Robust Photogeometric Localization over Time for Map-Centric Loop Closure

Select | Print


Park, Chanoh; Kim, Soohwan; Moghadam, Peyman; Guo, JD; Sridharan, Sridha; Fookes, Clinton


2019-04-01


Journal Article


IEEE Robotics and Automation Letters (RA-L)


4


2


1768-1775


Map-centric SLAM is emerging as an alterna- tive of conventional graph-based SLAM for its accuracy and efficiency in long-term mapping problems. However, in map- centric SLAM, the process of loop closure differs from that of conventional SLAM and the result of incorrect loop closure is more destructive and is not reversible. In this paper, we present a tightly coupled vision-LiDAR based pose estimation for the loop closure problem for map-centric SLAM. In particular, our method combines complementary constraints from LiDAR and camera sensors, and validates loop closure candidates with sequential observations. The proposed method provides a visual evidence-based outlier rejection where failures caused by either place recognition or localization outliers can be effectively detected. We demonstrate that the proposed method is not only as accurate as the conventional global ICP methods but is also robust to incorrect initial pose guesses.


IEEE


SLAM; Map-Centric; loop closure; metric localisation


Autonomous Vehicles; Computer Vision; Information Systems not elsewhere classified


https://doi.org/10.1109/LRA.2019.2895262


Link to Publisher's Version


EP188606


Journal article - Refereed


English


Park, Chanoh; Kim, Soohwan; Moghadam, Peyman; Guo, JD; Sridharan, Sridha; Fookes, Clinton. Robust Photogeometric Localization over Time for Map-Centric Loop Closure. IEEE Robotics and Automation Letters (RA-L). 2019; 4(2):1768-1775. https://doi.org/10.1109/LRA.2019.2895262



Loading citation data...

Citation counts
(Requires subscription to view)