Sewer Defect Classification using Synthetic Point Clouds

Joakim Bruslund Haurum, Moaaz M. J. Allahham, Mathias S. Lynge, Kasper Schøn Henriksen, Ivan A. Nikolov, Thomas B. Moeslund

2021

Abstract

Sewer pipes are currently manually inspected by trained inspectors, making the process prone to human errors, which can be potentially critical. There is therefore a great research and industry interest in automating the sewer inspection process. Previous research have been focused on working with 2D image data, similar to how inspections are currently conducted. There is, however, a clear potential for utilizing recent advances within 3D computer vision for this task. In this paper we investigate the feasibility of applying two modern deep learning methods, DGCNN and PointNet, on a new publicly available sewer point cloud dataset. As point cloud data from real sewers is scarce, we investigate using synthetic data to bootstrap the training process. We investigate four data scenarios, and find that training on synthetic data and fine-tune on real data gives the best results, increasing the metrics by 6-10 percentage points for the best model. Data and code is available at https://bitbucket.org/aauvap/sewer3dclassification.

Paper Citation

in Harvard Style

Haurum J., Allahham M., Lynge M., Henriksen K., Nikolov I. and Moeslund T. (2021). Sewer Defect Classification using Synthetic Point Clouds. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 891-900. DOI: 10.5220/0010207908910900

in Bibtex Style

@conference{visapp21,
author={Joakim Bruslund Haurum and Moaaz M. J. Allahham and Mathias S. Lynge and Kasper Schøn Henriksen and Ivan A. Nikolov and Thomas B. Moeslund},
title={Sewer Defect Classification using Synthetic Point Clouds},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={891-900},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010207908910900},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Sewer Defect Classification using Synthetic Point Clouds
SN - 978-989-758-488-6
AU - Haurum J.
AU - Allahham M.
AU - Lynge M.
AU - Henriksen K.
AU - Nikolov I.
AU - Moeslund T.
PY - 2021
SP - 891
EP - 900
DO - 10.5220/0010207908910900
PB - SciTePress