用路边 RGB 相机与 3D 雷达实现资源高效的道路使用者 3D 形状与朝向估计

View PDF HTML (experimental)

Abstract:End-to-end deep learning pipelines for camera-radar 3D object detection are well established in driver assistance systems and autonomous vehicles; however, adapting them to roadside-mounted infrastructure presents significant challenges. On vehicles, sensor heights, pitch angles, and relative geometries remain largely uniform, allowing end-to-end models to generalize effectively. On the contrary, roadside sensor installations vary drastically in height, tilt, and field of view across locations, rendering end-to-end models prone to failure and difficult to adapt without massive location-specific datasets. Hence, instead of designing a complex end-to-end pipeline for direct 3D bounding box estimation, a low-cost, resource-efficient two-stage approach is proposed for real-time 3D shape and orientation estimation. The first stage utilizes any off-the-shelf, state-of-the-art method to extract 2D camera bounding boxes and associated 3D radar points for each road user. The proposed second stage then processes these inputs to construct 3D oriented bounding boxes where radar data determines 3D position, predefined templates define size for each road user, and a tiny neural network predicts a site-specific and optimized yaw angle. The algorithm is successfully validated at a curved road with a junction for pedestrians, bicycles, and cars, where it achieves 25 frames per second on an NVIDIA Jetson ORIN for real-time applications.

Comments:	Accepted at the 18th IEEE Symposium Sensor Data Fusion: Trends, Solutions and Applications (SDF 2026), Bonn, Germany
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.18417 [cs.CV]
	(or arXiv:2610.18417v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.18417 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Shiva Agrawal [view email]
[v1] Tue, 13 Oct 2026 13:58:01 UTC (3,568 KB)