Next-generation automotive radars provide elevation data in addition to range-, azimuth- and Doppler velocity. In this experimental study, we apply a state-of-the-art object detector (PointPillars), previously used for LiDAR 3D data, such 3+1D radar (where 1D refers Doppler). ablation studies, first explore the benefits of additional information, together with that Doppler, cross section temporal accumulation, context multi-class road user detection. We subsequently compare detection...

This letter presents a novel radar based, single-frame, multi-class detection method for moving road users (pedestrian, cyclist, car), which utilizes low-level cube data. The provides class information both on the target- and object-level. Radar targets are classified individually after extending target features with cropped block of 3D around their positions, thereby capturing motion parts in local velocity distribution. A Convolutional Neural Network (CNN) is proposed this classification...

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such implicitly provides various forms of supervision cues radar estimation. Specifically, we introduce multi-task model architecture for identified learning problem and propose loss functions opportunistically engage using multiple constraints effective training. Extensive experiments show state-of-the-art...

Early and accurate detection of crossing pedestrians is crucial in automated driving order to perform timely emergency manoeuvres. However, this a difficult task urban scenarios where are often occluded (not visible) behind objects, e.g., other parked vehicles. We propose an occlusion aware fusion stereo camera radar sensors address with such Our proposed method adapts both the expected rate properties detections different areas according visibility sensors. In our experiments on real-world...

Early and accurate detection of crossing pedestrians is crucial in automated driving to execute emergency manoeuvres time. This a challenging task urban scenarios however, where people are often occluded (not visible) behind objects, e.g. other parked vehicles. In this paper, an occlusion aware multi-modal sensor fusion system proposed address with Our method adjusts the rate different areas based on visibility. We argue that using information can help evaluate measurements. experiments real...

Availability of datasets is a strong driver for research on 3D semantic understanding, and whilst obtaining unlabeled point cloud data straightforward, manually annotating this with labels time-consuming costly. Recently, Vision Foundation Models (VFMs) enable open-set segmentation camera images, potentially aiding automatic labeling. However,VFMs have been limited to adaptations 2D models, which can introduce inconsistencies labels. This work introduces Label Any Pointcloud (LeAP),...

In this paper, we address the limitations of traditional constant false alarm rate (CFAR) target detectors in automotive radars, particularly complex urban environments with multiple objects that appear as extended targets. We propose a data-driven radar detector exploiting highly efficient 2D CNN backbone inspired by computer vision domain. Our approach is distinguished unique cross-sensor supervision pipeline, enabling it to learn exclusively from unlabeled synchronized and lidar data,...

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such implicitly provides various forms of supervision cues radar estimation. Specifically, we introduce multi-task model architecture for identified learning problem and propose loss functions opportunistically engage using multiple constraints effective training. Extensive experiments show state-of-the-art...

In this paper, we address the limitations of traditional constant false alarm rate (CFAR) target detectors in automotive radars, particularly complex urban environments with multiple objects that appear as extended targets. We propose a data-driven radar detector exploiting highly efficient 2D CNN backbone inspired by computer vision domain. Our approach is distinguished unique cross sensor supervision pipeline, enabling it to learn exclusively from unlabeled synchronized and lidar data,...

The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors expensive, the performance radar-based is still inferior others. Camera-radar fusion methods have been proposed address this issue, but these constrained by typical sparsity radar point clouds often designed for radars without elevation information. We propose a novel camera-radar approach called Dual Perspective Fusion...

The detection of multiple extended targets in complex environments using high-resolution automotive radar is considered. A data-driven approach proposed where unlabeled synchronized lidar data used as ground truth to train a neural network with only input. To this end, the novel, large-scale, real-life, and multi-sensor RaDelft dataset has been recorded demonstrator vehicle different locations city Delft. dataset, well documentation example code, publicly available for those researchers...