Projects per year
Description
Sewer-ML is a sewer defect dataset. It contains 1.3 million images, from 75,618 videos collected from three Danish water utility companies over nine years. All videos have been annotated by licensed sewer inspectors following the Danish sewer inspection standard, Fotomanualen. This leads to consistent and reliable annotations, and a total of 17 annotated defect classes.
| Date made available | 18 Jun 2021 |
|---|---|
| Publisher | sciencedata.dk |
| Geographical coverage | Denmark |
Emneord
- Sewer Defects
- Sewer
- Sewer Inspection
- Multi-Label Image Classification
- Defect Classification
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
Research output
- 2 Article in proceeding
-
Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder
Haurum, J. B., Madadi, M., Guerrero, S. E. & Moeslund, T. B., 2022, Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022. IEEE, p. 1441-1452 12 p.Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Open Access -
Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
Haurum, J. B. & Moeslund, T. B., 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): IEEE, p. 13451-13462 12 p. 9577322. (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Open Access5 Citations (Scopus)
Press / Media
-
Tv-inspektioner af kloakker kan automatiseres
15/03/2022
1 Media contribution
Press/Media: Press / Media
-
Unikt datasæt skal bidrage til vedligehold af danske kloakker
Joakim Bruslund Haurum & Thomas B. Moeslund
22/06/2021
1 item of Media coverage
Press/Media: Press / Media
-
Data og algoritmer skal hjælpe med at vedligeholde vores kloakker
Joakim Bruslund Haurum & Thomas B. Moeslund
21/06/2021
1 Media contribution
Press/Media: Press / Media
Impacts
-
Robots find defects in sewers
Thomas B. Moeslund (Participant), Chris Holmberg Bahnsen (Participant) & Joakim Bruslund Haurum (Participant)
Impact: Economic impact, Other impact