Projects per year
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 16th International Conference on Computer Vision Theory and Applications (VISAPP) |
Editors | Giovanni Maria Farinella, Petia Radeva, Jose Braz, Kadi Bouatouch |
Number of pages | 10 |
Volume | 5 |
Publisher | SCITEPRESS Digital Library |
Publication date | 2021 |
Pages | 891-900 |
ISBN (Electronic) | 9789897584886 |
DOIs | |
Publication status | Published - 2021 |
Event | International Conference on Computer Vision Theory and Applications - Duration: 8 Feb 2021 → 10 Feb 2021 Conference number: 16 http://www.visapp.visigrapp.org/ |
Conference
Conference | International Conference on Computer Vision Theory and Applications |
---|---|
Number | 16 |
Period | 08/02/2021 → 10/02/2021 |
Internet address |
Keywords
- Sewer Pipes
- Geometric Deep Learning
- Synthetic Data
- Defect classification
- Sewer Inspection
- 3D sensor
- 3D deep learning
- Transfer learning
- Point clouds
- Sewers
Fingerprint
Dive into the research topics of 'Sewer Defect Classification using Synthetic Point Clouds'. Together they form a unique fingerprint.Projects
- 1 Finished
-
ASIR: ASIR: Autonomous Sewer Inspection Robot
Moeslund, T. B., Haurum, J. B., Bahnsen, C. H. & Hansen, B. D.
01/11/2018 → 30/04/2022
Project: Research
Datasets
-
AAU Sewer Defect Point Cloud Dataset
Haurum, J. B. (Creator), Allahham, M. M. J. (Creator), Lynge, M. S. (Creator), Henriksen, K. S. (Creator), Nikolov, I. A. (Creator) & Moeslund, T. B. (Creator), Kaggle, 2021
https://www.kaggle.com/aalborguniversity/sewerpointclouds
Dataset