Deep Autoencoder Architectures For Foreground Object Detection In Video Sequences Based On Probabilistic Mixture Models.
Jorge García-GonzálezMiguel A. Molina-CabelloRafael M. Luque-BaenaJuan Miguel Ortiz-de-Lazcano-LobatoEzequiel López-RubioPublished in: ICIP (2020)
Keyphrases
- mixture model
- generative model
- video sequences
- probabilistic model
- foreground object detection
- foreground objects
- gaussian mixture model
- generalized em algorithm
- em algorithm
- density estimation
- foreground detection
- expectation maximization
- language model
- mixture modeling
- unsupervised learning
- model selection
- maximum likelihood
- frame rate
- image sequences
- probability density function
- bayesian framework
- moving objects
- video camera
- bayesian networks
- machine learning
- object categories
- dynamic scenes
- gaussian mixture
- video data
- object recognition