Photographs and video provide a safe, non-destructive and efficient way to examine and monitor marine habitats, and are particularly useful in areas protected for their biodiversity values.
To be useful on a national scale, however, the life forms they reveal must be named in a consistent way. This project established a national standard for classifying the substrates, flora and fauna visible in marine photos and video. The Collaborative and Automated Tools for the Analysis of Marine Imagery (CATAMI) classification system now provides that common vocabulary for Australia.
The CATAMI classification system (CSS) was funded by the National eResearch Collaboration Tools and Resources and supported by the Australian National Data Service. It was established and refined during workshops involving software engineers, programmers, and benthic ecologists from state and Commonwealth agencies and universities, under the direction of the CATAMI Technical Working Group. For longevity, the CCS was incorporated into the Codes for Australian Aquatic Biota database.
New knowledge and opportunities
The CCS employs a standardised combination of high-level taxonomy (phylum, order, class) and morphological (shape, growth-form) characteristics that can be determined from a picture. This provides more consistency than traditional classification approaches. In future, the system could be combined with automated image analysis to ensure the consistent annotation of datasets used to ‘train’ automatic image analysis algorithms.
The CCS provides the framework for nationally-consistent annotation of marine imagery data. This will support national marine monitoring by streamlining data collated by different organisations, including through government contracts, environmental impact assessments and long-term monitoring.
Outputs and outcomes
An agreed, national standard for classifying substrates and biota in marine imagery has been developed and provided online through the Australian Ocean Data Network. Standardised, quantitative estimates such as the presence and percentage cover can now be made from video and photographic images, improving the efficiency of marine ecosystem research and the ability to compare results from different studies.
The CCS is being adopted by industry, government and academia, with several hundred copies of the technical document and code file downloaded from the website. It has been used by the NERP Marine Biodiversity Hub, the Reef Life Survey, the New South Wales Marine Protected Areas monitoring program, the Australian Institute of Marine Science, and the Australian Centre for Field Robotics, and in two online annotation tools: CATAMI and Squidle. Environmental consultants to oil and gas companies (GeoOceans and Chevron Wheatstone Project) have also used the CCS. An illustrated CATAMI poster is publicly available.
(08) 6304 6070