Next Article in Journal
Multicriteria Analysis of Alternative Marine Fuels in Sustainable Coastal Marine Traffic
Previous Article in Journal
In-Situ Photo-Dissociation and Polymerization of Carbon Disulfide with Vacuum Ultraviolet Microplasma Flat Lamp for Organic Thin Films
 
 
Article

Kernel Point Convolution LSTM Networks for Radar Point Cloud Segmentation

1
Institute of Automotive Technology, Technical University of Munich, 85748 Garching, Germany
2
mLab:Real-Time and Embedded Systems Lab, University of Pennsylvania, Philadelphia, PA 19104-6243, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Oscar Reinoso García
Appl. Sci. 2021, 11(6), 2599; https://doi.org/10.3390/app11062599
Received: 11 February 2021 / Revised: 9 March 2021 / Accepted: 11 March 2021 / Published: 15 March 2021
(This article belongs to the Section Robotics and Automation)
State-of-the-art 3D object detection for autonomous driving is achieved by processing lidar sensor data with deep-learning methods. However, the detection quality of the state of the art is still far from enabling safe driving in all conditions. Additional sensor modalities need to be used to increase the confidence and robustness of the overall detection result. Researchers have recently explored radar data as an additional input source for universal 3D object detection. This paper proposes artificial neural network architectures to segment sparse radar point cloud data. Segmentation is an intermediate step towards radar object detection as a complementary concept to lidar object detection. Conceptually, we adapt Kernel Point Convolution (KPConv) layers for radar data. Additionally, we introduce a long short-term memory (LSTM) variant based on KPConv layers to make use of the information content in the time dimension of radar data. This is motivated by classical radar processing, where tracking of features over time is imperative to generate confident object proposals. We benchmark several variants of the network on the public nuScenes data set against a state-of-the-art pointnet-based approach. The performance of the networks is limited by the quality of the publicly available data. The radar data and radar-label quality is of great importance to the training and evaluation of machine learning models. Therefore, the advantages and disadvantages of the available data set, regarding its radar data, are discussed in detail. The need for a radar-focused data set for object detection is expressed. We assume that higher segmentation scores should be achievable with better-quality data for all models compared, and differences between the models should manifest more clearly. To facilitate research with additional radar data, the modular code for this research will be made available to the public. View Full-Text
Keywords: perception; deep learning; radar segmentation; radar point cloud; object detection perception; deep learning; radar segmentation; radar point cloud; object detection
Show Figures

Figure 1

MDPI and ACS Style

Nobis, F.; Fent, F.; Betz, J.; Lienkamp, M. Kernel Point Convolution LSTM Networks for Radar Point Cloud Segmentation. Appl. Sci. 2021, 11, 2599. https://doi.org/10.3390/app11062599

AMA Style

Nobis F, Fent F, Betz J, Lienkamp M. Kernel Point Convolution LSTM Networks for Radar Point Cloud Segmentation. Applied Sciences. 2021; 11(6):2599. https://doi.org/10.3390/app11062599

Chicago/Turabian Style

Nobis, Felix, Felix Fent, Johannes Betz, and Markus Lienkamp. 2021. "Kernel Point Convolution LSTM Networks for Radar Point Cloud Segmentation" Applied Sciences 11, no. 6: 2599. https://doi.org/10.3390/app11062599

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop