Spatiotemporal Calibration of Camera and 3D Laser Scanner

TL;DR

This paper introduces an open-source framework for spatiotemporal calibration of cameras and 3D laser scanners, enabling accurate, repeatable measurements in dynamic conditions through batch optimization and novel continuous plane representations.

Contribution

It presents a novel calibration method using batch optimization, B-splines, and Lie algebra for precise spatiotemporal alignment of camera and laser sensors.

Findings

Validated in simulation with high accuracy

Demonstrated on Velodyne VLP-16 and SICK MRS6124 scanners

Requires only one-minute calibration with chessboard markers

Abstract

The multi-sensory setups consisting of the laser scanners and cameras are popular as the measurements complement each other and provide necessary robustness for applications. Under dynamic conditions or when in motion, a direct transformation (spatial calibration) and time offset between sensors (temporal calibration) is needed to determine the correspondence between measurements. We propose an open-source spatiotemporal calibration framework for a camera and a 3D laser scanner. Our solution is based on commonly available chessboard markers requiring one-minute calibration before the operation that offers accurate and repeatable results. The framework is based on batch optimization of point-to-plane constraints with a time offset calibration possible by a novel continuous representation of the plane equations based on a minimal representation in the Lie algebra and the use of B-splines. The framework's properties are evaluated in simulation while correctness is verified with two distinct sensory setups with Velodyne VLP-16 and SICK MRS6124 3D laser scanners.