Tracking marine microorganisms using deep learning

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/301092
Download file(s):
File Description SizeFormat 
HilleviWachtmeister_MasterThesis.pdf5.48 MBAdobe PDFView/Open
Bibliographical item details
FieldValue
Type: Examensarbete för masterexamen
Title: Tracking marine microorganisms using deep learning
Authors: Wachtmeister, Hillevi
Abstract: The goal of this project is to develop a software that can be used to study swimming patterns of marine microorganisms. The software is based on a neural network, which is trained to recognise different types of plankton. The predictions from the network are then used to find the positions of the plankton and track their movements. The project is divided into two parts. First, videos containing only one type of plankton, Lingulodinium polyedra and Alexandrium tamarense, respectively, are analyzed. A type of neural network, called U-net, is trained to segment the input images into background and plankton sections. From the segmented images, positions can be obtained and then connected to form a trajectory for each plankton. The drift of the plankton movements is calculated and subtracted from the trajectories, and finally the speed and net displacement are calculated. The results from the single plankton experiments are compared to a previous analysis that was made using an algorithmic method. Secondly, videos containing two types of plankton are analyzed containing the phytoplankton Strombidium arenicola and Rhodomonas baltica. The segmented images, obtained from the U-net, consists of an additional plankton section for the second type of plankton present in the experiment. The analysis of the single plankton experiments yields longer and fewer trajectories using the U-net method, compared to the previous results using the algorithmic method. This indicates that the U-net method detects plankton at more positions, and is therefore able to track each plankton for a longer time, compared to the algorithmic method. The multi-plankton experiments prove
Keywords: deep learning;U-net;plankton;tracking;drift compensation
Issue Date: 2020
Publisher: Chalmers tekniska högskola / Institutionen för fysik
URI: https://hdl.handle.net/20.500.12380/301092
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.