Visual/inertial odometry with tight coupling of multi-bit pose information

Abstract

To address the problem that the loosely coupled frame pose scale needs to be initialized manually, making the subsequent algorithm less accurate and less real-time, while the tightly coupled OKVIS does not include closed-loop detection and map building, an adaptive vision/inertial odometry method with tightly coupled multi-bit pose information is proposed, incorporating optimized map points to provide more accurate data for the subsequent algorithm, with repositioning, closed-loop detection and global a complete visual/inertial odometry system with repositioning, closed-loop detection, and global posture map optimization functions. The adaptive vision/inertial odometry with tightly coupled multi-location posture information is experimentally validated to have better real-time performance, accuracy, and robustness than the loosely coupled algorithm.