User: Guest  Login
Document type:
Konferenzbeitrag 
Contribution type:
Textbeitrag / Aufsatz 
Author(s):
Michael Truong Le, Frederik Diehl, Thomas Brunner, Alois Knoll 
Title:
Uncertainty Estimation for Deep Neural Object Detectors in Safety-Critical Applications 
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 algorithm...    »
 
Editor:
IEEE 
Book / Congress title:
International Conference on Intelligent Transportation Systems 2018 
Year:
2018