N
Niels Ole Salscheider
Researcher at Center for Information Technology
Publications - 15
Citations - 261
Niels Ole Salscheider is an academic researcher from Center for Information Technology. The author has contributed to research in topics: Object detection & Convolutional neural network. The author has an hindex of 7, co-authored 15 publications receiving 162 citations. Previous affiliations of Niels Ole Salscheider include Forschungszentrum Informatik & Karlsruhe Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Realtime 3D Object Detection for Automated Driving Using Stereo Vision and Semantic Information
TL;DR: This work proposes a 3D object detection and pose estimation method for automated driving using stereo images that focuses not only on cars, but on all types of road users and can ensure real-time capability through GPU implementation of the entire processing chain.
Journal ArticleDOI
Making Bertha Cooperate–Team AnnieWAY’s Entry to the 2016 Grand Cooperative Driving Challenge
Omer Sahin Tas,Niels Ole Salscheider,Fabian Poggenhans,Sascha Wirges,Claudio Bandera,Marc Rene Zofka,Tobias Strauss,J. Marius Zollner,Christoph Stiller +8 more
TL;DR: This paper presents a motion planner that plans different maneuvers flexibly by augmenting the cost function with situation specific cost terms and describes the requirements of the 2016 GCDC and evaluates the authors' performance during the competition.
Proceedings ArticleDOI
Precise Localization in High-Definition Road Maps for Urban Regions
TL;DR: This paper introduces a modular approach in which detections from different detection algorithms are associated with elements in the map and then fused to an absolute pose using an Unscented Kalman Filter, and shows that this approach is capable to be used for highly automated driving.
Proceedings ArticleDOI
Robot operating system: A modular software framework for automated driving
TL;DR: The requirements for software frameworks for automated driving projects are analyzed and the communication overhead of ROS is analyzed quantitatively in various configurations showing its applicability for systems with a high data load.
Posted Content
FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings
TL;DR: This work proposes FeatureNMS, a approach that outperforms classical NMS and derived approaches and achieves state of the art performance in scenes that contain objects with high overlap.