Sewer-ML Dataset Access Form
This is the official request form for the Sewer-ML dataset.
All submitted papers (or any publicly available text) that uses the Sewer-ML database must cite the following paper: Joakim Bruslund Haurum and Thomas B. Moeslund. "Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2021.
The Sewer-ML dataset is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license. Therefore, the data must not be used for commercial purposes. Researchers can request access to this database by filling in and submitting the form below and reading and agreeing to the terms of use.
The supplied information will be stored by the dataset providers. Parts of the supplied information may be shared with members of the research project Automated Sewer Inspection Robot (ASIR) (Innovation Fund Denmark grant: 8055-00015A.) in a processed format for analysis of the dataset usage. Personal contact information will not be shared.