SOME NEURAL COMPUTING APPROACHES TO TARGET TRACKING

PDF

Authors
  1. Maksym, J.N.
Corporate Authors
Defence Research Establishment Atlantic, Dartmouth NS (CAN)
Abstract
Multiple targets, false detections, and manoeuvres present difficulties in the application of tracking and data association algorithms. The discussion examines potential applications of neural networks in target tracking and data association problems. While neural computing has proved useful for many pattern recognition and control applications, it is not yet clear how and where neural networks should be used in systems for tracking targets. Preliminary work on the application of neural networks as adjuncts to more conventional Kalman filter tracking systems will be discussed. This paper examines the possible use of neural networks applied to model selection in a multiple model approach to tracking manoeuvring targets, as well as a neural network approach to measurment-to-track data association.
Report Number
DREA-TC-93-305-VOL-1-P-27 — @Conference Paper; CONTAINED IN 93-02664
Date of publication
01 Feb 1993
Number of Pages
24 (p27-50)
DSTKIM No
93-02662
CANDIS No
131299
Format(s):
Microfiche filmed at DSIS;Originator's fiche received by DSIS;Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: