应用自适应多测量融合粒子滤波的视场跟踪

田隽; 钱建生; 李世银; 厉丹

doi:10.3788/OPE.20101810.2254

您当前的位置：

首页 >

文章列表页 >

应用自适应多测量融合粒子滤波的视场跟踪

信息科学 | 更新时间：2020-08-12

- 应用自适应多测量融合粒子滤波的视场跟踪
- Visual tracking with adaptive multi-cue fusion particle filter
- 光学精密工程 2010年18卷第10期页码：2254-2261
- 作者机构：
  
  1. 中国矿业大学信息与电气工程学院,江苏徐州 221008
  2. 徐州工程学院信电工程学院,江苏徐州221008
- 作者简介：
- 基金信息：
  
  国家863高技术研究发计划(重点)资助项目(No.2008AA062200)();江苏省产学研联合创新基金资助项目(No.BY2009114)()
- DOI：10.3788/OPE.20101810.2254
  中图分类号： TP391
- 收稿日期：2009-12-15，
  
  修回日期：2010-03-10，
  
  网络出版日期：2010-10-28，
  
  纸质出版日期：2010-10-20
- 稿件说明：
移动端阅览
田隽, 钱建生, 李世银, 厉丹. 应用自适应多测量融合粒子滤波的视场跟踪[J]. 光学精密工程, 2010,18(10): 2254-2261

TIAN Jun, QIAN Jian-sheng, LI Shi-yin, LI Dan. Visual tracking with adaptive multi-cue fusion particle filter[J]. Editorial Office of Optics and Precision Engineering , 2010,18(10): 2254-2261
田隽, 钱建生, 李世银, 厉丹. 应用自适应多测量融合粒子滤波的视场跟踪[J]. 光学精密工程, 2010,18(10): 2254-2261 DOI： 10.3788/OPE.20101810.2254.

TIAN Jun, QIAN Jian-sheng, LI Shi-yin, LI Dan. Visual tracking with adaptive multi-cue fusion particle filter[J]. Editorial Office of Optics and Precision Engineering , 2010,18(10): 2254-2261 DOI： 10.3788/OPE.20101810.2254.

摘要

针对矿井跟踪视场中由于单一线索对目标特征描述缺乏可分性以及多线索融合策略对场景变化缺乏自适应性导致人员跟踪失效的问题

提出了基于自适应多测量融合粒子滤波的矿井人员跟踪算法。将粒子邻域光流统计信息表征的运动性作为线索建立运动光流直方图模型

并与颜色相融合建立多观测模型。将单观测估计状态粒子区域与融合估计粒子区域的质心距离作为单观测模型贡献率度量因子

定义了观测权值自适应策略

实现了粒子观测模型与跟踪目标状态特征的同步变化;通过建议重采样函数对粒子落入低观测似然时进行有效的采样补偿

增强了跟踪的鲁棒性。实验结果表明

本算法能够有效地解决矿井跟踪视场下(背景复杂)由于场景变换而导致跟踪目标丢失的问题;将本文算法与基于颜色和基于颜色与帧差分融合的粒子滤波算法做状态估计均方误差比较

结果表明

状态估计准确率提高了1.57倍。

Abstract

As the target-tracking in coal mines using a single-cue lacks discrimination of target features and strategies using the multi-cue fusion lack the adaptation to changes of scene

a novel particle filter algorithm based on adaptive multi-cue fusion models was proposed for object-tracking.An optical flow histogram was established based on particle motion

then

the optical flow was fused with color information to obtain a multi-cue based observation model. An adaptive strategy of observation model weights was implemented by taking the centroid distance between the single-cue observation model and multi-cue fusion model as the contribution factor of the single-cue observation model. When it was implemented

the particle observation model would change with the object characteristics.The particle re-sampling was achieved by a proposal re-sampling when weights of single-cue observation model were all below a threshold. The results show that the tracking algorithm is an effective solution to tracking failure due to changes of scene in coal mines.The accuracy of estimation has increased by 1.57 times as compared with those of other particle filter algorithms.

关键词

Keywords

references

SHALOM Y B, RONG L X. Estimation and Tracking: Principles , Techniques ,and Software [M]. Boston : Artech House , 1992.[2] DOUCET A, de FREITAS. Sequential Monte Carlo Methods in Practice[M].New York:Springer-Verlag,2001.[3] ARNAUD D,SIMON G. On sequential Monte Carlo sampling methods for Bayesian filtering[J]. Statistics and Computing,2000,10(3):197-208.[4] ISARD M,BLAKE A. Condensation-Conditional density propagation for visual tracking[J]. International Journal of Computer Vision,1998,29(1):5-28.[5] PATRICK P, VERMAAK J. Data fusion for visual tracking with particles [J]. IEEE,2004,92(3):495-513.[6] WU P L,KONG L F. Particle filter tracking based on color and SIFT features .Audio, Language and Image Processing, Shanghai,2008:932-937.[7] BRADSKI GARY R.Computer vision face tracking as a component of a perceptual user interface .Proceedings of IEEE Workshop Applications of Computer Vision, Princeton, 1998:214-219. [8] TAO X,CHRISTIAN D. Monte carlo visual tracking using color histograms and a spatially weighted oriented hausdorff measure .Proceedings of the Conference on Analysis of Images and Patterns. Groningen, 2003:190-197.[9] KWOLEK B. Stereovision-based head tracking using color and ellipse fitting in a particle filter .In Proceedings of the 8th European Conference on Computer Vision, Prague, 2004:192-204.[10] SPENGLER M, SCHIELE B. Towards robust multi-cue integration for visual tracking [J].Machine Vision and Applications,2003,14(1):5058.[11] 刘贵喜,马涛. 应用最小偏度采样的UPF算法[J]. 光学精密工程,2008,16(4):746-751. LIU G X,MA T. Unscented particle filtering algorithm using minimal skew sampling[J]. Opt. Precision Eng., 2008,16(4):746-751. (in Chinese)[12] LOWE D G. Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision, 2004,60(2):91-110.[13] 管志强,陈钱. 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,2009,28(8):1496-1501. GUAN ZH Q,CHEN Q. Dim target detection based on optical flow histogram in low frame frequence in clouds background [J]. Acta Optica Sinica, 2009,28(8):1496-1501. (in Chinese)[14] LUCAS B D, KANADE T. An Iterative image registration technique with an application to stereo vision .Proc 7th International Joint Conf on Artificial Intelligence,Vancouver,1981:674-679.

浏览量

240

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于场景辅助特征的T-S目标跟踪

基于稀疏正则约束的子空间视觉跟踪

基于显著性直方图的粒子滤波跟踪

基于仿射变换与均匀采样建模的目标跟踪

用于声矢量阵列目标波达方向跟踪的粒子滤波算法