PhD Study : Automated approaches to feature detection and classification in benthic imagery

Summary

Much of our current understanding about the distribution and ecological function of organisms and communities in the marine environment is based on analysis of imagery (Eleftheriou, 2013). Marine imaging techniques cover a wide range of scales and resolutions, from kilometres with acoustic imaging, to sub-centimetric with optical methods (Smith & Rumohr, 2013). In all respects, the number of observations decreases markedly with increasing water depth and distance from shore, meaning that for large areas of the seafloor we have very little information about the nature of the benthic environment (Webb et al., 2010). This lack of baseline data severely limits our ability to sustainably manage natural resources, understand the impacts of our activities and plan for future environmental change (Brierley & Kingsford, 2009).

The development and role of optical imagery in understanding biological processes in the marine environment has been well documented in the scientific literature (Solan et al., 2003; Durden et al., 2016; Shoening et al, 2017). Optical imagery of the benthos (photographs and video) are typically used to collect baseline information and for monitoring communities and fisheries habitats in a non-invasive manner.

These images are often used to identify organisms and characterise substrata in a fairly subjective manner that requires significant processing time. In the last decade, developments in acquisition platforms, imaging technologies and signal processing have transformed the quality and volume of data we now have available, thus motivating the current focus and development of new processing methodologies (eg. Durden et al., 2016; 2017; Gomes-Pereira et al., 2016; Schoening et al., 2017a). These developments represent significant research interest for both static imagery and video data and a wide range of potential applications (Matabos et al., 2017; Wäldchen and Mäder, 2018; Tabak et al., 2018; Schoening et al., 2017b).

This recent research paves the way to introduce computer vision and machine learning for next generation environmental monitoring which will form the basis of this PhD proposal. The ability to develop a framework that could automate, or semi-automate the process of feature detection and extraction combined with image classification in a standardised manner would be a significant advance to the field of marine ecology.  Hence, the aim of this project is to explore approaches for automated classification of benthic images and to examine the ecological validity of machine learning approaches to classification.

This PhD project involves researchers from the School of Geography and Environmental Sciences and the Intelligent Systems Research Centre at Ulster University, together with external partners at the Scottish Association for Marine Sciences and the University of Limerick. It will build on a framework of existing work performed in all research centres with a focus on feature extraction and classification for benthic imagery. Classification of such images is vital for biodiversity maintenance, environmental monitoring and fisheries management and aligns closely with Ulster University’s strategic research themes of sustainability and social renewal.

References

Brierley & Kingsford, 2009. DOI: 10.1016/j.cub.2009.05.046 | Durden et al, 2016. Perspectives in visual imaging for marine biology and ecology: from acquisition to understanding. Oceanography and Marine Biology: An Annual Review, 54:1-72 | Durden et al., 2017. DOI: 10.1002/lob.10213 | Eleftheriou (Ed.), 2013. DOI: 10.1002/9781118542392 | Solan et al., 2003. DOI: 10.1016/S0022-0981(02)00535-X | Matabos et al., 2017. DOI: 10.1111/2041-210X.12746 | Smith & Rumohr, 2013. DOI: 10.1002/9781118542392 | Schoening et al., 2017a. 10.3389/fmars.2016.00059 | Schoening et al., 2017b. DOI: 10.1038/s41598-017-13335-x | Wäldchen & Mäder, 2018. DOI: 10.1111/2041-210X.13075 | Webb et al., 2010. DOI: 10.1371/journal.pone.0010223 |

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

• A comprehensive and articulate personal statement

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

• First Class Honours (1st) Degree
• Masters at 65%
• Research project completion within taught Masters degree or MRES
• Experience using research methods or other approaches relevant to the subject domain
• Work experience relevant to the proposed project
• Experience of presentation of research findings

Funding and eligibility

The University offers the following levels of support:

Vice Chancellors Research Studentship (VCRS)

The following scholarship options are available to applicants worldwide:

• Full Award: (full-time tuition fees + £19,000 (tbc))
• Part Award: (full-time tuition fees + £9,500)
• Fees Only Award: (full-time tuition fees)

These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.

Department for the Economy (DFE)

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).

This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

• Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance.
• Republic of Ireland (ROI) nationals who satisfy three years’ residency in the UK prior to the start of the course MAY receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify).
• Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding.
• Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Due consideration should be given to financing your studies. Further information on cost of living