RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications

Schumann, Ole; Hahn, Markus; Scheiner, Nicolas; Weishaupt, Fabio; Tilly, Julius F.; Dickmann, Jürgen; Wöhler, Christian

doi:10.23919/fusion49465.2021.9627037

Cited by 91 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FoVs of different modalities are largely overlapped and, hence, are well suited for evaluating sensor fusion algorithms. The RadarScenes dataset [36] is a diverse large-scale dataset for instance segmentation of radar point clouds. It uses four 77 GHz radars with overlapping FoVs in the front of the vehicle.…”

Section: Radar Datasetsmentioning

confidence: 99%

Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges

Zhou

Liu

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

With recent developments, the performance of automotive radar has improved significantly. The next generation of 4D radar can achieve imaging capability in the form of high-resolution point clouds. In this context, we believe that the era of deep learning for radar perception has arrived. However, studies on radar deep learning are spread across different tasks, and a holistic overview is lacking. This review paper attempts to provide a big picture of the deep radar perception stack, including signal processing, datasets, labelling, data augmentation, and downstream tasks such as depth and velocity estimation, object detection, and sensor fusion. For these tasks, we focus on explaining how the network structure is adapted to radar domain knowledge. In particular, we summarise three overlooked challenges in deep radar perception, including multi-path effects, uncertainty problems, and adverse weather effects, and present some attempts to solve them.

show abstract

Section: Radar Datasetsmentioning

confidence: 99%

Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges

Zhou

Liu

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The Zendar dataset [27] provides Range-Doppler and Range-Azimuth views for such a radar. Both Astyx [24] and RadarScenes [36] datasets contain HD radar data processed as point clouds.…”

Section: Radar Backgroundmentioning

confidence: 99%

“…Owing to the promising capabilities of HD radars, our work [24] 2019 Small HD CL 3D Boxes RadarRobotCar [1] 2020 Large S CLO CARRADA [31] 2020 Small LD C Segmentation RADIATE [38] 2020 Medium S CLO 2D Boxes MulRan [17] 2020 Medium S CLO Zendar [27] 2020 Small HD CL 2D Boxes CRUW [41] 2021 Medium LD C Point Location RadarScenes [36] 2021 Large HD CO Point-wise RADDet [43] 2021…”

Section: Introductionmentioning

confidence: 99%

Raw High-Definition Radar for Multi-Task Learning

Rebut¹,

Ouaknine²,

Malik³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1: Overview of our RADIal dataset. RADIal includes a set of 3 sensors (camera, laser scanner, high-definition radar) and comes with GPS and vehicle's CAN traces; 25K synchronized samples are recorded in raw format. (a) Camera image with projected laser point cloud in red and radar point cloud in indigo, vehicle annotation in orange and free driving space annotation in green; (b) Radar power spectrum with bounding box annotations; (c) Free driving space annotation in bird-eye view, with annotated vehicle bounding boxes in orange, radar point cloud in indigo and laser point cloud in red; (d) Range-Azimuth map in Cartesian coordinates overlayed with radar point cloud and laser point cloud; (e) GPS trace in red and odometry trajectory reconstruction in green.

show abstract

“…By taking input as the dense radar spectra/images, recent works [10], [11] have shown the feasibility of place recognition based on mechanically spinning radar (e.g., CTS-350X). Despite the impressive performance achieved, spinning radar is known to be bulky and costly [12] and require to be mounted on the roof of the vehicle, nor able to provide the Doppler information. In contrast, automotive radar (aka.…”

Section: Introductionmentioning

confidence: 99%

AutoPlace: Robust Place Recognition with Single-chip Automotive Radar

Cai

Wang

2022

2022 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline that comprises (1) dynamic points removal from instant Doppler measurement, (2) spatial-temporal feature embedding on radar point clouds, and (3) retrieved candidates refinement from Radar Cross Section measurement. Extensive experimental results on the public nuScenes dataset demonstrate that existing visual/LiDAR/spinning radar place recognition approaches are less suitable for single-chip automotive radar. In contrast, our purpose-built approach for automotive radar consistently outperforms a variety of baseline methods via a comprehensive set of metrics, providing insights into the efficacy when used in a realistic system.

show abstract

RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications

Cited by 91 publications

References 18 publications

Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges

Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges

Raw High-Definition Radar for Multi-Task Learning

AutoPlace: Robust Place Recognition with Single-chip Automotive Radar

Contact Info

Product

Resources

About