Background subtraction based on Gaussian mixture models using color and depth information.
Young-Min SongSeungJong NohJongmin YuCheonwi ParkByung-Geun LeePublished in: ICCAIS (2014)
Keyphrases
- gaussian mixture model
- background subtraction
- depth information
- depth data
- mixture model
- depth map
- stereo vision
- video surveillance
- background model
- feature vectors
- foreground objects
- color images
- em algorithm
- maximum likelihood
- color information
- feature space
- expectation maximization
- dynamic scenes
- shadow detection
- stereo matching
- depth images
- real time
- foreground segmentation
- color correction
- mixture of gaussians
- vision system
- d scene
- optical flow
- reinforcement learning
- training data
- three dimensional
- image processing
- machine learning