Convolutional Neural Network Optimization for Homography Estimation
Date of Award
M.S. in Electrical Engineering
Department of Electrical and Computer Engineering
Advisor: Eric Balster
This thesis proposes an optimized convolutional neural network architecture to improve homography estimation applications. The parameters and structure of the CNN including the number of convolutional filters, stride lengths, kernel size, learning parameters, etc are altered from previous implementations. Multiple modifications of the network are trained and evaluated until a final network yields a corner pixel error of 4.7 which is less than a network proposed in previous literature's.
Electrical Engineering, Computer Engineering, Homography Estimation, Convolutional Neural Networks, Neural Networks, Image Registration, Deep Learning, Hyper-parameter Optimization
Copyright 2018, author
DiMascio, Michelle Augustine, "Convolutional Neural Network Optimization for Homography Estimation" (2018). Graduate Theses and Dissertations. 6732.