Vision Algorithms: Scene Models
-
Definition : a priori knowledge describing:
- the cameras: 3D position of the cameras, camera type (colour,
resolution), field of view and calibration matrix
- context objects : equipment (bench, trash, door), walls, interesting
zones (entrance zone), areas of interest
- 3D geometry : 3D location of the object and its volume
- Semantic information : type of the object (equipment), its
characteristics (yellow, fragile) and its function (seat)
-
Role:
- to keep the interpretation independent from the cameras and the sites
: many cameras, one 3D referential
- to provide additional knowledge to interpret up to the scenario level