Abstract
Activity Analysis of Surveillance Video is currently the focus of research community, however most work propose methods which are location specific or are activity specific. There has been very little work on automatic extraction of generic descriptors from video clips, which can then be used to build complex activities as required. In this work we present a novel approach to semantically describe the human activity from motion trajectories as a human operator asked to enter meta-data would. Our approach is generic that is the mapping to semantic descriptors can be applied across different camera locations and can be used with or with out site-specific information to build complex activities.
| Original language | English |
|---|---|
| Title of host publication | Automatic Semantic labelling of Human Activities |
| Place of Publication | U.K |
| Publisher | Institution of Engineering and Technology |
| Number of pages | 611 |
| Publication status | Published - 2006 |
| Event | VIE 2006 - Bangalore Duration: 26 Sept 2006 → 26 Sept 2006 |
Publication series
| Name | Automatic Semantic labelling of Human Activities |
|---|---|
| Publisher | IET |
Conference
| Conference | VIE 2006 |
|---|---|
| City | Bangalore |
| Period | 26/09/06 → 26/09/06 |
Keywords
- Motion trajectory
- semantic labelling
- video surveillance
- scene classification