全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于多观测模型的粒子滤波头部跟踪算法

DOI: 10.11834/jig.20090119

Keywords: 粒子滤波,头部跟踪,观测模型

Full-Text   Cite this paper   Add to My Lib

Abstract:

粒子滤波在非线性和非高斯问题上具有独特的优越性,但在视频跟踪过程中,其跟踪性能却在很大程度上依赖于观测模型的选择。为了解决被跟踪目标特征状态随时间变化而与粒子观测模型不匹配的问题,提出了一种新的粒子滤波算法,即将被跟踪目标的不同特征状态与粒子观测模型相结合,形成一组具有不同观测模型的粒子,并且在跟踪过程中,对应不同观测模型的粒子根据被跟踪目标所表现的特征线索的变化而相互转换,从而动态刻画了被跟踪目标特征变化的过程。实验结果表明,本算法能够有效处理由于头部旋转而导致跟踪性能下降甚至丢失跟踪目标的问题,提高了跟踪的准确性,并且具有较好的鲁棒性。

References

[1]  Isard M, Blake A. Condensation-conditional density propagation for visual tracking [J]. International Journal Of Computer Vision, 1998, 29(1) :5-28.
[2]  Li Yuan, Ai Hai-zhou, Chang Huang,et al. Robust head tracking based on a multi-state particle filter[ A]. In: Proceedings of IEEE Automatic Face and Gesture Recognition 2006 [C] , Southampton, UK, 2006:335-340.
[3]  Cheng Chang, Rashid Ansari. Real-time tracking with multiple cues by set theoretic random search [ A ]. In: Proceedings of IEEE CVPR\\'05 [C], San Diego, Calif, USA,2005, 1(20):932-938.
[4]  Apnaud Doucet, Simon Godsill, Christophe Andrieu. On sequential Monte Carlo sampling methods for Bayesian filtering [J]. Statistics and Computing ,2000,10(3) :197-208.
[5]  邓小龙 谢剑英 郭为忠.用于状态估计的自适应粒子滤波[J].华南理工大学学报,2006,34(1):57-61.
[6]  Arulampalam M S, Maskell S, Gordon N,et al. A tutorial on particle filters for on-line nonlinear/non-Gaussian Bayesian tracking [J]. IEEE Transactions on Signal Processing, 2002,50(2) :174-188.
[7]  Nummiaro K, Esther Koller-Meier, Luc Van Gool. An adaptive colorbased particle filter[J]. Image and Vision Computing, 2003, 21(1) : 99-110.
[8]  Li Yan-qiu, Yi Shen, Liu Zhi-yan. Tracking a Maneuvering Target in Clutter by a New Smoothing Particle Filter[A].In: Proceedings of IEEE Instrumentation and Measurement Technology 2005[C], Ontario, Canada, 2005, 2 (16) :843-848
[9]  McGinnity G, Irwin G W. Multiple model bootstrap filter for maneurvering target tracking [J] . IEEE Transactions on Aerospaceand Electronic Systems, 2000,36( 3 ) :1006-1012.
[10]  Xu Xin-yu, Li Bao-xin. Head tracking intensity gradient and color histogram [ A ]. International Conference on Multimedia Amsterdam, The Netherlands, 2005,6 ( 8 ) using panicle filter with In: P~ceedings of IEEE and Expo 2005 [C], 855-891.
[11]  Mark, Subhash. Manoeuvring Target tracking in clutter using particle filters[J]. IEEE Transactions on Aerospace and Electronic Systems, 2005,41 ( 1 ) :252-270.
[12]  Xu Xin-yu, Li Bao-xin. Rao-Blackwellised particle fiher for tracking with application in visual surveillance[ A ]. In: Proceedings of IEEE 2nd Joint IEEE International Workshop on VS-PETS [C] , Beijing, China, 2005 : 17-24.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133