An integrated multi-target tracking system for interacting target scenarios

Hongwei Mao, Glen P. Abousleman, Jennie Si

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In real-world target tracking scenarios, interactions among multiple moving targets can severely compromise the performance of the tracking system. Targets involved in interactions are typically closely-spaced and are often partially or entirely occluded by other objects. In these cases, valid target observations are unlikely to be available. To address this issue, we present an integrated multi-target tracking system. The data association method evaluates the overlap rates between newly detected objects (target observations) and already-tracked targets, and makes decisions pertaining to whether a target is interacting with other targets and whether it has a valid observation. Thus, the system is capable of recognizing target interactions and will reject invalid target observations. According to the association results, distinct strategies are adopted to update and manage the tracks of interacting versus well-isolated targets. Testing results on real-world airborne video sequences demonstrate the excellent performance of the proposed system for tracking targets with multiple target interactions. Moreover, the system operates in real time on an ordinary desktop computer.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume8713
DOIs
StatePublished - 2013
EventAirborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications X - Baltimore, MD, United States
Duration: May 1 2013May 2 2013

Other

OtherAirborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications X
CountryUnited States
CityBaltimore, MD
Period5/1/135/2/13

Fingerprint

Multi-target Tracking
Tracking System
Target tracking
Scenarios
Target
Personal computers
Target Tracking
Interaction
Testing
Valid
interactions
Data Association
Moving Target
Overlap
Update
Distinct

Keywords

  • Data association
  • Split and merged measurements
  • Target tracking
  • Track maintenance

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Mao, H., Abousleman, G. P., & Si, J. (2013). An integrated multi-target tracking system for interacting target scenarios. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 8713). [871314] https://doi.org/10.1117/12.2017661

An integrated multi-target tracking system for interacting target scenarios. / Mao, Hongwei; Abousleman, Glen P.; Si, Jennie.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8713 2013. 871314.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mao, H, Abousleman, GP & Si, J 2013, An integrated multi-target tracking system for interacting target scenarios. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 8713, 871314, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications X, Baltimore, MD, United States, 5/1/13. https://doi.org/10.1117/12.2017661
Mao H, Abousleman GP, Si J. An integrated multi-target tracking system for interacting target scenarios. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8713. 2013. 871314 https://doi.org/10.1117/12.2017661
Mao, Hongwei ; Abousleman, Glen P. ; Si, Jennie. / An integrated multi-target tracking system for interacting target scenarios. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8713 2013.
@inproceedings{3102117f47f54b7c8380c8567956aa8b,
title = "An integrated multi-target tracking system for interacting target scenarios",
abstract = "In real-world target tracking scenarios, interactions among multiple moving targets can severely compromise the performance of the tracking system. Targets involved in interactions are typically closely-spaced and are often partially or entirely occluded by other objects. In these cases, valid target observations are unlikely to be available. To address this issue, we present an integrated multi-target tracking system. The data association method evaluates the overlap rates between newly detected objects (target observations) and already-tracked targets, and makes decisions pertaining to whether a target is interacting with other targets and whether it has a valid observation. Thus, the system is capable of recognizing target interactions and will reject invalid target observations. According to the association results, distinct strategies are adopted to update and manage the tracks of interacting versus well-isolated targets. Testing results on real-world airborne video sequences demonstrate the excellent performance of the proposed system for tracking targets with multiple target interactions. Moreover, the system operates in real time on an ordinary desktop computer.",
keywords = "Data association, Split and merged measurements, Target tracking, Track maintenance",
author = "Hongwei Mao and Abousleman, {Glen P.} and Jennie Si",
year = "2013",
doi = "10.1117/12.2017661",
language = "English (US)",
isbn = "9780819495044",
volume = "8713",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - An integrated multi-target tracking system for interacting target scenarios

AU - Mao, Hongwei

AU - Abousleman, Glen P.

AU - Si, Jennie

PY - 2013

Y1 - 2013

N2 - In real-world target tracking scenarios, interactions among multiple moving targets can severely compromise the performance of the tracking system. Targets involved in interactions are typically closely-spaced and are often partially or entirely occluded by other objects. In these cases, valid target observations are unlikely to be available. To address this issue, we present an integrated multi-target tracking system. The data association method evaluates the overlap rates between newly detected objects (target observations) and already-tracked targets, and makes decisions pertaining to whether a target is interacting with other targets and whether it has a valid observation. Thus, the system is capable of recognizing target interactions and will reject invalid target observations. According to the association results, distinct strategies are adopted to update and manage the tracks of interacting versus well-isolated targets. Testing results on real-world airborne video sequences demonstrate the excellent performance of the proposed system for tracking targets with multiple target interactions. Moreover, the system operates in real time on an ordinary desktop computer.

AB - In real-world target tracking scenarios, interactions among multiple moving targets can severely compromise the performance of the tracking system. Targets involved in interactions are typically closely-spaced and are often partially or entirely occluded by other objects. In these cases, valid target observations are unlikely to be available. To address this issue, we present an integrated multi-target tracking system. The data association method evaluates the overlap rates between newly detected objects (target observations) and already-tracked targets, and makes decisions pertaining to whether a target is interacting with other targets and whether it has a valid observation. Thus, the system is capable of recognizing target interactions and will reject invalid target observations. According to the association results, distinct strategies are adopted to update and manage the tracks of interacting versus well-isolated targets. Testing results on real-world airborne video sequences demonstrate the excellent performance of the proposed system for tracking targets with multiple target interactions. Moreover, the system operates in real time on an ordinary desktop computer.

KW - Data association

KW - Split and merged measurements

KW - Target tracking

KW - Track maintenance

UR - http://www.scopus.com/inward/record.url?scp=84881069286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881069286&partnerID=8YFLogxK

U2 - 10.1117/12.2017661

DO - 10.1117/12.2017661

M3 - Conference contribution

AN - SCOPUS:84881069286

SN - 9780819495044

VL - 8713

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -