A New Particle Filter Based Algorithm for Image Tracking

Abstract

We have developed a novel algorithm for tracking an object, such as the UAVs, in a sequence of images. The development of such an algorithm is motivated by the idea behind the particle filter and the concept of feedback from control theory. We will thus temporarily refer to this algorithm as a particle filter with feedback (PFF) algorithm for image tracking. We will briefly describe our algorithm and compare its performance with some existing algorithms. This comparison indicates that the proposed tracking algorithm drastically outperforms the existing methods both in terms of tracking accuracy, robustness and tracking speed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 27, 2008
Accession Number
ADA501159

Entities

People

  • Scott T. Acton
  • Xinmin Liu
  • Zongli Lin

Organizations

  • University of Virginia

Tags

Communities of Interest

  • Air Platforms
  • Biomedical
  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Agreements
  • Algorithms
  • Change Detection
  • Computations
  • Control Theory
  • Department Of Defense
  • Detection
  • Diagnostic Imaging
  • Engineering
  • Mathematics
  • Multitarget Tracking
  • Sequences
  • Sequential Monte Carlo Methods
  • Students
  • Target Tracking

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Distributed Systems and Data Platform Development
  • Human-Computer Interaction (HCI).