TS-VINS: A Novel Visual-Inertial SLAM With Two-Stage Approach for Low-Texture Dynamic Environments

Most existing simultaneous localization and mapping (SLAM) algorithms demonstrate strong performance in static environments but encounter notable challenges in complex dynamic scenarios, particularly with camera rotation and objects moving along approximate epipolar lines. Moreover, dynamic environments with low texture further exacerbate positioning challenges. To address these issues, we propose TS-VINS, a novel visual-inertial SLAM framework. TS-VINS enhances feature point extraction and tracking through a well-designed mesh-based method and a feature point group (FPG)-based mistracking detector, ensuring stability even in low-texture scenes. Additionally, this method incorporates a two-stage dynamic feature recognition algorithm that uses geometric constraints to distinguish between static and dynamic objects. Extensive experiments on public datasets, including VIODE and KITTI, and real-world scenarios demonstrate that TS-VINS notably improves dynamic object recognition, system robustness, and trajectory accuracy, outperforming state-of-the-art SLAM systems in dynamic environments with low texture.