Foreground detection by probabilistic modeling of the features discovered by stacked denoising autoencoders in noisy video sequences.
Jorge García-GonzálezJuan Miguel Ortiz-de-Lazcano-LobatoRafael M. Luque-BaenaMiguel A. Molina-CabelloEzequiel López-RubioPublished in: Pattern Recognit. Lett. (2019)
Keyphrases
- denoising
- probabilistic modeling
- foreground detection
- video sequences
- image processing
- motion estimation
- foreground objects
- video surveillance
- image sequences
- background subtraction
- bayesian networks
- feature extraction
- object tracking
- parameter estimation
- feature vectors
- dynamic scenes
- bayesian inference
- feature space
- human detection