Robust visual SLAM with point and line features

In this paper, we develop a robust efficient visual SLAM system that utilizes heterogeneous point and line features. By leveraging ORB-SLAM [1], the proposed system consists of stereo matching, frame tracking, local mapping, loop detection, and bundle adjustment of both point and line features. In particular, as the main theoretical contributions of this paper, we, for the first time, employ the orthonormal representation as the minimal parameterization to model line features along with point features in visual SLAM and analytically derive the Jacobians of the re-projection errors with respect to the line parameters, which significantly improves the SLAM solution. The proposed SLAM has been extensively tested in both synthetic and real-world experiments whose results demonstrate that the proposed system outperforms the state-of-the-art methods in various scenarios.

I. Introduction

Visual SLAM (V-SLAM) is one of enabling technologies for autonomous systems such as self-driving cars, unmanned aerial vehicles and space robots. While most V-SLAM solutions rely on point features due to their simplicity, line features commonly seen in man-made environments are less sensitive to lighting variation and position ambiguity and have been only used in recent work [2]–[8]. In principle, the combination of point and line features would provide more geometric constraints about the structure of the environment than either one, which motivates us to design robust V-SLAM with point and line features.