Pixel-wise Ground Truth Annotation in Videos - An Semi-automatic Approach for Pixel-wise and Semantic Object Annotation.
Julius SchöningPatrick FaionGunther HeidemannPublished in: ICPRAM (2016)
Keyphrases
- pixel wise
- semi automatic
- semantic annotation
- semi automatically
- manual annotation
- gold standard
- ground truth
- pixel level
- labor intensive
- domain ontology
- fully automatic
- appearance model
- spatial information
- ontology mapping
- object tracking
- background subtraction
- semantic web
- video sequences
- metadata
- template matching
- high quality
- video surveillance
- foreground objects
- d objects
- semantic information
- moving objects
- image processing