no code implementations • 15 Aug 2023 • Marius Lippke, Maurice Quach, Sascha Braun, Daniel Köhler, Michael Ulrich, Bastian Bischoff, Wei Yap Tan
This paper investigates sparse convolutional object detection networks, which combine powerful grid-based detection with low compute resources.
no code implementations • 25 May 2023 • Daniel Köhler, Maurice Quach, Michael Ulrich, Frank Meinl, Bastian Bischoff, Holger Blume
The proposed multi-scale KPPillarsBEV architecture outperforms the baseline by 5. 37% and the previous state of the art by 2. 88% in Car AP4. 0 (average precision for a matching threshold of 4 meters) on the nuScenes validation set.
no code implementations • 7 Jul 2022 • Daniel Niederlöhner, Michael Ulrich, Sascha Braun, Daniel Köhler, Florian Faion, Claudius Gläser, André Treptow, Holger Blume
Labels for the Cartesian velocities or contiguous sequences, which are expensive to obtain, are not required.
no code implementations • 3 May 2022 • Michael Ulrich, Sascha Braun, Daniel Köhler, Daniel Niederlöhner, Florian Faion, Claudius Gläser, Holger Blume
This paper presents novel hybrid architectures that combine grid- and point-based processing to improve the detection performance and orientation estimation of radar-based object detection networks.