 针对中小型UAV(Unmanned Aerial Vehicle)平台运动目标跟踪系统由于受机载摄像条件及数据传输时延等因素,造成跟踪结果实时性不高、目标被遮挡时易丢失的问题,提出一种基于M-APF(Meanshift-Auxiliary Particle Filter)的UAV运动目标跟踪算法。该方法采用APF作为跟踪算法的主体框架,同时引入Meanshift计算少量辅助采样粒子的偏移,并将其移动到观测值的局部最优位置,解决了APF算法计算量大的问题,提高算法实时性。仿真结果显示:算法满足UAV平台运动目标跟踪要求,实时性及鲁棒性优于Meanshift和APF等算法。 Focusing on the problems of the target information estimated delay and the target lost for the occlusion reasons in the UAV moving target tracking system, a novel target tracking method based on M-APF (Meanshift-Auxiliary Particle Filter) was proposed. It adopted the APF as the main framework of the tracking algorithm, then the Meanshift was applied to calculate the offset of a few auxiliary particle and moved them to the local optimum position of the observed values. As a result, it solved the large calculation of the APF algorithm, and improved the real-time of the method. Simulation results show that the calculation cost and robustness of the M-APF is superior to Meanshift and APF algorithm, and satisfies the UAV target tracking requirements.
出处 《系统仿真学报》 CAS CSCD 北大核心 2014年第1期107-111,118,共6页 Journal of System Simulation
基金 国家自然科学基金(61074155)
关键词 无人机 目标跟踪 均值漂移 辅助粒子滤波 遮挡 UAV target tracking meanshifl auxiliary particle filter occlusion
  • 相关文献

参考文献8

  • 1王相海,方玲玲,丛志环.卡尔曼粒子滤波的视频车辆跟踪算法研究[J].中国图象图形学报,2010,15(11):1615-1622. 被引量:19
  • 2Isard M, Blake A. Condensation-conditional Density Propagation for Visual Tracking [J]. International Journal of Computer Vision: (S0920-5691), 1998, 29(1): 5-28.
  • 3Tada K, Takemura H, Mizoguchi H. Robust tracking method by Meanshift using Spatiograms [C]// SICE Annual Conference. Taipei, China: Institute of Electrical and Electronics Engineers (IEEE), 2010, 18-21 Aug: 1985-1988.
  • 4Sundaramoorthi G, Yezzi A, Mennucci A. Coarse-to-Fine Segmentation and Tracking Using Sobolev Active Contours [J].IEEE Transactions on Pattern Analysis and Machine Intelligence: (S0162-8828), 2008, 30(5): 851-864.
  • 5佘九华,王敬东,李鹏.基于Camshift的人脸跟踪算法[J].计算机技术与发展,2008,18(9):12-15. 被引量:14
  • 6陈兆学,赵晓静,聂生东.Mean shift方法在图像处理中的研究与应用[J].中国医学物理学杂志,2010,27(6):2244-2249. 被引量:9
  • 7Sullivan J, Rittscher J R. Guiding Random Particles by Deterministic Search [C]//Proc. of ICCV'01. USA: IEEE Press, 2001: 323-330.
  • 8Deguchi K, Kawanaka O, Okatani T. Object Tracking by the Mean-shift of Regional Color Distribution Combined with the Particle-filter Algorithms (C]// Proc. of the 17th International Conference on Pattern Recognition. Cambridge, UK: IEEE Computer Society, 2004: 506-509.

二级参考文献42

共引文献37

同被引文献34

引证文献5

二级引证文献13

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