TagLab is an interactive open source software system for facilitating the precise annotation of benthic species in orthophoto of the bottom of the sea. TagLab can automatically extract statistical informations about the evolution of monitored species and it segments large images using CNN-based algorithms.[2]
 TagLab | |
| Developer(s) | ISTI - CNR |
|---|---|
| Stable release | 2023.5.17
/ May 17, 2023[1] |
| Written in | python |
| Operating system | Cross-platform |
| Type | Graphics software |
| License | GPL |
| Website | taglab |
TagLab used also for the monitoring of the health of coral reefs, in order to quantify over large orthophotos of the seabed the extent of coral bleaching events.[3] Notable users of TagLab are MOTE Marine Laboratory,[4] the Hawaiʻi Institute of Marine Biology,[5] National Oceanic and Atmospheric Administration,[6] and Scripps Institution of Oceanography.[7]
TagLab is listed as one of the main tools for the standard operating procedures for the use of large-area imaging in tropical shallow water coral reef monitoring, research, and restoration.[8]
TagLab has won the 2023 VRVis Visual Computing Award for being "an open-source software solution that mitigates technological disparities between labs and promotes shared data standards and protocols".[9]
References edit
- ^ "TagLab 17 release notes". Official GitHub repository. 2023-02-24.
- ^ Pavoni, Gaia; Corsini, Massimiliano; Ponchio, Federico; Muntoni, Alessandro; Edwards, Clinton; Pedersen, Nicole; Sandin, Stuart; Cignoni, Paolo (2022). "TagLab: AI-assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages". Journal of Field Robotics. 39 (3): 246–262. doi:10.1002/rob.22049. S2CID 244648241.
- ^ Kopecky, Kai L.; Pavoni, Gaia; Nocerino, Erica; Brooks, Andrew J.; Corsini, Massimiliano; Menna, Fabio; Gallagher, Jordan P.; Capra, Alessandro; Castagnetti, Cristina; Rossi, Paolo; Gruen, Armin; Neyer, Fabian; Muntoni, Alessandro; Ponchio, Federico; Cignoni, Paolo (18 August 2023). "Quantifying the Loss of Coral from a Bleaching Event Using Underwater Photogrammetry and AI-Assisted Image Segmentation". Remote Sensing. 15 (16): 4077. Bibcode:2023RemS...15.4077K. doi:10.3390/rs15164077. hdl:11380/1316375. ISSN 2072-4292.
- ^ Combs, Ian. "MOTE - Coral Reef Ecosystems Program".
- ^ "Hybrid Reef Coastal Erosion Project". 31 October 2016.
- ^ Costa, Bryan; Sweeney, Edward; Mendez, Arnold (October 2022). "Leveraging Artificial Intelligence to Annotate Marine Benthic Species and Habitats". Noaa Technical Memorandum Nos Nccos. 306. doi:10.25923/7kgv-ba52.
- ^ Riegl, Bernhard, ed. (2020). Population Dynamics of the Reef Crisis. Elsevier Science. pp. 174–177. ISBN 9780128215302.
- ^ Sophie, Cook; G., Rojano, Sarah; B., Edwards, Clinton; A., Bollinger, Michael; Jordan, Pierce; Shay, Viehman, T. (2023). "Standard operating procedures for the use of large-area imaging in tropical shallow water coral reef monitoring, research and restoration: Applications for Mission: Iconic Reefs restoration in the Florida Keys National Marine Sanctuary". doi:10.25923/w8h9-4z75.
{{cite journal}}: Cite journal requires|journal=(help)CS1 maint: multiple names: authors list (link) - ^ "Gaia Pavoni and Thomas Höllt win VRVis Visual Computing Award".
 | This technology-related article is a stub. You can help Wikipedia by expanding it. |