Loading...
Please wait, while we are loading the content...
Similar Documents
Polynormal Fisher Vector for Activity Recognition from Depth Sequences
| Content Provider | CiteSeerX |
|---|---|
| Author | Yang, Xiaodong Tian, Yingli |
| Abstract | The advent of depth sensors has facilitated a variety of visual recognition tasks including human activity understanding. This paper presents a novel feature representation to recognize human activities from video sequences captured by a depth camera. We assemble local neighboring hypersurface normals from a depth sequence to form the polynormal which jointly encodes local motion and shape cues. Fisher vector is employed to aggregate the low-level polynormals into the Polynormal Fisher Vector. In order to capture the global spatial layout and temporal order, we employ a spatio-temporal pyramid to subdivide a depth sequence into a set of space-time cells. Polynormal Fisher Vectors from these cells are combined as the final representation of a depth video. Experimental results demonstrate that our method achieves the state-of-the-art results on the two public benchmark datasets, i.e., MSRAction3D and MSRGesture3D. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Depth Sequence Polynormal Fisher Vector Activity Recognition Video Sequence Human Activity Temporal Order Fisher Vector Low-level Polynormals Shape Cue Public Benchmark Datasets Local Motion Final Representation Visual Recognition Task Novel Feature Representation Global Spatial Layout Depth Sensor Hypersurface Normal Space-time Cell Human Activity Understanding Depth Video State-of-the-art Result Spatio-temporal Pyramid Experimental Result Depth Camera |
| Content Type | Text |
| Resource Type | Article |
