TC-LEC: Targetless Calibration for LiDAR-Event Camera Systems
Ying Yang, Jianing Li, Jiangming Shi, Yanyun Qu
AI summary
Problem
Existing calibration methods for LiDAR-event camera systems rely on physical targets or controlled lighting, making them inflexible and impractical for dynamic real-world deployment. Current targetless approaches often require strict hardware synchronization or precise initial alignment, limiting their robustness.
Approach
The method estimates camera angular velocity directly from asynchronous event streams to extract natural edges, then uses Canonical Correlation Analysis on rotational cues to jointly recover temporal offset and initial rotation. This coarse alignment is refined through nonlinear optimization that matches natural edge features across both modalities.
Key results
- Eliminates reliance on dedicated calibration targets and tight hardware synchronization
- Achieves 0.67 cm translation and 0.12° rotation error on the DSEC dataset
- Demonstrates robust convergence across diverse initial values and environmental conditions
- Outperforms or matches state-of-the-art methods in accuracy and deployment flexibility
Why it matters
Enables robust, high-precision sensor fusion for autonomous navigation and perception systems in complex, unstructured environments where traditional calibration is infeasible.
Abstract
LiDAR-event camera integration has shown con- siderable promise and is gaining traction across various perception applications. Event cameras offer high temporal resolution and wide dynamic range but suffer from noise sensitivity and lack depth information. LiDAR complements these capabilities by providing absolute scale and robustness, yet accurate calibration between the two sensors remains a significant challenge. This paper presents targetless calibration framework for LiDAR–event camera systems that removes dependence on dedicated calibration targets and strong initial assumptions. The method estimates the event camera angular velocity by analyzing the timestamp and spatial changes of per- pixel, enabling precise detection of natural edges. Calibration proceeds in two stages: (i) motion-based initialization, where Canonical Correlation Analysis (CCA) on rotational estimates from the event camera and LiDAR jointly recovers the temporal offset and rotation; (ii) nonlinear refinement of the extrinsics via cross-modal alignment of natural edge features. Experiments on physical platforms and public datasets demonstrate robust performance and high calibration accuracy across diverse scenarios. This work provides a solid foundation for further development and application of LiDAR-event camera fusion.