Monocular Visual Odometry Initialization With Points and Line Segments

Abstract

Conventional initialization algorithms for feature-based monocular visual simultaneous localization and mapping (V-SLAM)/visual odometry (VO) systems used point-based matrix decomposition. However, line segments are common in urban scenes and provide valuable information about scene structure. In this paper, we propose incorporating line segments for initializing, which allows obtaining accurate initial camera poses and generate reliable 3D line segment landmarks as well as point landmarks. The proposed algorithm, denoted as PLSfSM (point and line structure from small motion), employs both point and Pl $\ddot {u}$ cker line reprojection constraints to recover structure from small motion. In particular, we propose a closed-form solution to estimate rotation and optimize rotation with line segment correspondences, which provides good initial guesses for rotation and line directions. Mathematically proven criteria are introduced to detect degeneracy of line reconstruction. The algorithm is evaluated on synthetic indoor dataset and simulation data. The qualitative experiments on both indoor and outdoor scenes are conducted to verify the robustness. The experimental results validate that the proposed algorithm, which combines both points and line segments for initialization, outperforms the state-of-the-art methods which only use points for initialization.