A real-time semantic visual SLAM for dynamic environment based on deep learning and dynamic probabilistic propagation

Most existing visual simultaneous localization and mapping (SLAM) algorithms rely heavily on the static world assumption. Combined with deep learning, semantic SLAM has become a popular solution for dynamic scenes. However, most semantic SLAM methods show poor real-time performance when dealing with dynamic scenes. To handle this problem, a real-time semantic SLAM method is proposed in this paper, combining knowledge distillation and dynamic probability propagation strategy. First, to improve the execution speed, a multi-level knowledge distillation method is adopted to obtain a lightweight segmentation model, which is more suitable for continuous frames to create an independent semantic segmentation thread. This segmentation thread only accepts keyframes as input so that the system can avoid time delay caused by processing each frame. Second, a static semantic keyframe selection strategy is proposed based on the segmentation results. In this way, those keyframes containing more static information will be selected to reduce the participation of dynamic objects. By combining segmentation results and data matching algorithm, our system can realize the update and propagation of dynamic probability, reducing the influence of dynamic points in the pose optimization process. Validation results based on the KITTI and TUM datasets show that our method can effectively deal with dynamic feature points and improve running speed simultaneously.