Maximum Likelihood texture tracking in highly heterogeneous PolSAR clutter.
Olivier HarantLionel BombrunGabriel VasileLaurent Ferro-FamilMichel GayPublished in: IGARSS (2010)
Keyphrases
- highly heterogeneous
- maximum likelihood
- particle filter
- likelihood function
- appearance model
- texture images
- parameter estimation
- texture analysis
- em algorithm
- textured objects
- expectation maximization
- multi band
- kalman filter
- particle filtering
- computer vision
- color distribution
- gaussian distribution
- texture classification
- real time
- texture features
- motion model
- gray level
- maximum a posteriori
- multiple objects
- hidden markov models
- texture synthesis
- feature extraction