Sciweavers

ICPR
2008
IEEE
14 years 5 months ago
A bottom-up, view-point invariant human detector
We propose a bottom-up human detector that can deal with arbitrary poses and viewpoints. Heads, limbs and torsos are individually detected, and an efficient assembly strategy is u...
Nicolas Thome, Sebastien Ambellouis
ICPR
2004
IEEE
15 years 7 days ago
Reflectance Estimation from Motion under Complex Illumination
In this paper, we propose a method for recovering the reflectance properties of a moving Lambertian object from an image sequence of the object taken by a fixed camera under unkno...
Akihiro Sugimoto, Fei Du, Takahiro Okabe, Yoichi S...