A Particle Filtering Approach to Joint Passive Radar Tracking and Target Classification

Abstract

In this thesis, we present a recursive Bayesian solution to the problem of joint tracking and classification for ground-based air surveillance. In our system, we specifically allow for complications due to multiple targets, false alarms, and missed detections. Most importantly, though, we utilize the full benefit of a joint approach by implementing our tracker using an aerodynamically valid flight model that requires aircraft-specific coefficients such as the wing area, minimum drag, and vehicle mass. Of course, these coefficients are provided to our tracker by our classifier. The key feature that bridges the gap between tracking and classification is radar cross section (RCS), which we include in our measurement vector. By modeling the true deterministic relationship that exists between RCS and target aspect, we are able to gain both valuable class information and an estimate of target orientation. However, the lack of a closed-form relationship between RCS and target aspect prevents us from using the Kalman filter or any of its variants. Instead, we rely upon a sequential Monte Carlo-based approach known as particle filtering. In addition to allowing us to include RCS as a component in our measurement vector, the particle filter also simplifies the implementation of our nonlinear non-Gaussian flight model. Thus, we believe that we are the first to provide a joint tracking/classification framework that realizes the full potential of such an approach. Our joint formulation consists of three key developments: (1) an aerodynamically valid flight model that relies upon aircraft-specific coefficients such as the wing area and the minimum value of drag, (2) an electromagnetically correct model for RCS that yields information pertaining to both class identity and target orientation, and (3) a particle filter-based implementation that takes into account realistic difficulties caused by multiple targets, false alarms, and missed detections.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2002
Accession Number
ADA526763

Entities

People

  • Shawn M. Herman

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Air Platforms
  • Sensors

DTIC Thesaurus Topics

  • Aircrafts
  • Bayesian Networks
  • Commercial Aircraft
  • Computational Complexity
  • Computational Science
  • Data Association
  • Databases
  • Detection
  • Filtration
  • Gaussian Distributions
  • Kalman Filters
  • Mathematical Filters
  • Monte Carlo Method
  • Passive Radar
  • Radar
  • Random Variables
  • Three Dimensional

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms