25 September 2023
Domestic / International
About the research project
Underwater imagery is an important tool in a range of applications, including environmental monitoring, scientific research, and resource management. However, the interpretation and analysis of these images are often reliant on human annotators, who are prone to making errors. These errors can lead to incorrect or inconsistent interpretations of the images, potentially impacting the reliability and validity of the results. The aim of this PhD project is to explore the sources of human annotation errors in underwater imagery and to develop strategies for reducing the impact of these errors.
This project will involve a comprehensive literature review, user studies, and experimental design. The literature review will concentrate on existing studies on human annotation errors, with a specific emphasis on underwater imagery. The user studies will gather data from human annotators to comprehend the sources of errors and the factors that contribute to them. The experimental design will focus on developing and evaluating techniques such as human-in-the-loop machine learning to reduce the impact of these errors. This could include the creation of improved training and visualization tools. The project aligns with the IMOS Understanding Marine Imagery (UMI) Subfacility through Squidle+ (https://squidle.org/) and involves collaboration with ecologists, software engineers, and machine learning scientists.
The expected results of this project include a deeper understanding of the sources of human annotation errors impacting the quality of annotations from underwater imagery and the development of effective strategies to minimize their impact. These strategies might include improved training and visualization tools, as well as best practice guidelines for underwater image annotation. The outcomes of this project will enhance the accuracy and reliability of the interpretation and analysis of underwater imagery and have substantial implications for the tools developed within the UMI.
Primary SupervisorMeet Dr Jacquomo Monk
Applicants will be considered for a Research Training Program (RTP) scholarship or Tasmania Graduate Research Scholarship (TGRS) which, if successful, provides:
- a living allowance stipend of $31,500 per annum (2023 rate, indexed annually) for 3.5 years
- a relocation allowance of up to $2,000
- a tuition fees offset covering the cost of tuition fees for up to four years (domestic applicants only)
If successful, international applicants will receive a University of Tasmania Fees Offset for up to four years.
As part of the application process you may indicate if you do not wish to be considered for scholarship funding.
Other funding opportunities and fees
For further information regarding other scholarships on offer, and the various fees of undertaking a research degree, please visit our Scholarships and fees on research degrees page.
Applicants should review the Higher Degree by Research minimum entry requirements.
Ensure your eligibility for the scholarship round by referring to our Key Dates.
The project is competitively assessed and awarded. Selection is based on academic merit and suitability to the project as determined by the College.
Additional essential selection criteria specific to this project:
- Interest in quantitative ecology and/or computer science
- Advanced programming level in R or Python (especially machine learning)
- Experience in annotating underwater imagery datasets
- A familiarity with continental shelf ecology (including identifying demersal fishes and sessile invertebrates)
Additional desirable selection criteria specific to this project:
- Experience in scientific writing
- Select your project, and check that you meet the eligibility and selection criteria, including citizenship;
- Contact Dr Jacquomo Monk to discuss your suitability and the project's requirements; and
- In your application:
- Copy and paste the title of the project from this advertisement into your application. If you don’t correctly do this your application may be rejected.
- Submit a signed supervisory support form, a CV including contact details of 2 referees and your project research proposal.
- Apply prior to 25 September 2023.
Following the closing date applications will be assessed within the College. Applicants should expect to receive notification of the outcome by email by the advertised outcome date.