PLE-SLAM: A Visual-Inertial SLAM Based on Point-Line Features and Efficient IMU Initialization

Abstract

Camera and IMU are widely used in robotics to achieve accurate and robust pose estimation. However, this fusion relies heavily on sufficient visual feature observations and precise inertial state variables. This article proposes PLE-SLAM, a real-time visual-inertial simultaneous localization and mapping (SLAM) for complex environments, which introduces line features to point-based SLAM and proposes an efficient IMU initialization method. First, we use parallel computing methods to extract point-line features and compute descriptors to ensure real-time performance. Adjacent short-line segments are merged into long-line segments for more stable tracking, and isolated short-line segments are directly eliminated. Second, to overcome rapid rotation and low-texture scenes, we estimate gyroscope bias by tightly coupling rotation preintegration and 2-D point-line observations without 3-D point cloud and vision-only rotation estimation. Accelerometer bias and gravity direction are solved by an analytical method, which is more efficient than nonlinear optimization. To improve the system’s robustness in complex environments, an improved method of dynamic feature elimination and a solution for loop detection and loop frames pose estimation using CNN and GNN are integrated into the system. The experimental results on public datasets demonstrate that PLE-SLAM achieves more than 20%~50% improvement in localization performance than ORB-SLAM3 and outperforms other state-of-the-art visual-inertial SLAM systems in most environments.