*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Multi-sensor Mapping in Natural Environment: Three-Dimensional Reconstruction and Temporal Alignment
Committee:
Dr. Cedric Pradalier, ECE, Chair, Advisor
Dr. Henry Owen, ECE, Co-Advisor
Dr. Anthony Yezzi, ECE
Dr. Alexandre Locquet, ECE
Dr. Anirban Mazdumar, ME
Dr. Philippe Giguere, Laval University
Abstract: The objective of this thesis is the adaptation and development of robotic techniques, suitable for geometric three dimensional reconstruction of natural environments, leading into the temporal alignment of natural outdoor surveys. The objective has been achieved by adapting the state-of-the-art in field robotics and computer vision, such as sensor fusion and visual Simultaneous Localization And Mapping (SLAM). Throughout this thesis, we combine data generated by cameras, lasers and an inertial measurement unit, in order to geometrically reconstruct the surrounding scene as well as to estimate the trajectory. By supporting cameras with laser depth information, we show that it is possible to stabilize the state-of-the-art in visual odometry, and recover scale for visual maps. We also show that factor graphs are powerful tools for sensor fusion, and can be used for a generalized approach involving multiple sensors. Using semantic knowledge, we constrain the Iterative Closest Point (ICP) in order to build keyframes as well as to align them both spatially and temporally. Hierarchical clustering of ICP-generated transformations is then used to both eliminate outliers and find alignment consensus, followed by an optimization scheme based on a factor graph that includes loop closure. Data was captured using a portable robotic sensor suite consisting of three cameras, three dimensional lidar, and an inertial navigation system. Throughout this thesis, data was captured in the natural environment using a wearable sensor suite, conceived in the first months of this thesis. The data was acquired in monthly intervals over 12months, by revisiting the same trajectory between August 2020 and July 2021. Finally, it has been shown that it is possible to align monthly surveys, taken over a year using the conceived sensor suite, and to provide insightful metrics for change evaluation in natural environment.
