Monocular visual-inertial SLAM with IMU-aided point-line flow matching

As robotics advances, visual SLAM technology gains traction. Monocular inertial SLAM is notable for its affordability and real-time capabilities. Researchers introduce line features to enhance traditional point-based SLAM in scenarios like weak textures or motion blur. However, mainstream methods, combining LSD and LBD, suffer from high computational demands, impacting real-time robot localization. To address this, we propose a monocular inertial SLAM method using enhanced ELSED and imu-aided line optical flow. We replace LSD with improved ELSED, boosting line feature extraction speed. Additionally, our imu-aided approach enhances line feature tracking accuracy and matching precision. Comparative experiments with mainstream methods validate the effectiveness of the proposed method.