Name
Title | ||
|---|---|---|
An automatic three-dimensional human behavior analysis system for video surveillance applications |
Abstract | ||
|---|---|---|
We developed a system for automatic 3-D human body motion in video surveillance sequences. As the first step, the human body that will be used for the analysis is extracted and tracked based on video object (VO) segmentation technique. Once human body is extracted, this 2-D object, which consists of the merging of several regions, is then analyzed for activity and body part interpretation. The specific 2-D human body shape along with the information derived from maximum probable explanation (MPE) of dynamic Bayesian modeling is then effectively utilized to obtain 3-D body model frame-by-frame so that the 3-D motion trajectory of the human object can be derived for any future event analysis, which is independent of the viewing perspective of the 2-D video |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/ISCAS.2006.1692632 | ISCAS |
Keywords | Field | DocType |
dynamic bayesian modeling,video object segmentation technique,2d video,bayes methods,feature extracted,video surveillance sequences,3d motion trajectory,image segmentation,surveillance,automatic 3d human body motion,image sequences,maximum probable explanation,2d human body shape,image motion analysis,bayesian model,three dimensional,image analysis,shape,human behavior,human body | Computer vision,Bayesian inference,Pattern recognition,Computer science,Segmentation,Image segmentation,Video tracking,Artificial intelligence,Merge (version control),Event analysis,Trajectory,Human body | Conference |
ISSN | ISBN | Citations |
0271-4302 | 0-7803-9389-9 | 1 |
PageRank | References | Authors |
0.43 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jenq-Neng Hwang | 1 | 1675 | 206.57 |
| Ibrahim Karliga | 2 | 9 | 1.94 |
| H.-Y. Cheng | 3 | 1 | 0.43 |