Heterogeneous Multi-sensor Calibration based on Graph Optimization

TL;DR

This paper introduces a graph optimization method for multi-sensor calibration in robotics, improving the accuracy of extrinsic parameter estimation across diverse sensors like cameras and lidars.

Contribution

It presents a novel graph-based calibration approach that refines relative sensor poses, addressing inconsistencies in multi-sensor calibration results.

Findings

The method achieves high calibration accuracy on a twelve-sensor robotic platform.

Experimental results demonstrate significant performance improvements.

The approach effectively refines initial calibration estimates.

Abstract

Many robotics and mapping systems contain multiple sensors to perceive the environment. Extrinsic parameter calibration, the identification of the position and rotation transform between the frames of the different sensors, is critical to fuse data from different sensors. When obtaining multiple camera to camera, lidar to camera and lidar to lidar calibration results, inconsistencies are likely. We propose a graph-based method to refine the relative poses of the different sensors. We demonstrate our approach using our mapping robot platform, which features twelve sensors that are to be calibrated. The experimental results confirm that the proposed algorithm yields great performance.