Automatic Removal of Complex Shadows From Indoor Videos Metadata

Metadata describes a digital item, providing (if known) such information as creator, publisher, contents, size, relationship to other resources, and more. Metadata may also contain "preservation" components that help us to maintain the integrity of digital files over time.

Available Formats

Dublin Core: XML Dublin Core: JSON Dublin Core: Text Dublin Core: RDF/XML UNTL: XML Access METS: XML

Title

  • Main Title Automatic Removal of Complex Shadows From Indoor Videos

Creator

  • Author: Mohapatra, Deepankar
    Creator Type: Personal

Contributor

  • Chair: Yuan, Xiaohui
    Contributor Type: Personal
    Contributor Info: Major Professor
  • Committee Member: Fu, Song
    Contributor Type: Personal
  • Committee Member: Swigger, Kathleen M.
    Contributor Type: Personal

Publisher

  • Name: University of North Texas
    Place of Publication: Denton, Texas
    Additional Info: www.unt.edu

Date

  • Creation: 2015-08

Language

  • English

Description

  • Content Description: Shadows in indoor scenarios are usually characterized with multiple light sources that produce complex shadow patterns of a single object. Without removing shadow, the foreground object tends to be erroneously segmented. The inconsistent hue and intensity of shadows make automatic removal a challenging task. In this thesis, a dynamic thresholding and transfer learning-based method for removing shadows is proposed. The method suppresses light shadows with a dynamically computed threshold and removes dark shadows using an online learning strategy that is built upon a base classifier trained with manually annotated examples and refined with the automatically identified examples in the new videos. Experimental results demonstrate that despite variation of lighting conditions in videos our proposed method is able to adapt to the videos and remove shadows effectively. The sensitivity of shadow detection changes slightly with different confidence levels used in example selection for classifier retraining and high confidence level usually yields better performance with less retraining iterations.
  • Physical Description: viii, 53 pages : illustrations (some color)

Subject

  • Keyword: shadow removal
  • Keyword: background subtraction
  • Keyword: computer vision
  • Library of Congress Subject Headings: Video recordings -- Data processing.
  • Library of Congress Subject Headings: Motion pictures -- Editing -- Data processing.
  • Library of Congress Subject Headings: Shades and shadows.

Collection

  • Name: UNT Theses and Dissertations
    Code: UNTETD

Institution

  • Name: UNT Libraries
    Code: UNT

Rights

  • Rights Access: public
  • Rights Holder: Mohapatra, Deepankar
  • Rights License: copyright
  • Rights Statement: Copyright is held by the author, unless otherwise noted. All rights Reserved.

Resource Type

  • Thesis or Dissertation

Format

  • Text

Identifier

  • Archival Resource Key: ark:/67531/metadc804942

Degree

  • Academic Department: Department of Computer Science and Engineering
  • Degree Discipline: Computer Science
  • Degree Level: Master's
  • Degree Name: Master of Science
  • Degree Grantor: University of North Texas
  • Degree Publication Type: thesi

Note

Back to Top of Screen