CoVeRaP: Cooperative Vehicular Perception through mmWave FMCW Radars

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Jinyue, Ku, Hansol, Vora, Jayneel, Lee, Nelson, Kamari, Ahmad, Mohapatra, Prasant, Pathak, Parth
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918128919773184
author Song, Jinyue
Ku, Hansol
Vora, Jayneel
Lee, Nelson
Kamari, Ahmad
Mohapatra, Prasant
Pathak, Parth
author_facet Song, Jinyue
Ku, Hansol
Vora, Jayneel
Lee, Nelson
Kamari, Ahmad
Mohapatra, Prasant
Pathak, Parth
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoVeRaP: Cooperative Vehicular Perception through mmWave FMCW Radars
Song, Jinyue
Ku, Hansol
Vora, Jayneel
Lee, Nelson
Kamari, Ahmad
Mohapatra, Prasant
Pathak, Parth
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Networking and Internet Architecture
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.
title CoVeRaP: Cooperative Vehicular Perception through mmWave FMCW Radars
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2508.16030