Self-Localization in Highly Dynamic Environments Based on Dual-Channel Unscented Particle Filter.
Chen HaoLiu ChengjuChen QijunPublished in: Robotica (2021)
Keyphrases
- particle filter
- highly dynamic environments
- dual channel
- particle filtering
- particle filtering algorithm
- dynamic environments
- object tracking
- kalman filter
- visual tracking
- state space
- likelihood function
- motion model
- state estimation
- mean shift
- monte carlo
- importance sampling
- data association
- appearance model
- target tracking
- observation model
- multiple object tracking
- proposal distribution
- robust tracking
- sequential monte carlo
- robust visual tracking
- computer vision
- multiple objects
- face tracking
- multiple hypothesis
- multiple hypotheses
- rao blackwellized particle filter
- kalman filtering
- tracking accuracy
- abrupt motion
- multiple target tracking
- articulated body
- structure from motion
- em algorithm