Augmented Feature Point Initialization Method for Vision/Lidar Aided 6-DoF Bearing-Only Inertial SLAM

Abstract

-This study proposes a novel feature point initialization method in order to improve the accuracy of feature point positions by fusing a vision sensor and a lidar. The initialization is a process that determines three dimensional positions of feature points through two dimensional image data, which has a direct influence on performance of a 6-DoF bearing-only SLAM. Prior to the initialization, an extrinsic calibration method which estimates rotational and translational relationships between a vision sensor and lidar using multiple calibration tools was employed, then the feature point initialization method based on the estimated extrinsic calibration parameters was presented. In this process, in order to improve performance of the accuracy of the initialized feature points, an iterative automatic scaling parameter tuning technique was presented. The validity of the proposed feature point initialization method was verified in a 6-DoF bearing-only SLAM framework through an indoor and outdoor tests that compare estimation performance with the previous initialization method.

SLAM Overview: From Single Sensor to Heterogeneous Fusion

“…However, errors are prone to occur in pure rotational motion and cases of a lack of texture or extreme discontinuities due to the reliance on SFM methods and local dense reconstruction. Aiming at this problem, S. Yun et al [185] proposed a new method that uses 2D image data to determine the 3D position of feature points. The feature point localization process involves a combination of visual sensors and LIDAR and uses iterative automatic scaling parameter adjustment technology.…”