© The Institution of Engineering and Technology
A novel approach for recovering the human body configuration based on the silhouette is presented. By considering pose inference as traversing the difference subspaces and using a data-driven mechanism, reversible jump Markov chain Monte Carlo (RJMCMC) can explore such solution space very efficiently. Experimental results are provided to demonstrate the efficiency and effectiveness of the proposed approach.
References
-
-
1)
-
G. Shakhnarowich ,
P. Viola ,
T. Darrell
.
Fast pose estimation with parameter-sensitive hashing.
Int. Conf. on Computer Vision
,
750 -
757
-
2)
-
S. Ioffe ,
D.A. Forsyth
.
Probabilistic methods for finding people.
Int. J. Comput. Vis.
,
1 ,
45 -
68
-
3)
-
P.J. Green
.
Reversible jump Markov chain Monte Carlo computation and Bayesian Model Determination.
Biometrika
,
4 ,
711 -
732
-
4)
-
D. Reisfeld ,
H. Wolfson ,
Y. Yeshurun
.
Context free attentional operations: the generalized symmetry transform.
Int. J. Comput. Vis.
,
2 ,
119 -
130
-
5)
-
P.F. Felzenszwalb
.
Pictorial structures for object recognition.
Int. J. Comput. Vis.
,
1 ,
55 -
79
http://iet.metastore.ingenta.com/content/journals/10.1049/el_20060044
Related content
content/journals/10.1049/el_20060044
pub_keyword,iet_inspecKeyword,pub_concept
6
6