Fiducial marker detection and identification for individual honey bee tracking using cascaded deep learning models

Date

2024-12

Author

Kara, Mustafa Yavuz

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

39
views

39
downloads

Cite This

Performant and efficient detection and decoding of visual fiducial markers is an important task for tracking unique objects over long periods of time. These markers are often utilised by biologists to enable long-term analysis of their honey bee experiment hives and setups. Having a highly precise and time-efficient method for this task is especially important in context of automated monitoring, data recording and analysis of scientific experiments. In this thesis we propose a performant, efficient and flexible method of detecting and decoding fiducial markers in images and video frames. This method is structured as a two-stage marker detection and decoding pipeline made up of independent deep learning models that can be trained separately. We also describe and analyse a method for generating highly effective training datasets of varying size using a small set of source object and background images. Finally we demonstrate the effectiveness of our methods for fiducial detection and decoding tasks using real biological experiment data on Apis mellifera tagged with visual fiducial markers.

Subject Keywords

Visual recognition, Object detection, Data generation, Visual fiducial marker, Bee tracking

URI

https://hdl.handle.net/11511/113487

Collections

Graduate School of Natural and Applied Sciences, Thesis