Bi-directional Optical Flow-based Feature Point Tracking Method

Abstract

In order to improve the robustness of the SLAM system based on the optical flow method, we propose a feature point tracking method with a bi-directional optical flow. The method first couples the forward LK optical flow and the reverse LK optical flow. Then, the feature points are screened and tracked by coupling the bidirectional optical flow. If the screened feature points do not reach the set threshold, they can be supplemented with either Fast points or Harris points. The experimental validation of the above method by VINS-Mono with the EuRoC dataset shows that VINS-Mono using this method significantly improves the accuracy of localization without increasing the running time cost compared with the original VINS-Mono.