Skip to Main Content
 

Global Search Box

 
 
 
 

Files

ETD Abstract Container

Abstract Header

Depth Estimation Methodology for Modern Digital Photography

Abstract Details

2019, PhD, University of Cincinnati, Engineering and Applied Science: Electrical Engineering.
In the modern world, electronic devices with graphical imaging capability, such as digital cameras, projectors, mobile phones, and et cetera, are taking important roles to support modern life. In order for these devices to work properly and take the pictures people want, focusing mechanism, especially autofocus mechanism, is of pivotal importance. This involves obtaining three-dimension information from the scene being captured. To acquire three-dimensional information, the most apparent way is by capturing stereoscopic images with multiple lenses. However, the requirement of multiple lenses can sometimes become an obstacle for implementation, especially for modern digital photographic devices, for instance, digital cameras and camcorders. Most of them are designed to work with a single optical lens. This situation became the motivation for creating algorithms to cooperate with one lens only, and depth-from-defocus (DFD) is one of them. Depth-from-defocus (DFD) is a widely used three-dimensional reconstruction technique. It has certain practical advantages over other three-dimensional image processing techniques. It works perfectly fine with only one lens, and it does not require direct interaction with the scene. With the increasing appearance of high resolution, large aperture lens and high spec camera in modern digital photography, the occurrence of DFD is increasing rapidly as well. In this dissertation research, three approaches for estimating depth information using DFD are designed and presented. They used multiple images as the input to provide sufficient information for depth estimation, and focused on different aspects of the problem, such as depth accuracy, spatial resolution, and applicability of the algorithm. The first approach aimed at creating a depth map which can accurately register the depth of objects. In order to achieve this, multiple images of the same scene will be used to provide sufficient information to the algorithm. The depth map from the first approach can be used as the gold standard for other depth estimation methods, but it will suffer from its low spatial resolution. This will cause problems when estimating the depth at object boundary locations. Therefore the second approach provided a method to create depth maps which have the same resolution as the input images. Both first and second approaches utilized classical image processing process. Meanwhile, the third approach integrated the idea of neural network and deep learning into DFD algorithm. We created a new database containing about 20,000 images of seven patterns at different depth, and used them to estimate target depth. A modified VGGNet has been used as the structure of our convolutional neural network (CNN). Our experiment showed promising results comparing to other CNN applications.
William Wee, Ph.D. (Committee Chair)
Raj Bhatnagar, Ph.D. (Committee Member)
Chia Han, Ph.D. (Committee Member)
Anca Ralescu, Ph.D. (Committee Member)
Xuefu Zhou, Ph.D. (Committee Member)
118 p.

Recommended Citations

Citations

  • Sun, Y. (2019). Depth Estimation Methodology for Modern Digital Photography [Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549

    APA Style (7th edition)

  • Sun, Yi. Depth Estimation Methodology for Modern Digital Photography. 2019. University of Cincinnati, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549.

    MLA Style (8th edition)

  • Sun, Yi. "Depth Estimation Methodology for Modern Digital Photography." Doctoral dissertation, University of Cincinnati, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563527854489549

    Chicago Manual of Style (17th edition)