Benutzer: Gast  Login
Titel:

Uncertainty Estimation for Deep Neural Object Detectors in Safety-Critical Applications

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Textbeitrag / Aufsatz
Autor(en):
Michael Truong Le, Frederik Diehl, Thomas Brunner, Alois Knoll
Abstract:
Object detection algorithms are essential components for perceiving the environment in safety-critical systems like automated driving. However, current state-of-the-art algorithms based on deep neural networks can give high confidence values to falsely detected objects and it is therefore important to model uncertainty for these predictions. In this paper, we propose two aleatoric uncertainty estimation algorithms for state-of-the-art deep learning based object detectors. Established algorithms...     »
Herausgeber:
IEEE
Kongress- / Buchtitel:
International Conference on Intelligent Transportation Systems 2018
Jahr:
2018
 BibTeX