Daniel Köhler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Daniel Köhler has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Frank Meinl
Robert Bosch GmbH Leonberg
3 shared publications- Holger Blume
Leibniz University Hannover
2 shared publications Bastian Bischoff
1 shared publication- Gia Bao Thieu
Technische Universität Braunschweig
1 shared publication - Guillermo Payá-Vayá
Technische Universität Braunschweig
1 shared publication Holger Blume
1 shared publication
Latest Publications
- 28 January 2025
- Published by Springer Nature
- p. 167-182
A Novel Chaining-Based Indirect Addressing Mode in a Vertical Vector Processor
- 28 January 2025
- Published by Springer Nature
- p. 167-182
A Novel Chaining-Based Indirect Addressing Mode in a Vertical Vector Processor
- 28 January 2025
- Published by Springer Nature
- p. 138-154
Radar Object Detection on a Vector Processor Using Sparse Convolutional Neural Networks
- 28 January 2025
- Published by Springer Nature
- p. 138-154
Radar Object Detection on a Vector Processor Using Sparse Convolutional Neural Networks
- Open Access
Improved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks
Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense grid structure is often associated with a loss of information, due to the discretization and aggregation of points. In this paper, we propose a novel architecture, multi-scale KPPillarsBEV, that aims to mitigate the negative effects of grid rendering. Specifically, we propose a novel grid rendering method, KPBEV, which leverages the descriptive power of kernel point convolutions to improve the encoding of local point cloud contexts during grid rendering. In addition, we propose a general multi-scale grid rendering formulation to incorporate multi-scale feature maps into convolutional backbones of detection networks with arbitrary grid rendering methods. We perform extensive experiments on the nuScenes dataset and evaluate the methods in terms of detection performance and computational complexity. 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. Moreover, the proposed single-scale KPBEV grid rendering improves the Car AP4.0 by 2.90% over the baseline while maintaining the same inference speed.
Open AccessImproved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks
Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense grid structure is often associated with a loss of information, due to the discretization and aggregation of points. In this paper, we propose a novel architecture, multi-scale KPPillarsBEV, that aims to mitigate the negative effects of grid rendering. Specifically, we propose a novel grid rendering method, KPBEV, which leverages the descriptive power of kernel point convolutions to improve the encoding of local point cloud contexts during grid rendering. In addition, we propose a general multi-scale grid rendering formulation to incorporate multi-scale feature maps into convolutional backbones of detection networks with arbitrary grid rendering methods. We perform extensive experiments on the nuScenes dataset and evaluate the methods in terms of detection performance and computational complexity. 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. Moreover, the proposed single-scale KPBEV grid rendering improves the Car AP4.0 by 2.90% over the baseline while maintaining the same inference speed.