Tracking a rat in an open field experiment with a deep learning-based model
Abstract
New artificial neural network methods have changed the way animals are tracked in neuroscience and psychology experiments. The purpose of this thesis is to test the state-of-the-art method of animal tracking DeepLabCut and to develop a usable model for tracking rats in an open field type experiment, and to use tracking information to extract researchrelated key figures via self-tailored analysis software. The model trained with the DeepLabCut and 825 labeled images was accurate and suitable to be used in a research experiment. With the help of tracked body parts, it was possible to extract meaningful key figures for further analysis in a research experiment.
Main Author
Format
Theses
Master thesis
Published
2021
Subjects
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-202111095578Käytä tätä linkitykseen.
Language
English
License
