Context Identification from Video-surveillance Scenes of Multipurpose Halls
| Art der Publikation: | Artikel in einem Konferenzbericht |
| Zitat: | |
| Jahr: | 2014 |
| Monat: | März |
| Ort: | Lebanese University, Hadath, Lebanon |
| Organisation: | LAAS'14, 27-29.03.2014 |
| Abriss: | A novel method for multimodal context identification from video-surveillance footage of multipurpose halls is presented is this paper. After presenting a dedicated definition of ‘Context’ in computer vision systems, the goal is resumed by detecting the active context type among predefined ones. To this end, a spatial modeling of context is performed by extracting five discriminative semantic features according to depth zones. These zones are detected by depth-based scene segmentation method. These features are processed with the Transferable Belief Model (TBM) to propose a classification. Results show the validity of the method for context recognition. |
| Schlagworte: | context modeling, Pattern Recognition, Transferable Belief Model, Video-surveillance |
| Autoren | |
| Hinzugefügt von: | [] |
| Gesamtbewertung: | 0 |
|
Anhänge
|
|
|
|
|
Notizen
|
|
|
|
|
|
Themen
|
|
|
|
|
