A multi-object tracker using dynamic Bayesian networks and a residual neural network based similarity estimator.
Mohamad SaadaChristos KouppasBaihua LiQinggang MengPublished in: Comput. Vis. Image Underst. (2022)
Keyphrases
- multi object
- dynamic bayesian networks
- particle filtering
- particle filter
- multiple objects
- bayesian networks
- visual tracking
- approximate inference
- human perception
- similarity measure
- structure learning
- least squares
- appearance model
- maximum likelihood
- state variables
- state space
- image sequences
- maximum a posteriori
- object tracking
- statistical shape model
- belief propagation
- human body