Sciweavers

Share
FGR
2011
IEEE

Tangent bundle for human action recognition

10 years 3 months ago
Tangent bundle for human action recognition
— Common human actions are instantly recognizable by people and increasingly machines need to understand this language if they are to engage smoothly with people. Here we introduce a new method for automated human action recognition. The proposed method represents videos as a tangent bundle on a Grassmann manifold. Videos are expressed as third order tensors and factorized to a set of tangent spaces. Tangent vectors are then computed between elements on a Grassmann manifold and exploited for action classification. In particular, logarithmic mapping is applied to map a point from the manifold to tangent vectors centered at a given element. The canonical metric is used to induce the intrinsic distance for a set of tangent spaces. Empirical results show that our method is effective on both uniform and non-uniform backgrounds for action classification. We achieve recognition rates of 91% on the Cambridge gesture dataset, 88% on the UCF sport dataset, and 97% on the KTH human action dat...
Yui Man Lui, J. Ross Beveridge
Added 28 Aug 2011
Updated 28 Aug 2011
Type Journal
Year 2011
Where FGR
Authors Yui Man Lui, J. Ross Beveridge
Comments (0)
books