Abstract
AbstractSimultaneous Localization and Mapping (SLAM) algorithms have been growing popular in indoor navigation and mapping. However, it often fails in many real-world environments, such as low-lighting, fast motion, featureless walls, and large buildings. There are also usability issues with the 3D point clouds for actual indoor localization and mapping for humans and autonomous robots. In this study, we use depth sensor to generate 3D point cloud and then register that to the 2D building floor plan or footprint. We extract the ground plane from the point cloud and create a 2D point cloud and contours to be registered to the map. The experiments show that 2D map is more intuitive than 3D point cloud. Furthermore, the contour map reduces computational time in orders of magnitude. We also developed a graphical user interface to enable the user to register the 2D point cloud interactively. It is a new way to use SLAM data. Our case studies in large office buildings demonstrate that this approach is simple, intuitive, and effective to enhance the localization and mapping in the real-world. KeywordsIndoor navigationSimultaneous Localization and MappingSLAMLocalizationMappingFeaturesRANSACFloor mapFloor planPoint cloud3DRegistrationLiDARDepth sensorDepth cameraEdge detection
Sign-in/Register to access full text options 
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.
