An LSTM network is trained via supervised learning on simulated radar data to directly predict measurement-to-track association probabilities for multi-target tracking in clutter, reporting improved association ratios and fewer ID switches.
Iterative joint integrated probabilistic data association filter for multiple-detection multiple- target tracking,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter
An LSTM network is trained via supervised learning on simulated radar data to directly predict measurement-to-track association probabilities for multi-target tracking in clutter, reporting improved association ratios and fewer ID switches.