Radar LiDAR and camera sensors calibrated together without targets online
Online Target-less Radar-LiDAR-Camera Extrinsic Calibration via Joint Optimization
Robotics
Summary
Combining radar, LiDAR, and camera sensors helps machines see better in tough conditions, but to work well, these sensors must be perfectly aligned. The authors address the challenge of calibrating all three sensors together in real time without using special targets. They developed a method that optimizes calibration by considering all sensor pairs jointly, filtering out unreliable radar data, and collecting radar information over time. Their tests show this approach improves alignment accuracy over previous methods that focus only on camera and LiDAR.
What this means in practice
- •For autonomous vehicle engineers: Improve real-time sensor alignment for vehicles using radar, LiDAR, and cameras simultaneously without special calibration targets.
- •For robotics system integrators: Enable joint calibration of multiple sensor types in robots operating in dynamic environments to enhance perception accuracy and reliability.
Authors
Gunhee Shin, Yunsoo Kim, Chanhyuk Lee, Wanhee Kim, Minwoo Lee, Sungwoo Han, Jeongwoo Woo, Hyuntai Chin, Minha Park, Hyun Myung
Abstract
Fusing radar, LiDAR, and camera enables robust perception in diverse and adverse conditions, but the fusion performance critically depends on accurate extrinsic calibration among the three sensors. In this paper, we address the problem of online target-less extrinsic calibration for the radar-LiDAR-camera system. Existing target-less methods are mostly designed for a single sensor pair, and composing the pairwise results does not guarantee consistency across the three sensors. Moreover, the sparse and noisy radar measurements make the radar-involving pairs unreliable. To tackle these challenges, we propose a joint calibration framework that constructs residuals for each sensor pair and optimizes the extrinsics of all pairs together to minimize the overall residual. Furthermore, we introduce an adaptive radar noise filter that rejects spurious radar returns using a range-dependent margin, and a correspondence accumulation strategy that aggregates sparse radar correspondences over frames. We validate our method on an in-house radar-LiDAR-camera dataset covering diverse urban environments, where it reduces calibration errors across all sensor pairs over a state-of-the-art camera-LiDAR baseline.