© The Institution of Engineering and Technology
The authors introduce the concept of a spline resampling in the particle filter to deal with high accuracy and sample impoverishment. The resampling is usually based on a linear transformation on the weights of the particles, so it affects the filtering accuracy. The spline resampling consists of two parts: the spline transformation of weights and the spread transformation of states. The former is based on a spline transformation on the weights of the particles to obtain highly accurate particle filtering, and the latter is based on a point spread transformation on states of particles to prevent sample impoverishment due to a decline in the diversity of hypothesis after resampling. Two transformations are sequentially implemented to incorporate with each other. Then, the authors propose a global transition model in the particle filter, which takes account of the background variation caused by the camera motion, to decrease error from real object position. The authors test the performance of their spline resampling and the global transition model in the particle filter in an object-tracking scenario. Experimental results demonstrate that the particle filter with the spline resampling and the global transition model has promising discriminative capability in comparison with others.
References
-
-
1)
-
6. Kotecha, J.H., Djuric, P.M.: ‘Gaussian particle filtering’, IEEE Trans. J. Signal Process., 2003, 51, (10), pp. 259–260.
-
2)
-
12. Fu, X.Y., Jia, Y.M.: ‘An improvement on resampling algorithm of particle filters’, IEEE Trans. Signal Process., 2010, 58, (10), pp. 5414–5420 (doi: 10.1109/TSP.2010.2053031).
-
3)
-
15. Hearn, D., Baker, M.P.: ‘Computer graphics’ (Prentice Hall, New Jersey, 1997).
-
4)
-
W.R. Gilks ,
C. Berzuini
.
Following a moving target – Monte Carlo inference for dynamic Bayesian models.
J. R. Stat. Soc.
,
127 -
146
-
5)
-
M. Isard ,
A. Blake
.
Condensation-conditional density propagation for visual tracking.
Int. J. Comput. Vis.
,
1 ,
5 -
28
-
6)
-
11. Musso, C., Oudjane, N., LeGland, F.: ‘Improving regularized particle filters’, In Doucet, A., de Freitas, J.F.G., Gordon, N.J. (Eds.): ‘Sequential Monte Carlo methods in practice’ (Springer-Verlag, New York, 2001).
-
7)
-
J. Liang ,
X.Y. Peng
.
Improved particle filter for nonlinear system state.
Electron. Lett.
,
24 ,
1275 -
1277
-
8)
-
4. Gordon, N., Salmond, D.: ‘Novel approach to non-linear and non-Gaussian Bayesian state estimation’, J. Proc. Inst. Electr. Eng., 1993, 140, (2), pp. 107–113.
-
9)
-
1. Douc, R., Cappe, O.: ‘Comparison of resampling schemes for particle filtering’. Proc. Fourth Int. Symp. in Image and Signal Processing and Analysis, 2005, pp. 64–69.
-
10)
-
6. Yao, A., Lin, X., Wang, G., Yu, S.: ‘A compact association of particle filtering and Kernel based object tracking’, Pattern Recognit., 2012, 45, (7), pp. 2584–2597 (doi: 10.1016/j.patcog.2012.01.016).
-
11)
-
9. Wu, G., Tang, Z.: ‘A new resampling strategy about particle filter algorithm applied in Monte Carlo framework’. Proc. Second Int. Conf. Intelligent Computation Technology and Automation, Hunan, 2009, pp. 507–510.
-
12)
-
M.K. Pitt ,
N. Shephard
.
Filtering via simulation: auxiliary particle filters.
J. Am. Stat. Assoc.
,
2 ,
590 -
599
-
13)
-
3. Liang, J., Peng, X.Y.: ‘Development and prospect of particle filter’, Recent Pat. Electr. Eng., 2010, 3, (1), pp. 43–44 (doi: 10.2174/1874476111003010043).
-
14)
-
M.S. Arulampalam ,
S. Maskell ,
N. Gordon ,
T. Clapp
.
A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking.
IEEE Trans. Signal Process.
,
2 ,
174 -
188
-
15)
-
D. Comaniciu ,
V. Ramesh ,
P. Meer
.
Kernel-based object tracking.
IEEE Trans. Pattern Anal. Mach. Intell.
,
564 -
577
-
16)
-
J. Liang ,
X.-Y. Peng ,
Y.-T. Ma
.
Particle estimation algorithm using correlation of observation for nonlinear system state.
Electron. Lett.
,
8 ,
553 -
554
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0106
Related content
content/journals/10.1049/iet-cvi.2014.0106
pub_keyword,iet_inspecKeyword,pub_concept
6
6