ThermRad: A Multi-modal Dataset for Robust 3D Object Detection under Challenging Conditions
Qiao Yan, Yihan Wang

TL;DR
ThermRad introduces a novel multi-modal dataset with radar, thermal, LiDAR, and camera data captured in extreme weather, alongside a fusion method that significantly improves 3D object detection robustness under challenging conditions.
Contribution
The paper presents the first multi-modal dataset combining radar, thermal, LiDAR, and camera data in extreme weather, and proposes a fusion method that enhances detection accuracy in adverse conditions.
Findings
Detection improvements over 7.98% for cars
Over 24% improvement for pedestrians
Over 27% enhancement for cyclists
Abstract
Robust 3D object detection in extreme weather and illumination conditions is a challenging task. While radars and thermal cameras are known for their resilience to these conditions, few studies have been conducted on radar-thermal fusion due to the lack of corresponding datasets. To address this gap, we first present a new multi-modal dataset called ThermRad, which includes a 3D LiDAR, a 4D radar, an RGB camera and a thermal camera. This dataset is unique because it includes data from all four sensors in extreme weather conditions, providing a valuable resource for future research in this area. To validate the robustness of 4D radars and thermal cameras for 3D object detection in challenging weather conditions, we propose a new multi-modal fusion method called RTDF-RCNN, which leverages the complementary strengths of 4D radars and thermal cameras to boost object detection performance.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced SAR Imaging Techniques · Advanced Neural Network Applications · Thermal Regulation in Medicine
