Extrinsic Calibration of Multiple RGB-D Cameras Based on Descriptor-based Patterns

07/14/2018

∙

by   Hang Liu, et al.

∙

0

∙

share

This letter presents a novel method to estimate the relative poses between RGB-D cameras with minimal overlapping fields of view in a panoramic RGB-D camera system. This calibration problem is relevant to applications such as indoor 3D mapping and robots navigation that can benefit from a 360^∘ field of view using RGB-D cameras. The proposed approach relies on descriptor-based patterns to provide well-matched 2D keypoints in the case of a minimal overlapping field of view between cameras. Integrating the matched 2D keypoints with corresponding depth values, a set of 3D matched keypoints are constructed to calibrate multiple RGB-D cameras. Experiments validate the accuracy and efficiency of the proposed calibration approach.