Saeed Gholami Shahbandi, Martin Magnusson, and Karl Iagnemma
Nonlinear Optimization of Multimodal 2D Map Alignment with Application to Prior Knowledge Transfer
IEEE Robotics and Automation Letters (Volume: 3, Issue: 3, 2018)
Abstract
We propose a method based on a nonlinear transformation for nonrigid alignment of maps of different modalities, exemplified with matching partial and deformed two-dimensional maps to layout maps. For two types of indoor environments, over a dataset of 40 maps, we have compared the method to state-of-the-art map matching and nonrigid image registration methods and demonstrate a success rate of 80.41% and a mean point-to-point alignment error of 1.78 m, compared to 31.9% and 10.7 m for the best alternative method. We also propose a fitness measure that can quite reliably detect bad alignments. Finally, we show a use case of transferring prior knowledge (labels/segmentation), demonstrating that map segmentation is more consistent when transferred from an aligned layout map than when operating directly on partial maps (95.97% vs. 81.56%).
@article{shahbandi-2018-nonlinear,
author = {Gholami Shahbandi, Saeed and Magnusson, Martin and Iagnemma, Karl},
journal = {IEEE Robotics and Automation Letters},
title = {Nonlinear Optimization of Multimodal 2D Map Alignment with Application to Prior Knowledge Transfer},
year = {2018},
month = jul,
volume = 3,
nr = 3,
pages = {2040--2047},
}