KIT | KIT-Bibliothek | Impressum | Datenschutz

Estimating Uncertainties of Recurrent Neural Networks In Application to Multitarget Tracking

Pollithy, Daniel; Reith-Braun, Marcel; Pfaff, Florian; Hanebeck, Uwe D.

In multitarget tracking, finding an association between the new measurements and the known targets is a crucial challenge. By considering both the uncertainties of all the predictions and measurements, the most likely association can be determined. While Kalman filters inherently provide the predicted uncertainties, they require a predefined model. In contrast, neural networks offer data-driven possibilities, but provide only deterministic predictions. We therefore compare two common approaches for uncertainty estimation in neural networks applied to LSTMs using our multitarget tracking benchmark for optical belt sorting. As a result, we show that the estimation of measurement uncertainties improves the tracking results of LSTMs, posing them as a viable alternative to manual motion modeling.

Open Access Logo

Postprint §
DOI: 10.5445/IR/1000123693
Frei zugänglich ab 01.10.2021
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsmonat/-jahr 09.2020
Sprache Englisch
Identifikator ISBN: 978-172816422-9
KITopen-ID: 1000123693
Erschienen in Proceedings of the 2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2020), Karlsruhe, 14 - 16 September 2020
Veranstaltung International Conference on Multisensor Fusion and Integration for Intelligent Systems (2020), Online, 14.09.2020 – 16.09.2020
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten 229-236
Bemerkung zur Veröffentlichung Die Veranstaltung fand als Online-Event statt
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page