李力行,黄永梅,王强,贺东.点目标视频跟踪中的噪声自适应卡尔曼滤波器[J].电子测量技术,2017,40(6):170-174
点目标视频跟踪中的噪声自适应卡尔曼滤波器
Noise adaptive Kalman filter for video point target tracking
  
DOI:
中文关键词:  卡尔曼滤波  噪声自适应  点目标
英文关键词:Kalman filtering  noise adaptive  point target
基金项目:
作者单位
李力行 1.中国科学院光电技术研究所成都610209; 2.中国科学院光束控制重点实验室成都610209;3.中国科学院大学 北京 100039 
黄永梅 1.中国科学院光电技术研究所成都610209; 2.中国科学院光束控制重点实验室成都610209 
王强 1.中国科学院光电技术研究所成都610209; 2.中国科学院光束控制重点实验室成都610209 
贺东 1.中国科学院光电技术研究所成都610209; 2.中国科学院光束控制重点实验室成都610209 
AuthorInstitution
Li Lixing 1. Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China; 2. Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu 610209, China; 3. University of Chinese Academy of Sciences, Beijing 100039, China 
Huang Yongmei 1. Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China; 2. Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu 610209, China 
Wang Qiang 1. Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China; 2. Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu 610209, China 
He Dong 1. Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China; 2. Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu 610209, China 
摘要点击次数: 1151
全文下载次数: 987
中文摘要:
      针对卡尔曼滤波器在实用过程中所遇到的运动模型选择以及噪声给定问题,基于视频点目标的特征,提出了一种点目标视频跟踪中的噪声自适应卡尔曼滤波算法。该算法结合双步动态模型,在滤波过程中根据速度的相关系数调整运动模型参数,使运动模型更加切合实际。此外,该算法结合运动模型以及观测数据对一段时间的过程噪声进行估计,同时基于成像特性,利用单帧图像中灰度值的分布,对单次观测的观测噪声进行实时估计,实现过程噪声和观测噪声的自适应。根据在外场进行的仿真实验和实际跟踪实验结果,文中所提出的方法能够有效地保证跟踪精度。
英文摘要:
      To overcome the difficulty of choosing the dynamic model and giving the strength of noise that applying the Kalman filter will face, this paper presents an algorithm of noise adaptive Kalman filtering for video point target tracking, based on the characteristic of video point targets. To better fit the dynamics of a video point target, the two stage dynamic model, which can changes its form with regard to the value of correlation time constant, has been chosen as the state transition model for Kalman filtering. Moreover, the process noise is estimated according to the dynamic model and the observation data. Meanwhile, the observation noise is estimated according to the grey value distribution in each image. Then the process noise and the observation noise are adaptive. According to the outfield experimental result, the methods we proposed could effectively ensure the tracking accuracy.
查看全文  查看/发表评论  下载PDF阅读器