Flying target detection and recognition by feature fusion

Levente Kovács, Andrea Kovács, Ákos Utasi, T. Szirányi

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We present a near-real-time visual-processing approach for automatic airborne target detection and classification. Detection is based on fast and robust background modeling and shape extraction, while recognition of target classes is based on shape and texture-fused querying on a-priori built real datasets. The presented approach can be used in defense and surveillance scenarios where passive detection capabilities are preferred (or required) over a secured area or protected zone.

Original languageEnglish
Article number117002
JournalOptical Engineering
Volume51
Issue number11
DOIs
Publication statusPublished - Nov 2012

Fingerprint

Target tracking
Fusion reactions
Textures
fusion
flight
Processing
surveillance
textures

Keywords

  • Classification
  • Object segmentation
  • Target detection

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

Flying target detection and recognition by feature fusion. / Kovács, Levente; Kovács, Andrea; Utasi, Ákos; Szirányi, T.

In: Optical Engineering, Vol. 51, No. 11, 117002, 11.2012.

Research output: Contribution to journalArticle

Kovács, Levente ; Kovács, Andrea ; Utasi, Ákos ; Szirányi, T. / Flying target detection and recognition by feature fusion. In: Optical Engineering. 2012 ; Vol. 51, No. 11.
@article{28d515701771403191b5bcd07e5bf1e7,
title = "Flying target detection and recognition by feature fusion",
abstract = "We present a near-real-time visual-processing approach for automatic airborne target detection and classification. Detection is based on fast and robust background modeling and shape extraction, while recognition of target classes is based on shape and texture-fused querying on a-priori built real datasets. The presented approach can be used in defense and surveillance scenarios where passive detection capabilities are preferred (or required) over a secured area or protected zone.",
keywords = "Classification, Object segmentation, Target detection",
author = "Levente Kov{\'a}cs and Andrea Kov{\'a}cs and {\'A}kos Utasi and T. Szir{\'a}nyi",
year = "2012",
month = "11",
doi = "10.1117/1.OE.51.11.117002",
language = "English",
volume = "51",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "11",

}

TY - JOUR

T1 - Flying target detection and recognition by feature fusion

AU - Kovács, Levente

AU - Kovács, Andrea

AU - Utasi, Ákos

AU - Szirányi, T.

PY - 2012/11

Y1 - 2012/11

N2 - We present a near-real-time visual-processing approach for automatic airborne target detection and classification. Detection is based on fast and robust background modeling and shape extraction, while recognition of target classes is based on shape and texture-fused querying on a-priori built real datasets. The presented approach can be used in defense and surveillance scenarios where passive detection capabilities are preferred (or required) over a secured area or protected zone.

AB - We present a near-real-time visual-processing approach for automatic airborne target detection and classification. Detection is based on fast and robust background modeling and shape extraction, while recognition of target classes is based on shape and texture-fused querying on a-priori built real datasets. The presented approach can be used in defense and surveillance scenarios where passive detection capabilities are preferred (or required) over a secured area or protected zone.

KW - Classification

KW - Object segmentation

KW - Target detection

UR - http://www.scopus.com/inward/record.url?scp=84890840866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890840866&partnerID=8YFLogxK

U2 - 10.1117/1.OE.51.11.117002

DO - 10.1117/1.OE.51.11.117002

M3 - Article

AN - SCOPUS:84890840866

VL - 51

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 11

M1 - 117002

ER -