CAR-LOAM: Color-Assisted Robust LiDAR Odometry and Mapping

TL;DR

This paper introduces CAR-LOAM, a color-assisted LiDAR odometry and mapping framework that enhances accuracy and robustness by integrating camera color data with LiDAR scans for improved localization and 3D map reconstruction.

Contribution

It presents a novel framework that combines camera color information with LiDAR data, employing robust outlier rejection and optimization techniques for improved odometry and mapping.

Findings

Achieves higher robustness and accuracy than state-of-the-art methods.

Successfully reconstructs dense, colored 3D maps.

Performs well in challenging environments like forests and campuses.

Abstract

In this letter, we propose a color-assisted robust framework for accurate LiDAR odometry and mapping (LOAM). Simultaneously receiving data from both the LiDAR and the camera, the framework utilizes the color information from the camera images to colorize the LiDAR point clouds and then performs iterative pose optimization. For each LiDAR scan, the edge and planar features are extracted and colored using the corresponding image and then matched to a global map. Specifically, we adopt a perceptually uniform color difference weighting strategy to exclude color correspondence outliers and a robust error metric based on the Welsch's function to mitigate the impact of positional correspondence outliers during the pose optimization process. As a result, the system achieves accurate localization and reconstructs dense, accurate, colored and three-dimensional (3D) maps of the environment. Thorough experiments with challenging scenarios, including complex forests and a campus, show that our method provides higher robustness and accuracy compared with current state-of-the-art methods.