"ENHANCED DEEP TEMPLATE-BASED OBJECT INSTANCE DETECTION" by Travis Frink

Date of Award

2022

Degree Type

Thesis

Degree Name

Master of Science in Electrical Engineering (MSEE)

Department

Electrical Engineering

First Advisor

Resit Sendag

Abstract

Three alterations are investigated: The addition of a feature pyramid network to improve small object recognition, a loss weighting strategy dependent on object poses, and the addition of a transformer for feature comparisons.As a result increased performance was achieved for both the FPN and loss weighting alterations while the transformer alterations slightly underperformed the original model.

Creative Commons License

Creative Commons Attribution-Share Alike 4.0 License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.