Home | Impressum | Datenschutz | KIT
Florian Wirth

M.Sc. Florian Wirth

Research Assistant / Wissenschaftlicher Mitarbeiter
Raum: 033
Tel.: +49 721 608-42690
florian wirthKeb4∂kit edu

Karlsruher Institut für Technologie
Institut für Mess- und Regelungstechnik
Engler-Bunte-Ring 21
Gebäude 40.32
D-76131 Karlsruhe


Forschung

  • Deep Learning in Automated Driving
  • State Estimation and Prediction of Vulnerable Road Users (VRUs)
  • Data Acquisition and Labeling within the European General Data Protection Regulation (DSGVO)

 

Zu vergebende Abschlussarbeiten
Titel


Laufende Bachelor-, Diplom-, Master- und Studienarbeiten
Titel


Hiwi-Stellenangebote
Titel


Veröffentlichungen

Javier Lorenzo Díaz, Ignacio Parra Alonso, Florian Wirth, Christoph Stiller, David Fernandez Llorca, Miguel A. Sotelo. RNN-Based Pedestrian Crossing Prediction Using Activity and Pose-Related Features. In Proc. IEEE Intelligent Vehicles Symposium (IV), Las Vegas, USA, June 2020.

Florian Wirth, Tao Wen, Carlos Fernandez Lopez, Christoph Stiller. Model-Based Prediction of Two-Wheelers. In Proc. IEEE Intelligent Vehicles Symposium (IV), Las Vegas, USA, June 2020.

Florian Wirth, Jannik Quehl, Jeffrey Ota, Christoph Stiller. PointAtMe: Efficient 3D Point Cloud Labeling in Virtual Reality. In Proc. IEEE Intelligent Vehicles Symposium (IV), Paris, France, June 2019. [ DOI | http ]

Florian Wirth, Stephan Krane, Melanie Loos, Eike Rehder, Carlos Fernandez Lopez. What Does a Good Prediction Look Like? In Proc. IEEE International Conference on Intelligent Transportation Systems (ITSC), Auckland, New Zealand, Oktober 2019. [ DOI | http ]

Alexander Masalov, Pavel Matrenin, Jeffrey Ota, Florian Wirth, Christoph Stiller, Heath Corbet, Eric Lee. Specialized Cyclist Detection Dataset: Challenging Real-World Computer Vision Dataset for Cyclist Detection Using a Monocular RGB Camera. In 2019 IEEE Intelligent Vehicles Symposium (IV), Seiten 114--118. IEEE, 2019.

Eike Rehder, Florian Wirth, Martin Lauer, Christoph Stiller. Pedestrian prediction by planning using deep neural networks. In Proc. IEEE Int. Conf. International Conference on Robotics and Automation, May 2018. [ DOI | http ]