Name
Title | ||
|---|---|---|
On the improvement of human action recognition from depth map sequences using Space-Time Occupancy Patterns |
Abstract | ||
|---|---|---|
We present a new visual representation for 3D action recognition from sequences of depth maps. In this new representation, space and time axes are divided into multiple segments to define a 4D grid for each depth map sequences. Each cell in the grid is associated with an occupancy value which is a function of the number of space-time points falling into this cell. The occupancy values of all the cells form a high dimensional feature vector, called Space-Time Occupancy Pattern (STOP). We then perform dimensionality reduction to obtain lower-dimensional feature vectors. The advantage of STOP is that it preserves spatial and temporal contextual information between space and time cells while being flexible enough to accommodate intra-action variations. Furthermore, we combine depth maps with skeletons in order to obtain view invariance and present an automatic segmentation and time alignment method for on-line recognition of depth sequences. Our visual representation is validated with experiments on a public 3D human action dataset. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1016/j.patrec.2013.07.011 | Pattern Recognition Letters |
Keywords | DocType | Volume |
time alignment method,space-time occupancy patterns,occupancy value,new visual representation,visual representation,depth map sequence,depth sequence,depth map,time cell,new representation,time axis,human action recognition,pattern recognition | Journal | 36, |
ISSN | Citations | PageRank |
0167-8655 | 26 | 0.78 |
References | Authors | |
24 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Antonio W. Vieira | 1 | 83 | 3.18 |
| Erickson R. Do Nascimento | 2 | 265 | 23.10 |
| Gabriel Leivas Oliveira | 3 | 225 | 9.70 |
| zicheng liu | 4 | 3662 | 199.64 |
| Mario F. M. Campos | 5 | 106 | 9.17 |