Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 2 of 17
Back to Result List

Object Detection for the Audi Autonomous Driving Cup

  • One of the challenges for autonomous driving in general is to detect objects in the car's camera images. In the Audi Autonomous Driving Cup (AADC), among those objects are other cars, adult and child pedestrians andemergency vehicle lighting. We show that with recent deep learning networks weare able to detect these objects reliably on the limited Hardware of the model cars. Also, theOne of the challenges for autonomous driving in general is to detect objects in the car's camera images. In the Audi Autonomous Driving Cup (AADC), among those objects are other cars, adult and child pedestrians andemergency vehicle lighting. We show that with recent deep learning networks weare able to detect these objects reliably on the limited Hardware of the model cars. Also, the same deep network is used to detect road features like mid lines, stoplines and even complete crossings. Best results are achieved using Faster R-CNNwith Inception v2 showing an overall accuracy of 0.84 at 7 Hz.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Felix Wagner, Christoph Lehmann, Klaus DorerGND
Editor:Andreas Christ, Franz Quint
Creating Corporation:Hochschule Karlsruhe
Contributing Corporation:Hochschule Offenburg
Year of Publication:2019
Pagenumber:4
ISBN:978-3-9820756-0-0 (Print)
ISBN:978-3-9820756-1-7 (eBook)
Language:English
Parent Title (English):Artificial Intelligence. From Research To Application
First Page:43
Last Page:46
Document Type:Conference Proceeding
Open Access:Frei zugänglich
Institutes:Bibliografie
Release Date:2020/01/21
Licence (German):License LogoEs gilt das UrhG
Note:
The Upper-Rhine Artificial Intelligence Symposium (UR-AI 2019), Offenburg, March 13, 2019
ArXiv Id:http://arxiv.org/abs/1903.08495