Calibration-Informative Region Selection for Online LiDAR--Camera Calibration in Agricultural Environments
For autonomous systems operating in agricultural environments, this work addresses the problem of unreliable calibration by filtering noisy observations, but the improvements are incremental and domain-specific.
The paper proposes a support-map-driven approach for online LiDAR-camera calibration that identifies which observations reliably constrain extrinsic parameters. On KITTI, support-guided refinement improves translation accuracy, though rotational gains are limited.
Reliable multi-modal calibration requires identifying which observations truly constrain the extrinsic parameters and which ones mainly add noise or ambiguity. In this paper, we propose a support-map-driven approach to multi-modal calibration that decouples four functional blocks: initial calibration, cross-modal residual extraction, support-map estimation, and support-aware refinement. We instantiate this formulation for online LiDAR--camera calibration using MDPCalib, a target-less LiDAR--camera calibration method based on motion and deep point correspondences, and CMRNext, a dense LiDAR--camera matching model that predicts optical-flow-like image-plane residuals. The key contribution is a dense calibration support map that aggregates cross-modal agreement over aligned observations and highlights where calibration evidence is consistently reliable. Across the Bacchus Long-Term (BLT) dataset and KITTI, we show that calibration evidence is spatially and semantically non-uniform, indicating that some semantic regions provide stronger cues for calibration than others. On KITTI, support-guided refinement improves the calibration performance with better translation accuracy while rotational gains remain limited.