Inferring 3D body pose from silhouettes using activity manifold learning
Inferring 3D body pose from silhouettes using activity manifold learning
复制标题
DOI：
10.1109/cvpr.2004.132
复制
发表时间：
2004-06
期刊：
影响因子：
--
通讯作者：
A. Elgammal;Chan-Su Lee
中科院分区：
文献类型：
--
作者：
A. Elgammal;Chan-Su Lee
我们的目标是直接从人体轮廓推断出3D身体姿势。给定视觉输入（轮廓），目标是恢复内在的身体结构，恢复视点，重建输入并检测任何空间或时间异常值。为了从视觉输入（轮廓）中恢复内在的身体结构（姿势），我们明确地学习了活动流形的基于视图的表示，以及这种中心表示与视觉输入空间和3D身体姿势空间之间的映射函数。通过将视觉输入投影到学习到的活动流形表示上，即在学习到的流形表示上找到与视觉输入对应的点，然后插值三维姿态，可以分两步以封闭形式恢复身体姿态。
We aim to infer 3D body pose directly from human silhouettes. Given a visual input (silhouette), the objective is to recover the intrinsic body configuration, recover the viewpoint, reconstruct the input and detect any spatial or temporal outliers. In order to recover intrinsic body configuration (pose) from the visual input (silhouette), we explicitly learn view-based representations of activity manifolds as well as learn mapping functions between such central representations and both the visual input space and the 3D body pose space. The body pose can be recovered in a closed form in two steps by projecting the visual input to the learned representations of the activity manifold, i.e., finding the point on the learned manifold representation corresponding to the visual input, followed by interpolating 3D pose.