Repository logo
Log In(current)
  1. Home
  2. Colleges & Schools
  3. Graduate School
  4. Masters Theses
  5. Visual tracking using correlation techniques : algorithms, analysis, and pipeline architecture implementation
Details

Visual tracking using correlation techniques : algorithms, analysis, and pipeline architecture implementation

Date Issued
May 1994
Author(s)
Eklund, Mark William
Advisor(s)
Mohan Trivedi
Additional Advisor(s)
Doanld W. B.
Permanent URI
https://trace.tennessee.edu/handle/20.500.14382/59255
Abstract

In this thesis, a correspondence based tracking algorithm was detailed. This tracking algorithm tracked a region of an image located on an object. It used corrospondence between the training region and the current region to locate the object in the current image. Since manipulations of the object could dramatically change the geometry of the training region, the training region was updated while the tracking algorithm ran. Six steps were takin in creating the tracking algorithm. These were to

1. Define the issues associated with tracking.

2. Examine seven different tracking algorithms and choose a correspondence based tracking algorithm.

3. Introduce four correspondence algorithms to be compared.

4. Compare these four algorithms for accuracy and speed.

5. Choose the Minimum Noise and Correlation Energy (MINACE) filter for correspondence.

6. Build and evaluate a system that uses this tracking algorithm.

The tracking algorithm was implemented on a VME rack equipped with a Datacube MV20 pipeline processor and a Motorola 68030 processor. A data update rate of 15hz was achieved.

 
Degree
Master of Science
Major
Electrical Engineering
File(s)
Thumbnail Image
Name

Thesis94.E48.pdf

Size

13.87 MB

Format

Adobe PDF

Checksum (MD5)

20ab2ce0da9a65a79664b3c3dabc4584


University Libraries

1015 Volunteer Boulevard
Knoxville, TN 37996
865-974-4351

Map & Directions
Donate to the Libraries
  • About
  • John C. Hodges Society
  • Speaking Volumes magazine
  • Outreach
  • Directory
  • Employment
  • Policies
  • Library Intranet
University of Tennessee power T logo

The University of Tennessee, Knoxville
Knoxville, Tennessee 37996
865-974-1000

Events
A-Z
Apply
Privacy
Map
Directory
Give to UT
Accessibility

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science