Super Normal Vector for Activity Recognition Using Depth Sequences
Citations Over TimeTop 1% of 2014 papers
Abstract
This paper presents a new framework for human activity recognition from video sequences captured by a depth camera. We cluster hypersurface normals in a depth sequence to form the polynormal which is used to jointly characterize the local motion and shape information. In order to globally capture the spatial and temporal orders, an adaptive spatio-temporal pyramid is introduced to subdivide a depth video into a set of space-time grids. We then propose a novel scheme of aggregating the low-level polynormals into the super normal vector (SNV) which can be seen as a simplified version of the Fisher kernel representation. In the extensive experiments, we achieve classification results superior to all previous published results on the four public benchmark datasets, i.e., MSRAction3D, MSRDailyActivity3D, MSRGesture3D, and MSRActionPairs3D.
Related Papers
- → On some real hypersurfaces of a complex projective space(1975)283 cited
- → On Some Real Hypersurfaces of a Complex Projective Space(1975)81 cited
- → On the problem of isometry of a hypersurface preserving mean curvature(2007)4 cited
- → On the problem of isometry of a hypersurface preserving mean curvature(2007)
- ON A HYPERSURFACE OF THE FIRST APPROXIMATE MATSUMOTO SPACE(2001)