Coarse localization using space-time and semantic-context representations of geo-referenced video sequences.
Jassem MansouriBassem SeddikSami GazzahThierry ChateauPublished in: IPTA (2015)
Keyphrases
- space time
- video sequences
- geo referenced
- semantic context
- video annotation
- statistical data
- key frames
- dynamic scenes
- video data
- visual information
- frame rate
- video content
- temporal information
- moving objects
- image sequences
- urban environments
- spatio temporal
- video shots
- human actions
- video camera
- object tracking
- video database
- video frames
- geospatial data
- foreground objects
- visual words
- multiresolution
- human motion
- low level features
- spatial objects
- low level
- high resolution
- spatial relationships
- video images
- image classification
- feature space
- data structure