Toward Fast Computation of Dense Image Correspondence on the GPU

PDF Version Also Available for Download.

Description

Large-scale video processing systems are needed to support human analysis of massive collections of image streams. Video, from both current small-format and future large-format camera systems, constitutes the single largest data source of the near future, dwarfing the output of all other data sources combined. A critical component to further advances in the processing and analysis of such video streams is the ability to register successive video frames into a common coordinate system at the pixel level. This capability enables further downstream processing, such as background/mover segmentation, 3D model extraction, and compression. We present here our recent work on computing ... continued below

Physical Description

PDF-file: 4 pages; size: 2.4 Mbytes

Creation Information

Duchaineau, M; Cohen, J & Vaidya, S August 13, 2007.

Context

This article is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by UNT Libraries Government Documents Department to Digital Library, a digital repository hosted by the UNT Libraries. More information about this article can be viewed below.

Who

People and organizations associated with either the creation of this article or its content.

Publisher

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this article. Follow the links below to find similar items on the Digital Library.

Description

Large-scale video processing systems are needed to support human analysis of massive collections of image streams. Video, from both current small-format and future large-format camera systems, constitutes the single largest data source of the near future, dwarfing the output of all other data sources combined. A critical component to further advances in the processing and analysis of such video streams is the ability to register successive video frames into a common coordinate system at the pixel level. This capability enables further downstream processing, such as background/mover segmentation, 3D model extraction, and compression. We present here our recent work on computing these correspondences. We employ coarse-to-fine hierarchical approach, matching pixels from the domain of a source image to the domain of a target image at successively higher resolutions. Our diamond-style image hierarchy, with total pixel counts increasing by only a factor of two at each level, improves the prediction quality as we advance from level to level, and reduces potential grid artifacts in the results. We demonstrate the quality our approach on real aerial city imagery. We find that registration accuracy is generally on the order of one quarter of a pixel. We also benchmark the fundamental processing kernels on the GPU to show the promise of the approach for real-time video processing applications.

Physical Description

PDF-file: 4 pages; size: 2.4 Mbytes

Source

  • Presented at: 2007 High Performance Embedded Computing (HPEC) Workshop, Lexington, MA, United States, Sep 18 - Sep 20, 2007

Language

Item Type

Identifier

Unique identifying numbers for this article in the Digital Library or other systems.

  • Report No.: UCRL-CONF-233816
  • Grant Number: W-7405-ENG-48
  • Office of Scientific & Technical Information Report Number: 924953
  • Archival Resource Key: ark:/67531/metadc900029

Collections

This article is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

What responsibilities do I have when using this article?

When

Dates and time periods associated with this article.

Creation Date

  • August 13, 2007

Added to The UNT Digital Library

  • Sept. 27, 2016, 1:39 a.m.

Description Last Updated

  • Dec. 9, 2016, midnight

Usage Statistics

When was this article last used?

Congratulations! It looks like you are the first person to view this item online.

Interact With This Article

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

Citations, Rights, Re-Use

Duchaineau, M; Cohen, J & Vaidya, S. Toward Fast Computation of Dense Image Correspondence on the GPU, article, August 13, 2007; Livermore, California. (digital.library.unt.edu/ark:/67531/metadc900029/: accessed September 20, 2017), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.