Sparse 3D Point-cloud Map Upsampling and Noise Removal as a vSLAM Post-processing Step: Experimental Evaluation
This work addresses map quality issues for mobile robotics and computer vision applications, but it is incremental as it combines and evaluates existing algorithms without introducing new methods.
The paper tackles the problem of improving sparse 3D point-cloud maps from monocular vSLAM by evaluating post-processing techniques for noise removal and upsampling, identifying the most effective combination on real indoor and outdoor datasets and demonstrating its use in converting point-clouds to voxel grids for path planning.
The monocular vision-based simultaneous localization and mapping (vSLAM) is one of the most challenging problem in mobile robotics and computer vision. In this work we study the post-processing techniques applied to sparse 3D point-cloud maps, obtained by feature-based vSLAM algorithms. Map post-processing is split into 2 major steps: 1) noise and outlier removal and 2) upsampling. We evaluate different combinations of known algorithms for outlier removing and upsampling on datasets of real indoor and outdoor environments and identify the most promising combination. We further use it to convert a point-cloud map, obtained by the real UAV performing indoor flight to 3D voxel grid (octo-map) potentially suitable for path planning.