Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


Elwarfalli final dissertation__ final format approved LW 11-02-2023.pdf (11 MB)

Digital Accessibility Report

File List


Acrobat Accessibility Report.html (8.13 KB)

ETD Abstract Container

Abstract Header

A Convolutional Neural Network for Motion-Based Multiframe Super-Resolution Using Fusion of Interpolated Frames

Elwarfalli, Hamed
http://orcid.org/0009-0008-0658-3549
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1702401591513453

Abstract Details

2023, Doctor of Philosophy (Ph.D.), University of Dayton, Electrical Engineering.
We present two novel multiframe image super-resolution (SR) algorithms that employ convolutional neural networks (CNNs) to generate high-resolution (HR) images from mul- tiple low-resolution (LR) input frames. The first algorithm, named Fusion of Interpolated Frames Network (FIFNET), utilizes motion-based multiframe SR by fusing multiple input frames in a single CNN based on Random and Fixed shifts. The second algorithm, called the Exponential weighted Fusion of Interpolated Frames Network (EWF-FIFNET), presents two variations, Externally Exponential Weighted Fusion-FIFNET (EEWF-FIFNET) and Inter- nally Exponential Weighted Fusion-FIFNET (IEWF-FIFNET) based on affine motion. A custom layer called the Exponential Weighted Fusion (EWF) layer is developed to combine input frames using a technique inspired by the fusion interpolation frame SR framework within the IEWF-FIFNET model. The EWF-FIFNET network utilizes a modified Residual Channel Attention Network architecture with residual in residual (RIR) structures. The proposed algorithms are trained and tested using a realistic observation camera model that incorporates optical and sensor degradation. Affine motion is also incorporated to address a challenging degradation problem. The experimental results show that the proposed algorithms outperform the existing state-of-the-art methods using both simulated and real camera data. It is noteworthy that the real data is not artificially downsampled or degraded, making the proposed algorithms a promising solution for practical applications. This research contributes significantly to the field of multiframe image SR, particularly in motion-based and exponentially weighted fusion approaches using CNNs.
Russell Hardie, Ph.D. (Advisor)
Youssef Raffoul, Ph.D. (Committee Member)
John Loomis, Ph.D. (Committee Member)
Eric Balster, Ph.D. (Committee Member)
76 p.
Computer Engineering; Computer Science; Engineering
Multiframe super-resolution; convolutional neural network; fusion of interpolated frames; image restoration; subpixel registration.

Recommended Citations

Citations

  • Elwarfalli, H. (2023). A Convolutional Neural Network for Motion-Based Multiframe Super-Resolution Using Fusion of Interpolated Frames [Doctoral dissertation, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1702401591513453

    APA Style (7th edition)

  • Elwarfalli, Hamed. A Convolutional Neural Network for Motion-Based Multiframe Super-Resolution Using Fusion of Interpolated Frames . 2023. University of Dayton, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1702401591513453.

    MLA Style (8th edition)

  • Elwarfalli, Hamed. "A Convolutional Neural Network for Motion-Based Multiframe Super-Resolution Using Fusion of Interpolated Frames ." Doctoral dissertation, University of Dayton, 2023. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1702401591513453

    Chicago Manual of Style (17th edition)

dayton1702401591513453
20
© 2023, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.