Data

DeepFish: A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis

James Cook University
Saleh, A ; Bradley, M ; Sheaves, M
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.25903/5f617fb6d6e0e&rft.title=DeepFish: A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis&rft.identifier=10.25903/5f617fb6d6e0e&rft.publisher=James Cook University&rft.description=The dataset consists of approximately 40 thousand images collected underwater from 20 habitats in the marine-environments of tropical Australia. The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark. Videos for DeepFish were collected for 20 habitats from remote coastal marine environments of tropical Australia. These videos were acquired using cameras mounted on metal frames, deployed over the side of a vessel to acquire video footage underwater. The cameras were lowered to the seabed and left to record the natural fish community, while the vessel maintained a distance of 100 m. The depth and the map coordinates of the cameras were collected using an acoustic depth sounder and a GPS, respectively. Video recording was carried out during daylight hours and in relatively low turbidity periods. The video clips were captured in full HD resolution (1920 × 1080 pixels) from a digital camera. In total, the number of video frames taken is 39,766.  The DeepFish dataset and code are publicly available at https://alzayats.github.io/DeepFish/ and https://github.com/alzayats/DeepFish, respectively. The full methodology is available in the Open Access publication from the Related publications link below.&rft.creator=Saleh, A &rft.creator=Bradley, M &rft.creator=Sheaves, M &rft.date=2024&rft.edition=undefined&rft.coverage=Palm Islands, Queensland, Australia&rft.coverage=Western Australia&rft_rights=CC BY 4.0: Attribution 4.0 International http://creativecommons.org/licenses/by/4.0&rft_subject=fish datasets&rft_subject=DeepFish &rft_subject=deep learning&rft_subject=Computer Vision&rft_subject=fish Segmentation &rft_subject=ARC Centre of Excellence for Coral Reef Studies&rft_subject=Computer Vision&rft_subject=INFORMATION AND COMPUTING SCIENCES&rft_subject=ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING&rft_subject=Fisheries - Aquaculture not elsewhere classified&rft_subject=ANIMAL PRODUCTION AND ANIMAL PRIMARY PRODUCTS&rft_subject=FISHERIES - AQUACULTURE&rft.type=dataset&rft.language=English Access the data
Cite Saved to MyRDA Save to MyRDA

Licence & Rights:

Open Licence view details
CC-BY

CC BY 4.0: Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0

Access:

Open view details

Open: free access under license

Contact Information



Full description

The dataset consists of approximately 40 thousand images collected underwater from 20 habitats in the marine-environments of tropical Australia.

The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark.

Videos for DeepFish were collected for 20 habitats from remote coastal marine environments of tropical Australia. These videos were acquired using cameras mounted on metal frames, deployed over the side of a vessel to acquire video footage underwater. The cameras were lowered to the seabed and left to record the natural fish community, while the vessel maintained a distance of 100 m. The depth and the map coordinates of the cameras were collected using an acoustic depth sounder and a GPS, respectively. Video recording was carried out during daylight hours and in relatively low turbidity periods. The video clips were captured in full HD resolution (1920 × 1080 pixels) from a digital camera. In total, the number of video frames taken is 39,766. 

The DeepFish dataset and code are publicly available at https://alzayats.github.io/DeepFish/ and https://github.com/alzayats/DeepFish, respectively.

The full methodology is available in the Open Access publication from the Related publications link below.

Created: 2020

This dataset is part of a larger collection

Click to explore relationships graph
Help

Related People

Spatial Coverage And Location

text: Palm Islands, Queensland, Australia

text: Western Australia

Subjects
Animal Production and Animal Primary Products | ARC Centre of Excellence for Coral Reef Studies | Artificial Intelligence and Image Processing | Computer Vision | Computer Vision | DeepFish | Fisheries - Aquaculture | Fisheries - Aquaculture Not Elsewhere Classified | Information and Computing Sciences | deep learning | fish Segmentation | fish datasets |

User Contributed Tags    

Login to tag this record with meaningful keywords to make it easier to discover

Other Information
Saleh, Alzayat, Laradji, Issam H., Konovalov, Dmitry A., Bradley, Michael, Vazquez, David, and Sheaves, Marcus (2020) A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis. Scientific Reports, 10. 14671

doi : 10.1038/s41598-020-71639-x

DeepFish database

uri : https://alzayats.github.io/DeepFish

DeepFish code

uri : https://github.com/alzayats/DeepFish

Identifiers
  • DOI : 10.25903/5F617FB6D6E0E
  • Local : research.jcu.edu.au/data/published/48fcdde6576ee929325b01fca4207914
  • Local : 7bf2d3301c98f60a94912e27e2594eed
Similar data you may be interested in: