Увійти
ідея - Visual-Inertial Odometry
Fast Multi-State Constraint Kalman Filter for Improved Visual-Inertial Odometry
This paper introduces a faster and more accurate version of the Multi-State Constraint Kalman Filter (MSCKF) for visual-inertial odometry, called FMSCKF, which strategically manages feature extraction and state pruning to reduce computational cost without sacrificing accuracy.
DynaVINS++: Enhancing Visual-Inertial State Estimation in Dynamic Environments Using Adaptive Truncated Least Squares and Stable State Recovery
DynaVINS++ improves the robustness of visual-inertial state estimation in dynamic environments, particularly addressing challenges posed by abruptly dynamic objects, by introducing Adaptive Truncated Least Squares for outlier rejection and a Stable State Recovery mechanism based on bias consistency checks.
Продукти
© 2024 by Linnk AI