A neural network approach to bayesian background modeling for video object segmentation.
Dubravko CulibrkOge MarquesDaniel SocekHari KalvaBorko FurhtPublished in: VISAPP (1) (2006)
Keyphrases
- background modeling
- neural network
- background subtraction
- motion detection
- varying illumination
- object detection
- moving objects
- background model
- subspace learning
- video surveillance
- object tracking
- complex background
- multi camera
- region growing
- particle filter
- frame rate
- pattern recognition
- bayesian networks
- detection algorithm
- dynamic scenes
- maximum likelihood
- mixture of gaussians
- gaussian mixture model
- surveillance system
- markov random field
- face recognition