no code implementations • 2 Apr 2024 • Christoph Glasmacher, Michael Schuldes, Sleiman El Masri, Lutz Eckstein
Scenario-based testing of automated driving functions has become a promising method to reduce time and cost compared to real-world testing.
1 code implementation • 18 Feb 2024 • Till Beemelmanns, Yuchen Tao, Bastian Lampe, Lennart Reiher, Raphael van Kempen, Timo Woopen, Lutz Eckstein
Transforming the raw point cloud data into a dense 2D matrix structure is a promising way for applying compression algorithms.
1 code implementation • 18 Feb 2024 • Till Beemelmanns, Quan Zhang, Christian Geller, Lutz Eckstein
Multi-modal 3D object detection models for automated driving have demonstrated exceptional performance on computer vision benchmarks like nuScenes.
no code implementations • 17 Jan 2024 • Raphael van Kempen, Tim Rehbronn, Abin Jose, Johannes Stegmaier, Bastian Lampe, Timo Woopen, Lutz Eckstein
Our findings demonstrate that our novel method, involving temporal offset augmentation through randomized frame skipping in sequences, enhances object detection accuracy compared to both the baseline model (Pillar-based Object Detection) and no augmentation.
no code implementations • 22 Dec 2023 • Till Beemelmanns, Wassim Zahr, Lutz Eckstein
Vision Transformers (ViTs) have achieved state-of-the-art results on various computer vision tasks, including 3D object detection.
no code implementations • 24 Jul 2023 • Laurent Kloeker, Gregor Joeken, Lutz Eckstein
Due to its modularity, the calculation model is suitable for diverse applications and outputs a distinctive evaluation of the underlying cost-benefit ratio of investigated setups.
no code implementations • 16 Apr 2023 • Laurent Kloeker, Chenghua Liu, Chao Wei, Lutz Eckstein
The use of smart roadside infrastructure sensors is highly relevant for future applications of connected and automated vehicles.
1 code implementation • 8 Jun 2022 • Mohsen Vadidar, Ali Kariminezhad, Christian Mayr, Laurent Kloeker, Lutz Eckstein
The RGB complementary metal-oxidesemiconductor (CMOS) sensor works within the visible light spectrum.
1 code implementation • IEEE Intelligent Vehicles Symposium (IV) 2022 • Tobias Moers, Lennart Vater, Robert Krajewski, Julian Bock, Adrian Zlocki, Lutz Eckstein
For system-level evaluation and safety validation of an automated driving system, real-world trajectory datasets are of great value for several tasks in the process, i. a.
no code implementations • 12 Feb 2022 • Christoph Glasmacher, Robert Krajewski, Lutz Eckstein
Considering this amount of data, it is necessary to be able to compare these datasets in-depth with ease to get an overview.
no code implementations • 13 Jul 2021 • Laurent Kloeker, Amarin Kloeker, Fabian Thomsen, Armin Erraji, Lutz Eckstein, Serge Lamberty, Adrian Fazekas, Eszter Kalló, Markus Oeser, Charlotte Fléchon, Jochen Lohmiller, Pascal Pfeiffer, Martin Sommer, Helen Winter
With the Corridor for New Mobility Aachen - D\"usseldorf, an integrated development environment is created, incorporating existing test capabilities, to systematically test and validate automated vehicles in interaction with connected Intelligent Transport Systems Stations (ITS-Ss).
no code implementations • 8 Jun 2021 • Laurent Kloeker, Fabian Thomsen, Lutz Eckstein, Philip Trettner, Tim Elsner, Julius Nehring-Wirxel, Kersten Schuster, Leif Kobbelt, Michael Hoesch
The research project HDV-Mess aims at a currently missing, but very crucial component for addressing important challenges in the field of connected and automated driving on public roads.
no code implementations • 1 May 2021 • Maike Scholtes, Lutz Eckstein
On top of the literature review on environment factors influencing radar sensors, the paper introduces a modular structuring concept for such that can facilitate real-world data analysis by categorizing the factors possibly leading to performance limitations into different independent clusters in order to reduce the level of detail in complex real-world environments.
1 code implementation • 16 Feb 2021 • Michael Hoss, Maike Scholtes, Lutz Eckstein
Safety assurance of automated driving systems must consider uncertain environment perception.
no code implementations • 9 Dec 2020 • Maike Scholtes, Lukas Westhofen, Lara Ruth Turner, Katrin Lotto, Michael Schuldes, Hendrik Weber, Nicolas Wagener, Christian Neurohr, Martin Bollmann, Franziska Körtke, Johannes Hiller, Michael Hoss, Julian Bock, Lutz Eckstein
To define those scenarios and operate in a complex real-world design domain, a structured description of the environment is needed.
no code implementations • 2 Dec 2020 • Daniel Bauer, Lars Kuhnert, Lutz Eckstein
In this work, we describe a novel approach to integrate deep ISMs together with geometric ISMs into the evidential occupancy mapping framework.
1 code implementation • IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) 2020 • Robert Krajewski, Tobias Moers, Julian Bock, Lennart Vater, Lutz Eckstein
We present a new dataset of road user trajectories at roundabouts in Germany.
no code implementations • 28 Jul 2020 • Laurent Kloeker, Christian Kotulla, Lutz Eckstein
The use of infrastructure sensor technology for traffic detection has already been proven several times.
no code implementations • 22 Jun 2020 • Laurent Kloeker, Christian Geller, Amarin Kloeker, Lutz Eckstein
We then analyze the properties of the resulting point clouds and perform MODT for all emerging traffic participants.
2 code implementations • 8 May 2020 • Lennart Reiher, Bastian Lampe, Lutz Eckstein
Accurate environment perception is essential for automated driving.
Ranked #1 on Semantic Segmentation on Cam2BEV
Bird View Synthesis Cross-View Image-to-Image Translation +2
no code implementations • 5 May 2020 • Bastian Lampe, Raphael van Kempen, Timo Woopen, Alexandru Kampmann, Bassam Alrifaee, Lutz Eckstein
This paper describes a method to combine perception data of automated and connected vehicles in the form of evidential Dynamic Occupany Grid Maps (DOGMas) in a cloud-based system.
2 code implementations • 18 Nov 2019 • Julian Bock, Robert Krajewski, Tobias Moers, Steffen Runde, Lennart Vater, Lutz Eckstein
The dataset consists of 10 hours of measurement data from four intersections and is available online for non-commercial research at: http://www. inD-dataset. com
no code implementations • 29 Mar 2019 • Daniel Bauer, Lars Kuhnert, Lutz Eckstein
To perform high speed tasks, sensors of autonomous cars have to provide as much information in as few time steps as possible.
no code implementations • 29 Mar 2019 • Daniel Bauer, Lars Kuhnert, Lutz Eckstein
One essential step to realize modern driver assistance technology is the accurate knowledge about the location of static objects in the environment.
2 code implementations • 11 Oct 2018 • Robert Krajewski, Julian Bock, Laurent Kloeker, Lutz Eckstein
Scenario-based testing for the safety validation of highly automated vehicles is a promising approach that is being examined in research and industry.