Data-driven XGBoost-based filter for target tracking

Data-driven XGBoost-based filter for target tracking

In recent years, the data-driven approach has been introduced in the field of target tracking as a powerful tool developing the end-to-end mapping relationship between input features and outputs. Typically, in data-driven methods, neural networks serve as a supplement of traditional Bayesian filters...

Full description

Bibliographic Details
Main Authors: Bowen Zhai, Wei Yi, Ming Li, Hao Ju, Lingjiang Kong
Format: Article
Language:English
Published: Wiley 2019-08-01
Series:The Journal of Engineering
Subjects:
kalman filters
particle filtering (numerical methods)
learning (artificial intelligence)
target tracking
bayes methods
probability
neural nets
traditional bayesian filters
data-driven methods
end-to-end mapping relationship
data-driven approach
data-driven xgboost-based filter
data-driven random-forest-based filter
randomly initialised targets
different tracks
centralisation strategy
sliding window
data generator
dxgbf
Online Access:https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0174

Internet

https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0174

Similar Items