CoVeRaP: Cooperative Vehicular Perception through mmWave FMCW Radars
This work addresses the challenge of robust perception in adverse conditions like rain and glare for autonomous vehicles, though it is incremental as it builds on existing radar and fusion methods.
The paper tackles the problem of 3-D object detection using sparse, noisy point clouds from automotive FMCW radars by introducing CoVeRaP, a cooperative dataset and framework that fuses data from multiple vehicles. It shows that middle fusion with intensity encoding increases mean Average Precision by up to 9x at IoU 0.9 compared to single-vehicle baselines.
Automotive FMCW radars remain reliable in rain and glare, yet their sparse, noisy point clouds constrain 3-D object detection. We therefore release CoVeRaP, a 21 k-frame cooperative dataset that time-aligns radar, camera, and GPS streams from multiple vehicles across diverse manoeuvres. Built on this data, we propose a unified cooperative-perception framework with middle- and late-fusion options. Its baseline network employs a multi-branch PointNet-style encoder enhanced with self-attention to fuse spatial, Doppler, and intensity cues into a common latent space, which a decoder converts into 3-D bounding boxes and per-point depth confidence. Experiments show that middle fusion with intensity encoding boosts mean Average Precision by up to 9x at IoU 0.9 and consistently outperforms single-vehicle baselines. CoVeRaP thus establishes the first reproducible benchmark for multi-vehicle FMCW-radar perception and demonstrates that affordable radar sharing markedly improves detection robustness. Dataset and code are publicly available to encourage further research.