Insufficiency-Driven DNN Error Detection in the Context of SOTIF on Traffic Sign Recognition Use Case

Insufficiency-Driven DNN Error Detection in the Context of SOTIF on Traffic Sign Recognition Use Case

Deep Neural Networks (DNNs) are used in various domains and industry fields with great success due to their ability to learn complex tasks from high-dimensional data. However, the data-driven approach within deep learning results in various DNN-specific insufficiencies (e.g., robustness limitations,...

Full description

Bibliographic Details
Main Authors: Lukas Hacker, Jorg Seewig
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Open Journal of Intelligent Transportation Systems
Subjects:
Artificial intelligence
automated driving
deep learning
deep neural networks
safety of the intended functionality
traffic sign recognition
Online Access:https://ieeexplore.ieee.org/document/10016638/

Internet

https://ieeexplore.ieee.org/document/10016638/

Similar Items