@article{ZHANG2026, 
author = {Wei ZHANG and HaiFang WANG and XuGang DING and DiXin ZHAN},
title = {A monocular vision inertial localization system based on improved point-line feature extraction},
year = {2026},
journal = {Journal of Beijing University of Chemical Technology (Natural Science Edition)},
volume = {53},
number = {1},
pages = {115-124},
keywords = {monocular visual-inertial SLAM with efficient point-line flow features (EPLF-VINS), gradient threshold, EDLines, optical flow tracing, adaptive adjustment, ROS platform},
url = {https://www.sciopen.com/article/10.13543/j.bhxbzr.2026.01.011},
doi = {10.13543/j.bhxbzr.2026.01.011},
abstract = {To meet the requirements of positioning accuracy in the pose recognition process of the SLAM (simultaneous localization and mapping) algorithm based on point-line features, an improved EPLF-VINS (monocular visual-inertial SLAM with efficient point-line flow features) algorithm has been proposed. The influence of gradient threshold parameters on the EDLines (line segment detection by edge drawing) line segment extraction algorithm was first analyzed. Secondly, after forward optical flow tracing of point features, reverse optical flow tracing was used to eliminate the wrong tracking points, thereby improving the accuracy of optical flow tracing. Then, an adaptive adjustment algorithm was fused at the line segment extraction of the EPLF-VINS algorithm, and the gradient threshold parameters were adjusted in real time by calculating the success rate of point feature optical flow tracing after reverse optical flow tracing. This allows dynamic adjustment of line segment extraction based on changes in the environment, and results in a better balance of calculation cost and positioning accuracy. Finally, based on the Robot Operating System (ROS) platform, the trajectory accuracy and efficiency of the improved EPLF-VINS algorithm and the comparison algorithm in the EuRoc and TUM-VI datasets were analyzed. The results show that the trajectory curve generated by the improved EPLF-VINS algorithm more closely matches the real trajectory, and has higher positioning accuracy while maintaining real-time performance.}
}