Raw High-Definition Radar for Multi-Task Learning

Abstract

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.

Sensing and Machine Learning for Automotive Perception: A Review

“…4) datasets used mechanically scanning FMCW radar to get sub-1 cir c angular resolution for BEV radar images but without the Doppler velocity information. More recent efforts focus on the radar heatmap in RD, rangeangle (RA), and RA-Doppler (RAD) domains [54], [55], [56], [57], [58]. For instance, the CARRADA dataset provides three (RA, RD, and RAD) heatmaps on a scenario of test tracks [54].…”

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

“…Different classes are equally distributed (21.6% pedestrians, 8.8% cyclists, and 21.9% cars). The RADIal dataset [51] is a 4D radar dataset for vehicle detection and open space segmentation. The sensors include camera, LiDAR, 4D radar, GPS.…”

“…They argued that phase normalisation is crucial for successful training. Rebut et al [51] designed a DDM-MIMO encoder with a complex RD map as the input. In the DDM configuration, as illustrated in Figure 3, all Tx antennas transmit signals at the same time.…”