ConSLAM: Periodically Collected Real-World Construction Dataset for SLAM and Progress Monitoring
Abstract
Hand-held scanners are progressively adopted to workflows on construction sites. Yet, they suffer from accuracy problems, preventing them from deployment for demanding use cases. In this paper, we present a real-world dataset collected periodically on a construction site to measure the accuracy of SLAM algorithms that mobile scanners utilize. The dataset contains time-synchronised and spatially registered images and LiDAR scans, inertial data and professional ground-truth scans. To the best of our knowledge, this is the first publicly available dataset which reflects the periodic need of scanning construction sites with the aim of accurate progress monitoring using a hand-held scanner.
Cite
Text
Trzeciak et al. "ConSLAM: Periodically Collected Real-World Construction Dataset for SLAM and Progress Monitoring." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25082-8_21Markdown
[Trzeciak et al. "ConSLAM: Periodically Collected Real-World Construction Dataset for SLAM and Progress Monitoring." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/trzeciak2022eccvw-conslam/) doi:10.1007/978-3-031-25082-8_21BibTeX
@inproceedings{trzeciak2022eccvw-conslam,
title = {{ConSLAM: Periodically Collected Real-World Construction Dataset for SLAM and Progress Monitoring}},
author = {Trzeciak, Maciej and Pluta, Kacper and Fathy, Yasmin and Alcalde, Lucio and Chee, Stanley and Bromley, Antony and Brilakis, Ioannis K. and Alliez, Pierre},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {317-331},
doi = {10.1007/978-3-031-25082-8_21},
url = {https://mlanthology.org/eccvw/2022/trzeciak2022eccvw-conslam/}
}