Electrical & Computer Engineering, Department of


First Advisor

Eric T. Psota

Date of this Version



Peace, J. Brennan. (2020). An End-to-End Trainable Method for Generating and Detecting Fiducial Markers (Master's Thesis). University of Nebraska-Lincoln.


A THESIS Presented to the Faculty of The Graduate College at the University of Nebraska In Partial Fulfilment of Requirements For the Degree of Master of Science, Major: Electrical Engineering, Under the Supervision of Professor Eric T. Psota. Lincoln, Nebraska: August, 2020.

Related work to appear in the 2020 British Machine Vision Conference.

Copyright (c) 2020 John Brennan Peace


Existing fiducial markers are designed for efficient detection and decoding. The methods are computationally efficient and capable of demonstrating impressive results, however, the markers are not explicitly designed to stand out in natural environments and their robustness is difficult to infer from relatively limited analysis. Worsening performance in challenging image capture scenarios - such as poorly exposed images, motion blur, and off-axis viewing - sheds light on their limitations. The method introduced in this work is an end-to-end trainable method for designing fiducial markers and a complimentary detector. By introducing back-propagatable marker augmentation and superimposition into training, the method learns to generate markers that can be detected and classified in real-world environments using a fully convolutional detector network. Results demonstrate that E2ETag outperforms existing methods in ideal conditions and performs much better with challenging poses, motion blur, contrast fluctuations, and noise. Augmentations are analyzed with ablation studies to convey the significance of each augmentation in training simulations for better detection in real-world deployment.

Advisor: Eric T. Psota