InfraDet3D: Multi-Modal 3D Object Detection based on Roadside Infrastructure Camera and LiDAR Sensors

TL;DR

InfraDet3D introduces a multi-modal 3D object detection system for roadside infrastructure that fuses LiDARs and cameras, enhancing perception range and accuracy for traffic monitoring and autonomous driving safety.

Contribution

The paper presents a novel roadside perception framework combining LiDAR and camera data with HD map grounding, improving detection robustness and small object detection.

Findings

Fusing two LiDARs with two cameras improves mAP by +1.90 over camera-only methods.

Achieved 68.48 mAP on the A9 infrastructure dataset.

Deployed and tested on a real-world intersection in Munich, demonstrating practical effectiveness.

Abstract

Current multi-modal object detection approaches focus on the vehicle domain and are limited in the perception range and the processing capabilities. Roadside sensor units (RSUs) introduce a new domain for perception systems and leverage altitude to observe traffic. Cameras and LiDARs mounted on gantry bridges increase the perception range and produce a full digital twin of the traffic. In this work, we introduce InfraDet3D, a multi-modal 3D object detector for roadside infrastructure sensors. We fuse two LiDARs using early fusion and further incorporate detections from monocular cameras to increase the robustness and to detect small objects. Our monocular 3D detection module uses HD maps to ground object yaw hypotheses, improving the final perception results. The perception framework is deployed on a real-world intersection that is part of the A9 Test Stretch in Munich, Germany. We perform several ablation studies and experiments and show that fusing two LiDARs with two cameras leads to an improvement of +1.90 mAP compared to a camera-only solution. We evaluate our results on the A9 infrastructure dataset and achieve 68.48 mAP on the test set. The dataset and code will be available at https://a9-dataset.com to allow the research community to further improve the perception results and make autonomous driving safer.