Tracking multiple targets with self-organizing distributed ground sensors

Richard Brooks, David Friedlander, John Koch, Shashi Phoha

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

This paper describes a fully distributed approach to target tracking that we have implemented and tested in a military setting. The approach uses local sharing of robust statistics that summarize local events. Local collaboration extracts detection information such as time, velocity, position, heading and target type from the summary statistics. Groups of nodes used for local collaboration are determined dynamically at run time. Local collaboration information is compared with a list of tracks in the immediate vicinity. A variation on the nearest-neighbor algorithm associates detections to tracks. This paper extends our previous work by analyzing the ability of our distributed tracker to track multiple targets in a simulated environment. Results from simulations and field tests of the approach are provided.

Original languageEnglish (US)
Pages (from-to)874-884
Number of pages11
JournalJournal of Parallel and Distributed Computing
Volume64
Issue number7
DOIs
StatePublished - Jan 1 2004

Fingerprint

Multiple Target Tracking
Self-organizing
Statistics
Sensor
Sensors
Target tracking
Robust Statistics
Target
Target Tracking
Military
Nearest Neighbor
Sharing
Vertex of a graph
Collaboration
Simulation

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Brooks, Richard ; Friedlander, David ; Koch, John ; Phoha, Shashi. / Tracking multiple targets with self-organizing distributed ground sensors. In: Journal of Parallel and Distributed Computing. 2004 ; Vol. 64, No. 7. pp. 874-884.
@article{4363dd8442644d6caf74bce8d66792f8,
title = "Tracking multiple targets with self-organizing distributed ground sensors",
abstract = "This paper describes a fully distributed approach to target tracking that we have implemented and tested in a military setting. The approach uses local sharing of robust statistics that summarize local events. Local collaboration extracts detection information such as time, velocity, position, heading and target type from the summary statistics. Groups of nodes used for local collaboration are determined dynamically at run time. Local collaboration information is compared with a list of tracks in the immediate vicinity. A variation on the nearest-neighbor algorithm associates detections to tracks. This paper extends our previous work by analyzing the ability of our distributed tracker to track multiple targets in a simulated environment. Results from simulations and field tests of the approach are provided.",
author = "Richard Brooks and David Friedlander and John Koch and Shashi Phoha",
year = "2004",
month = "1",
day = "1",
doi = "10.1016/j.jpdc.2003.12.005",
language = "English (US)",
volume = "64",
pages = "874--884",
journal = "Journal of Parallel and Distributed Computing",
issn = "0743-7315",
publisher = "Academic Press Inc.",
number = "7",

}

Tracking multiple targets with self-organizing distributed ground sensors. / Brooks, Richard; Friedlander, David; Koch, John; Phoha, Shashi.

In: Journal of Parallel and Distributed Computing, Vol. 64, No. 7, 01.01.2004, p. 874-884.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Tracking multiple targets with self-organizing distributed ground sensors

AU - Brooks, Richard

AU - Friedlander, David

AU - Koch, John

AU - Phoha, Shashi

PY - 2004/1/1

Y1 - 2004/1/1

N2 - This paper describes a fully distributed approach to target tracking that we have implemented and tested in a military setting. The approach uses local sharing of robust statistics that summarize local events. Local collaboration extracts detection information such as time, velocity, position, heading and target type from the summary statistics. Groups of nodes used for local collaboration are determined dynamically at run time. Local collaboration information is compared with a list of tracks in the immediate vicinity. A variation on the nearest-neighbor algorithm associates detections to tracks. This paper extends our previous work by analyzing the ability of our distributed tracker to track multiple targets in a simulated environment. Results from simulations and field tests of the approach are provided.

AB - This paper describes a fully distributed approach to target tracking that we have implemented and tested in a military setting. The approach uses local sharing of robust statistics that summarize local events. Local collaboration extracts detection information such as time, velocity, position, heading and target type from the summary statistics. Groups of nodes used for local collaboration are determined dynamically at run time. Local collaboration information is compared with a list of tracks in the immediate vicinity. A variation on the nearest-neighbor algorithm associates detections to tracks. This paper extends our previous work by analyzing the ability of our distributed tracker to track multiple targets in a simulated environment. Results from simulations and field tests of the approach are provided.

UR - http://www.scopus.com/inward/record.url?scp=10844235700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10844235700&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2003.12.005

DO - 10.1016/j.jpdc.2003.12.005

M3 - Article

VL - 64

SP - 874

EP - 884

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

SN - 0743-7315

IS - 7

ER -