Abstract
Simultaneous Localization and Mapping (SLAM) have become a new research hotspot in the field of artificial intelligence applications such as unmanned driving and mobile robots. Most of the current SLAM research is based on the assumption of static scenes, and dynamic objects in the indoor environment are inevitable. The assumption based on static scenes greatly limits the development of SLAM and the application of SLAM system in real life. At the same time, the semantic segmentation is added to the SLAM system to generate a semantic map with semantic information, which can enrich the understanding of the mobile carrier to the environment and obtain high-level perception. In this paper, we combine the visual SLAM system ORB-SLAM2 and PSPNet semantic segmentation network, and propose a PSPNet-SLAM system, which uses optical flow and semantic segmentation to detect and eliminate dynamic points to achieve dynamic scenes semantic SLAM. We performed experiments on the TUM RGB-D dataset. The results show that compared with other SLAM systems, PSPNet-SLAM can reduce the camera pose estimation error in indoor dynamic scenes to different degrees and improve the camera position estimation accurately.
Highlights
The Simultaneous Localization and Mapping (SLAM) problem can be described as a robot moving from an unknown location in an environment without a priori knowledge
The results show that the SLAM system can improve the robustness and stability of the SLAM system in highly dynamic scenes
In low dynamic sequences, such as the fr3_sitting_static sequence, the error reduction is small because ORB-SLAM2, DS-SLAM, and DynaSLAM can already handle low dynamic scenes well and achieve good performance, so the space that can be improved is limited
Summary
The Simultaneous Localization and Mapping (SLAM) problem can be described as a robot moving from an unknown location in an environment without a priori knowledge. The traditional SLAM research is mostly based on the assumption of static scenes, while the existence of dynamic objects in real-life scenes. A typical SLAM system usually builds a map based on geometric information. This method only provides the structural information of the environment and its location information. Xi: Dynamic Scene Semantics SLAM Based on Semantic Segmentation detected and eliminated using optical flow and semantic segmentation to implement a semantic SLAM system in dynamic scenes Can it greatly reduces the interference of dynamic objects on pose estimation and improve the accuracy of pose estimation, but it can generate semantic maps with semantic information, which can enrich mobile carriers’ understanding of the environment and obtain high-level perception. The rest of the structure of this paper is as follows: the second part reviews the related work, the third part introduces the PSPNet-SLAM system in detail, the fourth part details the experimental results, and the fifth part introduces the conclusions and future work
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
