Abstract
Feature matching is an important step for SLAM with high real-time requirements. Currently, most feature matching methods only rely on visual information, even in visual-inertial SLAM. In this paper, we propose an efficient feature matching method for point and line features by fusing IMU information with visual information. The key ideas are utilizing IMU pre-integration to estimate the relative pose change of two consecutive frames and narrow the feature search area to accelerate feature matching. Experiment results show that our method shortens the feature matching time significantly compared with other feature matching methods while ensuring high matching accuracy.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
