Deep learning for particle tracking

Examensarbete för kandidatexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/300955
Download file(s):
File Description SizeFormat 
TIFX04-20-17, kandidatrapport.pdf1.8 MBAdobe PDFThumbnail
View/Open
Bibliographical item details
FieldValue
Type: Examensarbete för kandidatexamen
Title: Deep learning for particle tracking
Authors: Lundell, Adrian
Tonderski, David
Meisingseth, Fredrik
Kristiansson, Dennis
Abstract: The use of machine learning for classifcation has in recent years spread into a wide range of disciplines, amongst them the detection of particles for particle tracking on microscopy data. We modifed the Python package DeepTrack, which makes use of deep learning to detect particles, creating a package called U-Track. By using a new network architecture based on a U-Net, better performance and higher computational effciency than DeepTrack was achieved on images with multiple particles. Furthermore, functionality to track detected particles over series of frames was developed. The application of U-Track on experimental data from two-dimensional ow nanometry produced tracks consistent with theory, as well as tracking larger quantities of particles over longer periods of time compared to a digital filter based benchmark algorithm.
Issue Date: 2020
Publisher: Chalmers tekniska högskola / Institutionen för fysik
URI: https://hdl.handle.net/20.500.12380/300955
Collection:Examensarbeten för kandidatexamen // Bachelor Theses



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