Most SLAM (Simultaneous Localization and Mapping) algorithms are based on the assumption that the scene is static. However, in practice, most real scenes usually contain moving objects. In this letter, we introduce DymSLAM, a dynamic stereo visual SLAM system being capable of reconstructing a 4D (3D + time) dynamic scene with rigid moving objects. Unlike previous attempts that have considered moving objects as outliers and ignored them, DymSLAM obtains the 6DoF motion trajectory and 3D models about the dynamic objects. We segment motion models of different moving objects by a multi-motion segmentation approach and obtain the accurate masks of moving objects. Besides ego-motion, our system can obtain the 4D (3D + time) model and 6DoF trajectory of the moving object in the global reference frame while simultaneously reconstructing the dense map of the static background. Meanwhile, DymSLAM does not rely on semantic cues or prior knowledge and is suitable for unknown rigid objects. We conducted experiments in a real-world indoor environment where both the camera and the objects were moving in a wide range. The results proved that our proposed method is a state-of-the-art SLAM system for use in this dynamic environment.

中文翻译：

---

DymSLAM：基于几何运动分割的4D动态场景重建

大多数 SLAM（同步定位和映射）算法都基于场景是静态的假设。然而，在实践中，大多数真实场景通常包含移动物体。在这封信中，我们介绍了 DymSLAM，这是一种动态立体视觉 SLAM 系统，能够重建具有刚性运动物体的 4D（3D + 时间）动态场景。与之前将移动物体视为异常值并忽略它们的尝试不同，DymSLAM 获得了关于动态物体的 6DoF 运动轨迹和 3D 模型。我们通过多运动分割方法分割不同运动物体的运动模型，并获得运动物体的准确掩码。除了自我运动，我们的系统可以在全局参考系中获得运动物体的 4D（3D + 时间）模型和 6DoF 轨迹，同时重建静态背景的密集图。同时，DymSLAM 不依赖于语义线索或先验知识，适用于未知的刚性物体。我们在真实世界的室内环境中进行了实验，其中相机和物体都在大范围内移动。结果证明，我们提出的方法是用于这种动态环境的最先进的 SLAM 系统。