Automated Photogrammetry Using a Particle Filter

David Schug

AMSC663 Course Instructors: Professor C. David Levermore, Professor James Drake
Advisors: Professor Rama Chellappa, Professor Ankur Srivastava.

Abstract

Photogrammetry uses pictures to measure the position and orientation of objects with respect to each other or some specified origin. Manual tracking of necessary targets is labor intensive so automated tracking is imperitive. The particle filter provides a robust algorithm to meet automatic visual tracking and recognition needs from a single sensor in two dimensions. Extending the technology to multiple sensors will provide postion data in three dimensions.

Context

Motivating this project is the human desire to quickly visualize and understand the relationships of important objects. Whether human faces, automobiles, or weapons this project will give engineers and scientists a tool to aquire necessary data.

Updated 13 October 2005