Automatic camera and range sensor calibration using a single shot

TLDR

Camera and range sensor calibration is a core robotic vision problem that has been extensively studied, yet practical deployments still suffer delays from the need to set up calibrated multi‑sensor systems. This work introduces a web‑based toolbox that performs fully automatic camera‑to‑camera and camera‑to‑range calibration, eliminating the manual setup burden. The toolbox automatically recovers intrinsic and extrinsic camera parameters and the camera‑to‑sensor transformation within one minute from a single image and range scan, and is robust to varying imaging conditions without user intervention. Experiments show that the checkerboard corner detector outperforms state‑of‑the‑art methods, the camera‑to‑range registration can resolve multiple solutions in ambiguous cases, and the approach remains robust across diverse indoor and outdoor sensors and lighting conditions.

Abstract

As a core robotic and vision problem, camera and range sensor calibration have been researched intensely over the last decades. However, robotic research efforts still often get heavily delayed by the requirement of setting up a calibrated system consisting of multiple cameras and range measurement units. With regard to removing this burden, we present a toolbox with web interface for fully automatic camera-to-camera and camera-to-range calibration. Our system is easy to setup and recovers intrinsic and extrinsic camera parameters as well as the transformation between cameras and range sensors within one minute. In contrast to existing calibration approaches, which often require user intervention, the proposed method is robust to varying imaging conditions, fully automatic, and easy to use since a single image and range scan proves sufficient for most calibration scenarios. Experimentally, we demonstrate that the proposed checkerboard corner detector significantly outperforms current state-of-the-art. Furthermore, the proposed camera-to-range registration method is able to discover multiple solutions in the case of ambiguities. Experiments using a variety of sensors such as grayscale and color cameras, the Kinect 3D sensor and the Velodyne HDL-64 laser scanner show the robustness of our method in different indoor and outdoor settings and under various lighting conditions.