Sciweavers

ICIP
2009
IEEE
13 years 5 months ago
View-invariant action recognition using cross ratios across frames
We present a new method of computing invariants in videos captured from different views to achieve view-invariant action recognition. To avoid the constraints of collinearity or c...
Yeyin Zhang, Kaiqi Huang, Yongzhen Huang, Tieniu T...
ICASSP
2009
IEEE
14 years 2 months ago
Estimating correspondence between multiple cameras using joint invariants
The joint invariants of the projective group PSL(3, R) on RP2 , the five-point volume cross-ratios, are studied to address the problem of correspondence in a camera network. The ...
Raman Arora, Yu Hen Hu, Charles Dyer