Dr Scarlett Raine

Find Scarlett Raine on

Research Fellow (Underwater Perception, Artificial Intelligence, Computer Vision, Marine Robotics)

Doctor of Philosophy (Queensland University of Technology), B.Eng (Hons) (Queensland University of Technology)

Biography

Dr Scarlett Raine is a Research Fellow in the QUT Centre for Robotics, pioneering the use of Artificial Intelligence to analyse underwater images and help monitor marine ecosystems more efficiently.  With the increasing use of robotic underwater and surface vehicles to study coral reefs and seagrass meadows, vast amounts of imagery are generated. Traditionally, analysing this data has been challenging, time-consuming, and expensive, as it heavily relied on marine experts. Dr Raine’s innovative artificial intelligence methods automatically identify marine species in these images, streamlining the process. This technology can monitor coral reef health, estimate blue carbon in seagrass meadows, and identify the best seafloor areas for coral restoration.

Dr Raine is also an enthusiastic, dedicated and award-winning teacher with over five years of sessional academic experience spanning control and dynamic systems, electrical engineering, artificial intelligence, and engineering design and professional practice.  She is committed to improving diversity and gender representation in the field of engineering, and is a member of QUT’s Ally Network.

Research Overview

Dr Raine conducts research at the intersection of robotics, computer vision, artificial intelligence, environmental monitoring, and marine conservation.  She is passionate about designing novel deep learning approaches, especially for applied data-constrained and weakly labelled problems, and is motivated by multi-disciplinary, impactful applications of robotics and analysis of challenging real-world field data.

In her current research, Dr Raine brings her expertise in artificial intelligence to the Reef Restoration and Adaptation Program, where she is working on the Deployment Guidance System (DGS).  Her research on automated underwater image analysis will enable differentiation of substrate types in real-time, which will guide the automated deployment of corals to areas of the seafloor that provide optimal support and survival conditions. The DGS will enable broad-scale and targeted autonomous deployment of coral devices across the Great Barrier Reef, contributing to its adaptation and restoration.

Career History

Dr Raine completed her PhD at QUT in the Centre for Robotics and in collaboration with CSIRO’s Data61 on the topic of Weakly Supervised Segmentation of Underwater Imagery.  Her thesis was nominated by both examiners for the QUT Outstanding Doctoral Thesis Award. During her PhD, she published extensively on innovative deep learning strategies for analysing underwater imagery, with significant implications for ecological monitoring.   She is a published researcher in computer vision and artificial intelligence for applied robotics and environmental monitoring problems, with papers published in the D1-ranked Robotics and Automation Letters and Q1-equivalent WACV, CVPRW and DICTA.  Her work, Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery, won the SAGE publication prize in 2022.

Dr Raine has worked as a sessional academic in the School of Electrical Engineering and Robotics for over 5 years, accruing more than 1,300 hours of teaching experience in units spanning control and dynamic systems, electrical engineering, Artificial Intelligence and engineering professional design and practice.  During her PhD candidature, she also worked as the QUT Centre for Robotics Ambassador, which involved representing the Centre to visiting executives, academics, industry partners, collaborators and students, and demonstrating robotics platforms to audiences of hundreds of prospective students and parents at key recruitment events including QUT Open Day and the Brisbane Tertiary Studies & Careers Expo.

In 2023, Dr Raine worked as a Policy Officer at the Australian Government, in the Department of Climate Change, Energy, the Environment and Water. In this role, she planned and executed an $8 million research grant program for Innovative Biodiversity Monitoring technologies, including writing the grants guidelines and accompanying documents, launching the grant on GrantConnect, managing enquiries, assessing and moderating a huge number of grant applications. The role required understanding government processes and grant funding mechanisms and engaging with diverse stakeholders including the Minister’s Office, legal and finance departmental teams, and subject matter experts.

From November 2019 until August 2020, Dr Raine worked as a research intern at CSIRO’s Data61 Distributed Sensing Systems in the Cyber-Physical Systems lab.  In this role, she designed a novel proof-of-concept deep learning system for automated detection of the damaging Crown-of-Thorns Starfish.

Dr Raine received her Bachelor of Engineering in Mechatronics from QUT in 2020, majoring in Mechatronics and with minors in Computer Science and Management, and graduating with First Class Honours and as the class valedictorian. Scarlett wrote her Honours thesis under the supervision of Professor Jason Ford and Dr Jasmin Martin on the topic of Deep Learning with Temporal Features in the Context of Vision-Based Aircraft Detection.  From February 2016 until June 2020, Scarlett was a holder of the prestigious QUT Vice-Chancellor’s Scholarship for Academic Excellence.

Weblinks

Publication Highlights

  1. Raine, S., Marchant, R., Kusy, B., Maire, F., Suenderhauf, N. & Fischer, T. (2024). Human-in-the-Loop Segmentation of Multi-species Coral Imagery. Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition Workshops.
  2. Raine, S., Marchant, R., Kusy, B., Maire, F. & Fischer, T. (2024). Image Labels Are All You Need for Coarse Seagrass Segmentation. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. https://eprints.qut.edu.au/248331/ (Accepted as Oral Presentation – 2.6% selection rate)
  3. Raine, S., Marchant, R., Kusy, B., Maire, F. & Fischer, T. (2022). Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery. IEEE Robotics and Automation Letters, 7(3), 8291-8298. https://eprints.qut.edu.au/233592/  (Winner SAGE Publication Prize 2022)

Projects (Chief Investigator)

Additional Information

Awards

  • Type: Academic Honours, Prestigious Awards or Prizes
  • Reference year: 2022
  • Details: My first author paper “Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery” has received the 2022 Sage Publication Prize for the Faculty of Engineering.

Publications

  • Raine, S., Marchant, R., Kusy, B., Maire, F., Suenderhauf, N. & Fischer, T. (2024). Human-in-the-Loop Segmentation of Multi-species Coral Imagery. Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition Workshops.
  • Raine, S., Marchant, R., Kusy, B., Maire, F. & Fischer, T. (2024). Image Labels Are All You Need for Coarse Seagrass Segmentation. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. https://eprints.qut.edu.au/248331/
  • Raine, S., Marchant, R., Kusy, B., Maire, F. & Fischer, T. (2022). Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery. IEEE Robotics and Automation Letters, 7(3), 8291-8298. https://eprints.qut.edu.au/233592/
  • Raine, S., Marchant, R., Maire, F., Suenderhauf, N. & Kusy, B. (2021). Towards Dynamic Adaptation of Marine Surveys: Leveraging Fine-grained Segmentation from Sparse Labels. Proceedings of the IEEE International Conference on Robotics and Automation Workshops.
  • Raine, S., Marchant, R., Moghadam, P., Maire, F., Kettle, B. & Kusy, B. (2020). Multi-species Seagrass Detection and Classification from Underwater Images. Proceedings of the Digital Image Computing: Techniques and Applications (DICTA). https://eprints.qut.edu.au/210580/

Projects (Chief investigator)

Projects (Chief investigator)