Dataset Open Access

A deep learning dataset for underwater object detection of tropical freshwater fish species in northern Australia

Jansen, Andrew; Walden, David; Walker, Samantha; Buccella, Constanza

This dataset includes 44,112 images with 82,904 bounding box annotations for 23 tropical freshwater fish taxa from northern Australia. 

Images were derived from Remote Underwater Video (RUV) deployments in deep channel and shallow lowland billabongs, Kakadu National Park, Northern Territory Australia. RUV deployments were conducted during the Supervising Scientists annual fish monitoring program in the 2016, 2017 and 2018 recessional flow period (dry season). More information can be found here.

  • All images are in .jpg format and are 1920x1080 in dimension.
  • Bounding box annotations are in COCO format. 

Two .zip files are included:

  • includes compact model weights in tensorflow format (.pb) trained using Azure's Custom Vision platform. This model is suitable for edge devices due to its reduced size. Code is provided to use the compact model for inferencing. 
  • includes all images and one COCO (.json) file with annotations. 

Fish taxa include: 

  1. Ambassis agrammus
  2. Ambassis macleayi
  3. Amniataba percoides
  4. Craterocephalus stercusmuscarum
  5. Denariusa bandata
  6. Glossamia aprion
  7. Glossogobius spp.
  8. Hephaestus fuliginosus
  9. Lates calcarifer
  10. Leiopotherapon unicolor
  11. Liza ordensis
  12. Megalops cyprinoides
  13. Melanotaenia nigrans
  14. Melanotaenia splendida inornata
  15. Mogurnda mogurnda
  16. Nemetalosa erebi
  17. Neoarius spp.
  18. Neosilurus spp.
  19. Oxyeleotris spp.
  20. Scleropages jardinii
  21. Strongylura kreffti
  22. Syncomistes butleri
  23. Toxotes chatareus

If you use this data for your own deep learning project we'd love to hear about how you used this dataset:

Files (6.0 GB)
Name Size
41.2 MB Download
5.9 GB Download
All versions This version
Views 120120
Downloads 4141
Data volume 208.3 GB208.3 GB
Unique views 104104
Unique downloads 2626


Cite as