Tracking on Intensity-Modulated Data Streams

Abstract

The theoretical framework of probabilistic multi-hypothesis tracking is used to derive an algorithm for tracking one or more targets moving against a noisy background in an intensity-modulated, nonstationary data stream. The resulting multi-target tracking algorithm utilizes all the data available to a sensor display, and it completely avoids the current widespread practice of thresholding sensor data to generate point measurements that are subsequently fed to a tracker. The fundamental premise of the report is that tracking losses due to sensor data thresholding can be eliminated if the entire sensor output data set is utilized by the tracking algorithm.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2000
Accession Number
ADA377255

Entities

People

  • Roy L. Streit
  • Walter R. Lane

Organizations

  • Naval Undersea Warfare Center

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Bayes Theorem
  • Bayesian Networks
  • Cell Count
  • Computational Complexity
  • Computational Science
  • Data Sets
  • Estimators
  • Filters
  • Intensity
  • Mathematical Filters
  • Measurement
  • Multiple Hypothesis Tracking
  • Multitarget Tracking
  • Probability
  • Random Variables
  • Target Tracking

Readers

  • Approximation Theory.
  • Sensor Fusion and Tracking Systems.