Towards Fast and Automatic Map Initialization for Monocular SLAM Systems
dc.contributor.author | Troutman, Blake | |
dc.contributor.author | Tuceryan, Mihran | |
dc.contributor.department | Computer and Information Science, School of Science | en_US |
dc.date.accessioned | 2023-02-10T20:32:57Z | |
dc.date.available | 2023-02-10T20:32:57Z | |
dc.date.issued | 2021-10 | |
dc.description.abstract | Simultaneous localization and mapping (SLAM) is a widely adopted approach for estimating the pose of a sensor with 6 degrees of freedom. SLAM works by using sensor measurements to initialize and build a virtual map of the environment, while simultaneously matching succeeding sensor measurements to entries in the map to perform robust pose estimation of the sensor on each measurement cycle. Markerless, single-camera systems that utilize SLAM usually involve initializing the map by applying one of a few structure-from-motion approaches to two frames taken by the system at different points in time. However, knowing when the feature matches between two frames will yield enough disparity, parallax, and/or structure for a good initialization to take place remains an open problem. To make this determination, we train a number of logistic regression models on summarized correspondence data for 927 stereo image pairs. Our results show that these models classify with significantly higher precision than the current state-of-the-art approach in addition to remaining computationally inexpensive. | en_US |
dc.eprint.version | Final published version | en_US |
dc.identifier.citation | Troutman, B., & Tuceryan, M. (2021). Towards Fast and Automatic Map Initialization for Monocular SLAM Systems: Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems, 22–30. https://doi.org/10.5220/0010640600003061 | en_US |
dc.identifier.issn | 978-989-758-537-1 | en_US |
dc.identifier.uri | https://hdl.handle.net/1805/31225 | |
dc.language.iso | en_US | en_US |
dc.publisher | SciTePress | en_US |
dc.relation.isversionof | 10.5220/0010640600003061 | en_US |
dc.relation.journal | Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems | en_US |
dc.rights | Publisher Policy | en_US |
dc.source | Publisher | en_US |
dc.subject | Simultaneous Localization and Mapping (SLAM) | en_US |
dc.subject | Structure From Motion | en_US |
dc.subject | Map Initialization | en_US |
dc.subject | Monocular Vision | en_US |
dc.title | Towards Fast and Automatic Map Initialization for Monocular SLAM Systems | en_US |
dc.type | Article | en_US |