A feature map produced by the second convolutional layer of a Convolutional Neural Network applied to an input RGB image of Nephrops norvegicus recorded inside the demersal trawl.

PhD defence about the optical catch monitoring of demersal trawl fisheries

Friday 19 Aug 22

Contact

Maria Sokolova
Researcher

Contact

Ludvig Ahm Krag
Professor
DTU Aqua
+45 21 31 64 57

On 25 August 2022, Maria Sokolova will defend her PhD thesis. It is possible to attend the defence at DTU in Hirtshals or online.

During her PhD study, Maria Sokolova has developed, tested and demonstrated a real-time optical catch monitoring tool for demersal trawl fisheries. The tool consists of an in-trawl image acquisition system to ensure high-resolution catch recordings during trawling and a software to automatically detect, classify and count the catch.

Demersal trawl fisheries are one of the most productive and widely used types of fishing activities globally. In recent years, demersal trawl fisheries have—as commercial fisheries in general—been increasingly challenged by several factors. 

The major issue is a considerable amount of unwanted species and sizes obtained by the demersal trawls together with the target catch. Therefore there is a need to develop methods and technologies that can transform demersal trawl fisheries from a blind process to a more informed process during which the fisher can continuously make decisions to optimize the ongoing catch process. This will improve both the biological and the economical sustainability of the fisheries.

In an experimental pilot study, Maria Sokolova designed and tested a prototype of an in-trawl image acquisition system and explored computer vision methods for automated catch description. This pilot study provided the basis for two further developments of the optical monitoring tool. 

The second study covered the successful transfer of an experimental image acquisition system to real demersal trawling conditions, ensuring stable and consistent background and illumination during image acquisition. 

The third study included software development for automated catch description, based on a deep-learning approach, which became possible to implement due to the collected catch data during in-trawl image acquisition system test at sea.

About the PhD defence

Maria Sokolova will defend her PhD thesis "Development of an optical catch monitoring tool for demersal trawl fisheries" on Thursday 25 August 2022, 09:30 - 13:00 (including break) on Zoom and at DTU Aqua, Willemoesvej 2, 9850 Hirtshals.

Supervisors

  • Principal supervisor: Professor Ludvig Ahm Krag, DTU Aqua
  • Co-supervisor: Postdoc Fletcher Thompson, DTU Aqua
  • Co-supervisor: Professor Barry O'Neill, DTU Aqua

Assessment committee

  • Senior Researcher Ole Ritzau Eigaard, DTU Aqua (chair)
  • Senior Researcher Jacopo Aguzzi, Spanish National Research Council, Spain
  • Principal Scientist Manu Sistiaga, Institute of Marine Research, Norway

Chairperson at defence

  • Senior Researcher Junita Diana Karlsen, DTU Aqua
Learn more

A popular science summary of the thesis can be downloaded here  

A copy of the thesis is available by e-mail by request. Please contact PhD Secretary Karin Stubgaard, stub@aqua.dtu.dk  

It is possible to attend Maria Sokolovas’s defence on Zoom or physically at DTU Aqua in Hirtshals, Willemoesvej 2, 9850 Hirtshals.

If you want to participate online, please e-mail PhD secretary Karin Stubgaard, stub@aqua.dtu.dk by Wednesday 24 August at 13:00. After this time, you'll receive an e-mail confirming your registration, including a link for online participation.

https://www.aqua.dtu.dk/english/news/2022/08/phd-defence-maria-sokolova
30 APRIL 2024