一种基于多特征聚类的粒子滤波跟踪算法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3725 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
包加桐, 郭晏, 唐鸿儒, 宋爱国. 一种基于多特征聚类的粒子滤波跟踪算法[J]. 机器人, 2011, 33(5): 634-640.. BAO Jiatong, GUO Yan, TANG Hongru, SONG Aiguo. A Particle Filter Tracking Algorithm Based on Multi-Feature Clustering. ROBOT, 2011, 33(5): 634-640..

摘要提出了一种基于多特征聚类的粒子滤波目标跟踪算法．针对目标描述特征的多样性、特征分布描述方法的差异性及特征空间结构的任意性，提出将目标模型多特征表示统一在聚类计算框架下．算法利用基于均值移动的特征空间分析方法来自适应地计算任意结构特征空间中的聚类，在聚类的基础上提出了一种高效准确的目标概率密度估计方法来表示目标模型．利用核密度估计相似度量方法计算参考目标与候选目标的距离，作为粒子滤波系统观测的重要信息．提出了改进的粒子传播模型，有效提高粒子利用率．在大量真实序列图像上，使用LUV颜色特征与LBP纹理特征进行了目标跟踪实验．实验结果表明，提出的算法能获得较高的跟踪精度、鲁棒性强且满足实时性要求，与一些其它典型的算法相比，整体跟踪性能更好．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	包加桐
	郭晏
	唐鸿儒
	宋爱国

关键词 ：目标跟踪, 聚类分析, 概率密度估计, 粒子滤波

Abstract：A particle filter tracking algorithm based on multi-feature clustering is proposed.To address the issues such as the diversity of target features,the difference between methods of feature distribution description,and the arbitrariness of feature spatial structure,the multi-features representation of target model is unified into a clustering computing framework. The mean shift based feature space analysis approach is employed to adaptively calculate the clusters in any arbitrarily structured feature space.Based on the clusters,a target probability density estimation method,which is efficient and accurate, is proposed to represent the target model.The distance between the reference target and the candidate is calculated by the similarity measure of kernel density estimation,and is taken as important information for observation in particle filter system. To efficiently enhance the utilization rate of particles,an improved particle propagation model is presented.The object tracking experiments are performed on many real image sequences by using the LUV color features and the LBP(local binary pattern) texture features.Experiment results show that the proposed algorithm can obtain high tracking accuracy and strong robustness,meet real-time demand,and provide better tracking performance comparing with other typical algorithms.

Key words： object tracking clustering analysis probability density estimation particle filter

收稿日期: 2010-12-09 录用日期: 2011-04-07

TP391

基金资助:国家863计划资助项目（2006AA04Z246）；国家自然科学基金资助项目（61075068）；教育部重大创新工程培育资金项目（708045）；江苏省自然科学基金重点项目（BK2009183）；江苏省自然科学基金重点项目（BK2010063）

通讯作者: 宋爱国 E-mail: a.g.song@seu.edu.cn

作者简介: 包加桐（1983- ），男，博士生．研究领域：移动机器人，机器人视觉．
郭晏（1984- ），男，博士生．研究领域：移动机器人，机器人视觉．
宋爱国（1968- ），男，博士，教授，博士生导师．研究领域：机器人传感与控制，人机交互技术．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2011/V33/I5/634

[1] Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.

[2] Bradski G R.Real time face and object tracking as a component of a perceptual user interface[C]//4th IEEE Workshop on Applications of Computer Vision.Piscataway,NJ,USA:IEEE,1998:214-219.
[3] Li P H.A clustering-based color model and integral images for fast object tracking[J].Signal Processing:Image Communication,2006,21(8):676-687.

[4] Gotlieb C C,Kreyszig H E.Texture descriptors based on cooccurrence matrices[J].Computer Vision,Graphics,and Image Processing,1990,51(1):70-86.

[5] Van de Wouwer G,Scheunders P,Van Dyck D.Statistical texture characterization from discrete wavelet representations[J].IEEE Transactions on Image Processing,1999,8(4):592-598.

[6] Leung T,Malik J.Representing and recognizing the visual appearance of materials using three-dimensional textons[J],International Journal of Computer Vision,2001,43(1):29-44.

[7] Ojala T,Pietikainen M,Maenpa T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.

[8] Ning J F,Zhang L.,Zhang D,et al.Robust object tracking using joint color-texture histogram[J].International Journal of Pattern Recognition and Artificial Intelligence,2009,23(7):1245-1263.

[9] Birchfield S.Elliptical head tracking using intensity gradients and color histograms[C]//Conference on Computer Vision and Pattern Recognition.Piscataway,NJ,USA:IEEE,1998:232-237.
[10] Seemann E,Leibe B,Mikolajczyk K,et al.An evaluation of local shape-based features for pedestrian detection[C]//British Machine Vision Conference.2005.
[11] Wang J Q,Yagi Y.Integrating color and shape-texture features for adaptive real-time object tracking[J].IEEE Transactions on Image Processing,2008,17(2):235-240.

[12] Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine intelligence,2002,24(5):603-614.

[13] Christoudias C M,Georgescu B,Meer P.Synergism in low level vision[C]//16th International Conference on Pattem Recognition.Piscataway,NJ,USA:IEEE,2002:150-155.
[14] Yang C J,Duraiswami R,Davis L.Efficient mean-shift tracking via a new similarity measure[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ,USA:IEEE,2005:176-183.
[15] Arulampalam M S,Maskell S,Gordon N,et al.A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking[J].IEEE Transactions on Signal Processing,2002,50(2):174-188.

[16] Stan Birchfield.Test image sequences for face tracking[EB/OL].[2010-12-27].http://www.ces.clemson.edu/～stb/research/headtracker/.
[17] Adam A,Rivlin E,Shimshoni I.Robust fragments-based tracking using the integral histogram[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ,USA:IEEE,2006:798-805.