[1] Gao Jianpo, Yang Hao, An Guocheng, Wu Zhenyang, et al. Face tracking algorithm based on particle filterwith mean shift importance sampling [J]. Journal of Southeast University (English Edition), 2007, 23 (2): 196-201. [doi:10.3969/j.issn.1003-7985.2007.02.009]
Copy
Face tracking algorithm based on particle filterwith mean shift importance sampling(
)
基于均值移动重要性采样的粒子滤波人脸跟踪算法
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 23
- Issue:
- 2007 2
- Page:
- 196-201
- Research Field:
- Computer Science and Engineering
- Publishing date:
- 2007-06-30
Info
- Title:
- Face tracking algorithm based on particle filterwith mean shift importance sampling
- 基于均值移动重要性采样的粒子滤波人脸跟踪算法
- Author(s):
- Gao Jianpo; Yang Hao; An Guocheng; Wu Zhenyang
- School of Information Science and Engineering, Southeast University, Nanjing 210096, China
- Keywords:
- face tracking; particle filter; importance sampling; condensation; mean shift
- 人脸跟踪; 粒子滤波; 重要性采样; condensation; 均值移动
- PACS:
- TP391
- DOI:
- 10.3969/j.issn.1003-7985.2007.02.009
- Abstract:
- The condensation tracking algorithm uses a prior transition probability as the proposal distribution, which does not make full use of the current observation.In order to overcome this shortcoming, a new face tracking algorithm based on particle filter with mean shift importance sampling is proposed.First, the coarse location of the face target is attained by the efficient mean shift tracker, and then the result is used to construct the proposal distribution for particle propagation.Because the particles obtained with this method can cluster around the true state region, particle efficiency is improved greatly.The experimental results show that the performance of the proposed algorithm is better than that of the standard condensation tracking algorithm.
- 针对condensation目标跟踪算法中用先验转移概率作建议分布函数时没有充分考虑最新观测信息的缺点, 提出了一种基于均值移动重要性采样的粒子滤波人脸跟踪算法.算法首先利用均值移动跟踪器粗略定位人脸目标, 然后再用此跟踪结果去构造建议分布函数进行粒子传播.由于通过该方法所构造的建议分布函数中包含了最新的观测信息, 所以它可以使大多数粒子点都能分布在真实状态区域周围, 进而提高了粒子传播的准确性.人脸跟踪结果表明, 该算法的跟踪性能明显优于标准condensation方法.
References:
[1] Maskell S, Gordon S, Clapp N.A tutorial on particle filters for on-line nonlinear/non-Gaussian Bayesian tracking [J].IEEE Transactions on Signal Processing, 2002, 50(2):174-188.
[2] Merwe R, Doucet A, Freitas N, et al.The unscented particle filter, CUED/FINFENG/TR 380 [R].Cambridge:Cambridge University, 2000.
[3] Doucet A, Godsill S, Andrieu C.On sequential Monte Carlo sampling methods for Bayesian filtering [J].Statistics and Computing, 2000, 10(3):197-208.
[4] Haykin S, Huber K, Chen Z.Bayesian sequential state estimation for MIMO wireless communication [J].Proceedings of the IEEE, 2004, 92(3):439-454.
[5] Kotecha J H, Djuric P M.Gaussian particle filtering [J].IEEE Transactions on Signal Processing, 2003, 51(10):2592-2601.
[6] Kotecha J H, Djuric P M.Gaussian sum particle filtering [J].IEEE Transactions on Signal Processing, 2003, 51(10):2602-2612.
[7] Isard M, Blake A.Condensation-conditional density propagation for visual tracking [J].International Journal of Computer Vision, 1998, 29(1):5-28.
[8] Comaniciu D, Ramesh V, Meer P.Kernel-based object tracking [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5):564-577.
[9] 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):603-619.
[10] Isard M, Blake A.ICONDENSATION:unifying low-level and high-level tracking in a stochastic framework [C]//Proceeding of the 5th European Conference on Computer Vision. Freiburg, Germany, 1998, 1:893-908.
Memo
- Memo:
- Biographies: Gao Jianpo(1975—), male, graduate;Wu Zhenyang(corresponding author), male, professor, zywu@seu.edu.cn.