Calibration of Non-overlapping Cameras Using an External SLAM System

Abstract

We present a simple method for calibrating a set of cameras that may not have overlapping field of views. We reduce the problem of calibrating the non-overlapping cameras to the problem of localizing the cameras with respect to a global 3D model reconstructed with a simultaneous localization and mapping (SLAM) system. Specifically, we first reconstruct such a global 3D model by using a SLAM system using an RGB-D sensor. We then perform localization and intrinsic parameter estimation for each camera by using 2D-3D correspondences between the camera and the 3D model. Our method locates the cameras within the 3D model, which is useful for visually inspecting camera poses and provides a model-guided browsing interface of the images. We demonstrate the advantages of our method using several indoor scenes. International Conference on 3D Vision (3DV)This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. Abstract-We present a simple method for calibrating a set of cameras that may not have overlapping field of views. We reduce the problem of calibrating the non-overlapping cameras to the problem of localizing the cameras with respect to a global 3D model reconstructed with a simultaneous localization and mapping (SLAM) system. Specifically, we first reconstruct such a global 3D model by using a SLAM system using an RGB-D sensor. We then perform localization and intrinsic parameter estimation for each camera by using 2D-3D correspondences between the camera and the 3D model. Our method locates the cameras within the 3D model, which is useful for visually inspecting camera poses and provides a model-guided browsing interface of the images. We demonstrate the advantages of our method using several indoor scenes.

Global calibration of non-overlapping cameras: State of the art

“…The experimental results show that the system achieves 0.1 mm measurement accuracy in the range of 1353 mm. Other works based on combined techniques are described in [91][92][93][94][95][96][97][98][99][100][101][102][103][104][105][106] to implement global calibration. Fig.…”

A Robust Extrinsic Calibration Framework for Vehicles with Unscaled Sensors

“…Ling and Shen achieve this for finding the offset between each sensor in a stereo camera [9]. For monocular cameras, Ataer-Cansizoglu et al exploit a previously generated SLAM model, where 2D-3D correspondences are formed from the images to find the global camera positions [10]. More closely related to our work is the approach of Maye et al , in which the self-calibration is online and robust to small motion [11].…”

Wide baseline pose estimation from video with a density-based uncertainty model

“…A second strategy which has gained popularity recently relies on the additional creation of a cartography of the surveyed environment using SLAM [1,18,48]. While this technique is the only way to register cameras with nonoverlapping fields of view (using visual information), it can also help in wide baseline scenarios as the pose estimation is reduced to two localization tasks within the cartography.…”

“…The full implementations of the pose estimation algorithm and of the variant for pose refinement are accessible online. 1…”