Cubic B-Spline-Based Feature Tracking for Visual-Inertial Odometry With Event Camera

It is challenging to obtain accurate trajectories with standard camera visual odometry (VO) in environments with weak textures and light variations. This article introduces a novel approach [cubic B-spline-based visual-inertial odometry (CB-VIO)], using the dynamic and active-pixel vision sensor (DAVIS) camera. In the proposed CB-VIO method, the matching mechanism between images and events is designed to improve the success rate of event tracking, based on which the template points from events are utilized to construct a cubic B-spline based event tracking model within a continuous spatiotemporal window [under SE(3)]. Based on the tracking model to interpolate poses at any time point, the inertial measurement unit (IMU) measurement model is constructed to achieve data fusion from asynchronous and synchronous sensors with different rates. Compared with the Spline-visual-inertial odometry (VIO) and the event-based VO (EVO), the proposed continuous spatiotemporal window method can effectively solve the data association for EVO and the continuous-time trajectory with fixed-time intervals for Spline-VIO. The experimental results are compared on public datasets of multiple different scenes, which demonstrate the superior performance of CB-VIO in terms of accuracy and robustness (translation error <= 1.3% and rotation error <= 2(degrees)).