Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Convolutional Neural Network Optimization for Homography Estimation

DiMascio, Michelle Augustine
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1544214038882564

Abstract Details

2018, Master of Science (M.S.), University of Dayton, Electrical Engineering.
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.
Eric Balster (Advisor)
Yakov Diskin (Committee Member)
Tarek Taha (Committee Member)
39 p.
Computer Engineering; Electrical Engineering
Homography Estimation; Convolutional Neural Networks; Neural Networks; Image Registration; Deep Learning; Hyper-parameter Optimization

Recommended Citations

Citations

  • DiMascio, M. A. (2018). Convolutional Neural Network Optimization for Homography Estimation [Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1544214038882564

    APA Style (7th edition)

  • DiMascio, Michelle. Convolutional Neural Network Optimization for Homography Estimation. 2018. University of Dayton, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1544214038882564.

    MLA Style (8th edition)

  • DiMascio, Michelle. "Convolutional Neural Network Optimization for Homography Estimation." Master's thesis, University of Dayton, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1544214038882564

    Chicago Manual of Style (17th edition)

dayton1544214038882564
1,238
© 2018, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.