Inspired by the recent success of application of dense data approach by using ORB-SLAM and RGB-D SLAM, we propose a better pipeline of real-time SLAM in dynamics environment. Different from previous SLAM which can only handle static scenes, we are presenting a solution which use RGB-D SLAM as well as YOLO real-time object detection to segment and remove dynamic scene and then construct static scene 3D. We gathered a dataset which allows us to jointly consider semantics, geometry, and physics and thus enables us to reconstruct the static scene while filtering out all dynamic objects.

翻译：受近期使用ORB-SLAM和RGB-D SLAM的密集数据方法成功应用的启发，我们提出了一种在动态环境下更优的实时SLAM流水线。与以往只能处理静态场景的SLAM不同，我们提出了一种解决方案，该方法同时采用RGB-D SLAM和YOLO实时目标检测来分割并移除动态场景，进而构建静态场景的三维模型。我们收集了一个数据集，该数据集使我们能够联合考虑语义、几何和物理信息，从而在滤除所有动态对象的同时重建静态场景。