http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
PLI-VIO: Real-time Monocular Visual-inertial Odometry Using Point and Line Interrelated Features
Jiahui Zhang,Qingzhen Shang,Jinfu Yang,Mingai Li 제어·로봇·시스템학회 2023 International Journal of Control, Automation, and Vol.21 No.6
As a popular technology, visual-inertial odometry (VIO) has been widely applied in many fields such as autonomous robots and unmanned aerial vehicle (UAV). However, the trade-off between localization accuracy and real-time performance still needs to be optimized. This paper presents a real-time tightly-coupled monocular VIO system using point and line interrelated features (PLI-VIO) under the sliding window optimization framework. In line feature extraction part of PLI-VIO, a line segment extraction and coalescence algorithm based on EDlines is proposed, which extracts line features in real-time without concession on feature quality. At the same time, in order to get efficient and robust line tracking effect, PLI-VIO presents a line-to-point tracking method that fully utilizes the interrelation between point and line. Specifically, line features are divided as a group of points and tracked by pyramidal implementation of Lucas Kanade feature tracker. The proposed line feature tracking method can effectively reduce time consumption on tracking process in a robust way. Extensive evaluations on Euroc and TUM-VI public datasets are performed to demonstrate the preferable performance of our proposed system, and the results show that PLI-VIO obtains better localization accuracy with less computation cost compared against other state-of-the-art VIO algorithms.