The FishID project aims to transform environmental monitoring of aquatic ecosystems in Australia through automated detection and identification of animals in underwater imagery.

The FishID platform will overcome the cost associated with manually processing and extracting data from underwater cameras by creating a user-friendly, public-facing end-to-end pipeline for deep learning detection and automated identification of animals. FishID will deliver a robust and intuitive system for researchers to annotate imagery, train and evaluate deep learning models to accurately detect, identify and count species of interest across coastal and marine ecosystems.

1 An automated, integrated service for object detection and classification of underwater imagery
This includes an annotation tool, video analysis and output, improved user interface and a public API.
2 Training
Videos, documentation and full training packages will be provided to support uptake and use.
3 Community
Software testing with key users, and workshops with the user community.

Core features

Integrated end-to-end automation service
A pipeline of software packages that: assist annotations using Machine Learning (ML), support model creation & testing of deep learning models for object detection and classification, and provide species identification and abundance data outputted in common database formats (e.g. for GlobalArchive).
Online training
A training package will be provided. Consisting of multiple elements designed as user-friendly tutorials, for topics including annotation training, model development and model evaluation.
Community building
Sharing knowledge among the network of Australian experts through regular workshops with research data scientists and aquatic ecosystem scientists. Enabling users to access and use models and workflows by making available code through easy-to-understand JupyterLab Notebooks. These are likely to be deployed and run in the EcoCommons command-line environment, EcoCloud.

Who is this project for?

  • Researchers
  • Federal and state government
  • Farmers
  • Environmental educators
  • Tourism operators

What does this project enable?

This project fills a critical infrastructure gap between the collection of underwater imagery and the resulting data made available in national repositories.

The project will enable a step-change in monitoring efficiency that will improve outcomes across multiple sectors such as marine environmental monitoring (e.g. environmental assessments, State of Environment reporting); river health monitoring (e.g. Murray-Darling Basin Authority); fisheries assessments (e.g. State Fisheries departments); aquatic habitat restoration (e.g. NGOs investing $130 million in reef restoration over 5 years), some already with streaming cameras suitable for automated image analysis; education (e.g. Moreton Bay Live streaming cameras by QLD Environmental Education Centre); and tourism (e.g. Great Barrier Reef live streaming cameras with Cairns Aquarium).

Griffith UniversityVisit
University of AdelaideVisit
University of the Sunshine CoastVisit
University of Western AustraliaVisit
James Cook UniversityVisit
Education Queensland (Moreton Bay Environmental Education Centre)Visit
Western Australia Department of Primary Industries and Regional DevelopmentVisit