Learning-based monocular visual-inertial odometry with S E 2 ( 3 ) $S{E}_{2}(3)$ -EKF

Abstract

Learning-based visual odometry (VO) becomes popular as it achieves a remarkable performance without manually crafted image processing and burdensome calibration. Meanwhile, the inertial navigation can provide a localization solution to assist VO when the VO produces poor state estimation under challenging visual conditions. Therefore, the combination of learning-based technique and classical state estimation method can further improve the performance of pose estimation. In this paper, we propose a learning-based visual-inertial odometry (VIO) algorithm, which consists of an end-to-end VO network and an $S{E}_2\left(3\right)$-Extended Kalman Filter (EKF). The VO network mainly combines a convolutional neural network with a recurrent neural network, taking advantage of two consecutive monocular images to produce relative pose estimation with associated uncertainties. The $S{E}_2\left(3\right)$-EKF, which is proved to overcome the inconsistency issues of VIO, propagates inertial measurement unit kinematics-based states, and fuses relative measurements and uncertainties from the VO network in its update step. The extensive experimental results on the KITTI data set and the EuRoC data set demonstrate the superior performance of the proposed method compared to other related methods.