期刊文献+

基于自适应多测量融合UPF的矿井人员跟踪算法 被引量:4

Unscented particle filter algorithm for people tracking in coal mines based on adaptive multi-cues integration models
原文传递
导出
摘要 针对复杂背景下的矿井跟踪视场由于单一线索对目标缺乏可分性、观测模型可靠度对场景变化缺乏自适应性致使观测失效、跟踪发散的问题,提出了基于自适应多测量融合UPF的矿井人员跟踪算法.采用UKF产生预测样本,通过融入最新观测的建议分布引导预测样本分布在状态空间的高似然区域,扩大了预测样本与观测似然峰值重叠区域;提出运动光流直方图,将其与颜色直方图融合建立多观测模型,根据贡献率度量因子实现对观测模型可靠度的动态调节,定义了采样补偿函数有效克服观测失效时的粒子扩散.结果表明:本算法能够有效的解决矿井跟踪视场下(背景复杂)由于观测模型失效而导致的跟踪发散问题,与3种不同观测模型PF算法做状态估计MSE比较,估计准确率提高87%. To resolve the target-tracking in coal mines,which was caused by a single-cue lacking of discrimination to target features and the reliability of observation modals lacking of self-adaptation to changes of scenes,a novel unscented particle filter(UPF) algorithm was proposed for object-tracking using an unscented kalman filter(UKF)as proposal distribution and an adaptive multi-cues fusion modal as the observation modal.To integrate the latest observation into proposal distribution,the UKF generate prediction samples were adjusted to high likelihood area in state-space,and more overlap regions of prediction samples and peak zones of observation likelihood were achieved.The optical flow histogram was presented and observation model based on multi-cues fusion was implemented by integrating optical flow with color.The adaptive strategy of observation modal weights was implemented by adjusting the contribution rate of single-cue observation modal,and the reliability of an observation modal was adjusted.A function of sample compensation was proposed to handle particle diffusion due to failure of observation modal.The results show that the tracking algorithm is effective for solving tracking failure in coal mines(complex background).The estimating accuracy was increased by 87% compared with three other particle filter algorithms.
出处 《中国矿业大学学报》 EI CAS CSCD 北大核心 2011年第1期146-151,共6页 Journal of China University of Mining & Technology
基金 国家高技术研究发展计划(863)项目(2008AA062200) 江苏省产学研联合创新基金项目(BY2009114)
关键词 UKF 粒子滤波 运动光流直方图 观测权值自适应 采样补偿 unscented kalman filter particle filter moving optical flow histogram adaptive weights of observation modal resample compensation
  • 引文网络
  • 相关文献

参考文献11

  • 1DOUCET A, DE FREITAS N, GORDON N, et al. Sequential monte carlo methods in practice[M]. New York: Springer-Verlag, 2001.
  • 2DOUCET A, GODSILL S, ANDRIEU C. On sequential monte carlo sampling methods for bayesian filtering [J]. Statistics and Computing,2000,10(3) :197-208.
  • 3PEREZ P, VERMAAK J, BLAKE A. Data fusion for visual tracking with particles [J]. Proceedings of the IEEE,2004,92(3) :495-513.
  • 4WU P L, KONG L F, ZHAO F D, et al. Particle filter tracking based on color and sift features[C]// Audio, Language and Image Processing, 2008. Shanghai: [s. n. ], 2008:932-937.
  • 5TAO X, CHRISTIAN D. Monte carlo visual tracking using color histograms and a spatially weighted o- riented hausdorff measure [ C ]/ /Proceedings of the Conference on Analysis of Images and Patterns. Groningen: Springer Berlin Heidelberg, 2003: 190- 197.
  • 6KWOLEK B. Stereovision-based head tracking using color and ellipse fitting in a particle filter[C]//Proceedings of the 8th European Conference on Computer Vision. Prague: Springer Berlin Heidelberg, 2004..192-204.
  • 7SPENGLER M, SCHIELE B. Towards robust multi-cue integration for visual tracking [J]. Machine Vision and Applications, 2003,14 (1) : 50-58.
  • 8JULIER S, UHLMANN J, DURRANT-WHYTE HF. A new approach for the nonlinear transformation of means and covariances in filters and estimators[J]. IEEE Transation Automatic Control, 2000, 45(3) : 477-482.
  • 9LOWE DG. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60 (2): 91-110.
  • 10管志强,陈钱,顾国华,钱惟贤.基于光流直方图的云背景下低帧频小目标探测方法[J].光学学报,2008,28(8):1496-1501. 被引量:16

二级参考文献12

  • 1宗思光,王江安.多尺度形态算子融合图像滤波技术及滤波质量评价[J].光学学报,2005,25(9):1176-1180. 被引量:15
  • 2曾明,李建勋.基于改进遗传算法优化的形态学修正TOP-HAT滤波器设计方法[J].光学学报,2006,26(4):510-515. 被引量:8
  • 3刘贵喜,邵明礼,刘先红,朱东波.真实场景下视频运动目标自动提取方法[J].光学学报,2006,26(8):1150-1155. 被引量:32
  • 4J. M. Missirian, L. Ducruet IRST: a key system in modern warfare[C]. Proc. SPIE, 1997, 3061:554-565.
  • 5J. Arnold, S. Shaw. Efficient target tracking using dynamic programming [J]. IEEE Trans. Aerospace and Electrical Systems, 1993, 29(1): 44-56.
  • 6I. S. Reed, R. M. Gagliardi, L. Stotts. Optical moving target detection with 3-D matched filtering[J]. IEEE Trans. Aerospace and Electrical Systems, 1988, 24(4): 327-326.
  • 7S. D. Blostein, H. S. Richardson. A sequential detection approach to target tracking [J]. IEEE Trans. Aerospace and Electrical Systems, 1994, 30(1) : 197-211.
  • 8B. S. Denney, R. J. P. de Figuebedo. Optimal point target detection using adaptive auto regressive background[C]. Proc. SPIE, 2000, 4048:46-57.
  • 9B. R. David. Spatial signal processing for infrared detection[J]. Proc. SPIE, 1994, 2235:38-51.
  • 10B. K. P. Horn, B. G. Schunck. Determining optical flow[J]. Artificial Intelligence, 1981, (17) : 185-203.

共引文献15

同被引文献56

引证文献4

二级引证文献32

;
使用帮助 返回顶部