Vision-based Simultaneous Localization and Mapping (vSLAM) is a challenging task in modern computer vision. vSLAM is particularly important as mobile robotics application. It allows to localize the robot and build the map of unknown environment in 3D in real-time. During research and development of new methods, it needs extensive evaluation on trajectory and map quality compared to known methods. In this work we focus on map quality estimation. We develop the simulated ground-truth data in photo-realistic environment and introduce new metrics in order to estimate map quality. We evaluate neural network based vSLAM methods with our framework in order to show that it fits map quality estimation more than standard approaches. Open-source implementation of our map metrics is available at https://github.com/CnnDepth/slam_comparison
DOI: 10.1109/SIBCON50419.2021.9438884
Download PDF or read online at IEEE Xplore: https://ieeexplore.ieee.org/document/9438884
Download open-source implementation at GetHub: https://github.com/CnnDepth/slam_comparison
ResearchGate: https://www.researchgate.net/publication/351855531_Assessment_of_Map_Construction_in_vSLAM
A. Bokovoy and K. Muraviev. Assessment of Map Construction in vSLAM // 2021 International Siberian Conference on Control and Communications (SIBCON), Kazan, Russia, 2021, pp. 1–6.