Automatic Target Detection in UAV Imagery Using Image Formation Conditions

Huibao Lin, Jennie Si, Glen P. Abousleman

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

Abstract

This paper presents an automatic target detection (ATD) system for use with unmanned aerial vehicle (UAV) imagery. Extracting reliable features under all conditions from a 2-D projection of a target in UAV imagery is a difficult problem. However, since the target size information is usually invariant to the image formation process, we propose an algorithm for automatically estimating the size of a 3-D target by using its 2-D projection. The size information in turn becomes an important feature to be used in a knowledge-driven, multi-resolution-based algorithm for automatically detecting targets in UAV imagery. Experimental results show that our proposed ATD algorithm provides outstanding detection performance, while significantly reducing the false alarm rate and the computational complexity.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsF.A. Sadjadi
Pages136-147
Number of pages12
Volume5094
DOIs
StatePublished - 2003
EventPROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Automatic Target Recognition XIII - Orlando, FL, United States
Duration: Apr 22 2003Apr 24 2003

Other

OtherPROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Automatic Target Recognition XIII
CountryUnited States
CityOrlando, FL
Period4/22/034/24/03

Fingerprint

pilotless aircraft
Unmanned aerial vehicles (UAV)
Target tracking
imagery
Image processing
Computational complexity
projection
false alarms
estimating

Keywords

  • Automatic target detection
  • Multi-scale image processing
  • Region-of-interest
  • Target size estimation
  • Unmanned aerial vehicle

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Lin, H., Si, J., & Abousleman, G. P. (2003). Automatic Target Detection in UAV Imagery Using Image Formation Conditions. In F. A. Sadjadi (Ed.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5094, pp. 136-147) https://doi.org/10.1117/12.487578

Automatic Target Detection in UAV Imagery Using Image Formation Conditions. / Lin, Huibao; Si, Jennie; Abousleman, Glen P.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / F.A. Sadjadi. Vol. 5094 2003. p. 136-147.

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

Lin, H, Si, J & Abousleman, GP 2003, Automatic Target Detection in UAV Imagery Using Image Formation Conditions. in FA Sadjadi (ed.), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5094, pp. 136-147, PROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Automatic Target Recognition XIII, Orlando, FL, United States, 4/22/03. https://doi.org/10.1117/12.487578
Lin H, Si J, Abousleman GP. Automatic Target Detection in UAV Imagery Using Image Formation Conditions. In Sadjadi FA, editor, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5094. 2003. p. 136-147 https://doi.org/10.1117/12.487578
Lin, Huibao ; Si, Jennie ; Abousleman, Glen P. / Automatic Target Detection in UAV Imagery Using Image Formation Conditions. Proceedings of SPIE - The International Society for Optical Engineering. editor / F.A. Sadjadi. Vol. 5094 2003. pp. 136-147
@inproceedings{8495b6d9992048a2be0348dfe692994f,
title = "Automatic Target Detection in UAV Imagery Using Image Formation Conditions",
abstract = "This paper presents an automatic target detection (ATD) system for use with unmanned aerial vehicle (UAV) imagery. Extracting reliable features under all conditions from a 2-D projection of a target in UAV imagery is a difficult problem. However, since the target size information is usually invariant to the image formation process, we propose an algorithm for automatically estimating the size of a 3-D target by using its 2-D projection. The size information in turn becomes an important feature to be used in a knowledge-driven, multi-resolution-based algorithm for automatically detecting targets in UAV imagery. Experimental results show that our proposed ATD algorithm provides outstanding detection performance, while significantly reducing the false alarm rate and the computational complexity.",
keywords = "Automatic target detection, Multi-scale image processing, Region-of-interest, Target size estimation, Unmanned aerial vehicle",
author = "Huibao Lin and Jennie Si and Abousleman, {Glen P.}",
year = "2003",
doi = "10.1117/12.487578",
language = "English (US)",
volume = "5094",
pages = "136--147",
editor = "F.A. Sadjadi",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Automatic Target Detection in UAV Imagery Using Image Formation Conditions

AU - Lin, Huibao

AU - Si, Jennie

AU - Abousleman, Glen P.

PY - 2003

Y1 - 2003

N2 - This paper presents an automatic target detection (ATD) system for use with unmanned aerial vehicle (UAV) imagery. Extracting reliable features under all conditions from a 2-D projection of a target in UAV imagery is a difficult problem. However, since the target size information is usually invariant to the image formation process, we propose an algorithm for automatically estimating the size of a 3-D target by using its 2-D projection. The size information in turn becomes an important feature to be used in a knowledge-driven, multi-resolution-based algorithm for automatically detecting targets in UAV imagery. Experimental results show that our proposed ATD algorithm provides outstanding detection performance, while significantly reducing the false alarm rate and the computational complexity.

AB - This paper presents an automatic target detection (ATD) system for use with unmanned aerial vehicle (UAV) imagery. Extracting reliable features under all conditions from a 2-D projection of a target in UAV imagery is a difficult problem. However, since the target size information is usually invariant to the image formation process, we propose an algorithm for automatically estimating the size of a 3-D target by using its 2-D projection. The size information in turn becomes an important feature to be used in a knowledge-driven, multi-resolution-based algorithm for automatically detecting targets in UAV imagery. Experimental results show that our proposed ATD algorithm provides outstanding detection performance, while significantly reducing the false alarm rate and the computational complexity.

KW - Automatic target detection

KW - Multi-scale image processing

KW - Region-of-interest

KW - Target size estimation

KW - Unmanned aerial vehicle

UR - http://www.scopus.com/inward/record.url?scp=0344514097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344514097&partnerID=8YFLogxK

U2 - 10.1117/12.487578

DO - 10.1117/12.487578

M3 - Conference contribution

AN - SCOPUS:0344514097

VL - 5094

SP - 136

EP - 147

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

A2 - Sadjadi, F.A.

ER -