The Resource Relative depth estimation from single monocular images with deep convolutional network, by Alex Yang

Relative depth estimation from single monocular images with deep convolutional network, by Alex Yang

Label
Relative depth estimation from single monocular images with deep convolutional network
Title
Relative depth estimation from single monocular images with deep convolutional network
Statement of responsibility
by Alex Yang
Creator
Contributor
Author
Degree supervisor
Subject
Genre
Language
eng
Summary
Depth estimation from single monocular images is a theoretical challenge in computer vision as well as a computational challenge in practice. This thesis addresses the problem of depth estimation from single monocular images using a deep convolutional neural fields framework; which consists of convolutional feature extraction, superpixel dimensionality reduction, and depth inference. Data were collected using a stereo vision camera, which generated depth maps though triangulation that are paired with visual images. The visual image (input) and computed depth map (desired output) are used to train the model, which has achieved 83 percent test accuracy at the standard 25 percent tolerance. The problem has been formulated as depth regression for superpixels and our technique is superior to existing state-of-the-art approaches based on its demonstrated its generalization ability, high prediction accuracy, and real-time processing capability. We utilize the VGG-16 deep convolutional network as feature extractor and conditional random fields depth inference. We have leveraged a multi-phase training protocol that includes transfer learning and network fine-tuning lead to high performance accuracy. Our framework has a robust modular nature with ca- pability of replacing each component with different implementations for maximum extensibility. Additionally, our GPU-accelerated implementation of superpixel pooling has further facilitated this extensibility by allowing incorporation of feature tensors with exible shapes and has provided both space and time optimization. Based on our novel contributions and high-performance computing methodologies, the model achieves a minimal and optimized design. It is capable of operating at 30 fps; which is a critical step towards empowering real-world applications such as autonomous vehicle with passive relative depth perception using single camera vision-based obstacle avoidance, environment mapping, etc
Cataloging source
MUU
http://library.link/vocab/creatorName
Yang, Alex
Degree
M.S.
Dissertation note
Thesis
Dissertation year
2017.
Government publication
government publication of a state province territory dependency etc
Granting institution
University of Missouri--Columbia
Illustrations
illustrations
Index
no index present
Literary form
non fiction
Nature of contents
  • dictionaries
  • bibliography
  • theses
http://library.link/vocab/relatedWorkOrContributorName
Scott, Grant
Label
Relative depth estimation from single monocular images with deep convolutional network, by Alex Yang
Instantiates
Publication
Note
  • Field of study: Computer science
  • Dr. Grant Scott, Thesis Supervisor
Bibliography note
Includes bibliographical references (pages 61-65)
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Control code
1101434765
Extent
1 online resource (viii, 65 pages)
Form of item
online
Media category
computer
Media MARC source
rdamedia
Media type code
  • c
Other physical details
illustrations (chiefly color)
Specific material designation
remote
System control number
(OCoLC)1101434765
Label
Relative depth estimation from single monocular images with deep convolutional network, by Alex Yang
Publication
Note
  • Field of study: Computer science
  • Dr. Grant Scott, Thesis Supervisor
Bibliography note
Includes bibliographical references (pages 61-65)
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Control code
1101434765
Extent
1 online resource (viii, 65 pages)
Form of item
online
Media category
computer
Media MARC source
rdamedia
Media type code
  • c
Other physical details
illustrations (chiefly color)
Specific material designation
remote
System control number
(OCoLC)1101434765

Library Locations

  • Health Sciences LibraryBorrow it
    2411 Holmes St, Kansas City, Kansas City, MO, 64108, US
    39.083418 -94.575323
  • LaBudde Special CollectionsBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Leon E. Bloch Law LibraryBorrow it
    500 E. 52nd Street, Kansas City, MO, 64110, US
    39.032488 -94.581967
  • Marr Sound ArchivesBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Miller Nichols LibraryBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
Processing Feedback ...