Display screens enable faster LiDAR camera alignment with improved accuracy
Can a Display Be Used for Rapid LiDAR-Camera Extrinsic Calibration?
Computer Vision and Pattern Recognition
Summary
Calibrating the position and angle between a LiDAR sensor and a camera is usually tricky and requires special targets. The authors show that an ordinary screen displaying simple visual markers can be used instead. This helps the camera see known patterns while the LiDAR senses the screen's edges, letting the system figure out the precise relationship between the two devices more easily. Their method works well even in cluttered indoor spaces and with different devices like phones or monitors.
What this means in practice
- •For autonomous vehicle engineers: Calibrate LiDAR and camera sensors more quickly and accurately on vehicles using standard screens instead of specialized targets.
- •For robotics system integrators: Use portable screens to perform sensor calibration on robots in varied environments without lengthy setup or dedicated calibration boards.
- •For smartphone camera manufacturers: Improve in-factory calibration of LiDAR-camera modules using existing device displays to streamline production and testing.$Commercial implications: Enables integrating calibration directly into devices, reducing specialized hardware and speeding up manufacturing.
Authors
Zuhao Zou, Xiangcheng Hu, Jianhao Jiao, Jin Wu
Abstract
ScreenCalib enables light detection and ranging (LiDAR)--camera extrinsic calibration using an ordinary programmable display, providing known visual markers and controlled geometry while reducing dedicated target preparation. The camera observes displayed AprilTags, whereas the LiDAR measures the physical screen surface and boundary, requiring indirect cross-modal association. Display geometry introduces association ambiguities, while indoor clutter complicates extraction. ScreenCalib addresses these challenges through tag-guided display extraction, geometric hypothesis generation and refinement, and surrounding scene edges for ambiguity resolution. The single-pose mode requires only one static placement. The joint multi-pose mode combines independent static observations through cross-pose consensus and jointly refines the shared extrinsics and tag scale, reducing sensitivity to tag-size measurement errors without requiring continuous motion or inter-pose trajectory estimation. Experiments in simulation and on three different sensor platforms cover mechanical and nonrepetitive LiDARs in clean and cluttered environments. Benchmark results show that ScreenCalib outperforms competitive calibration-board-based methods in translation accuracy. Joint multi-pose refinement further reduces mean rotation and translation errors across the three platforms and improves rendered-map alignment. Evaluation across readily available displays, including cell phones, tablets, laptops, computer monitors, and televisions, further examines ScreenCalib's versatility as a practical alternative to dedicated calibration targets. The source code is available at https://github.com/ZuhaoZou2026/ScreenCalib.