Outlier and target detection in aerial hyperspectral imagery: a comparison of traditional and percentage occupancy hit or miss transform techniques

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

Abstract

The use of aerial hyperspectral imagery for the purpose of remote sensing is a rapidly growing research area. Currently, targets are generally detected by looking for distinct spectral features of the objects under surveillance. For example, a camouflaged vehicle, deliberately designed to blend into background trees and grass in the visible spectrum, can be revealed using spectral features in the near-infrared spectrum. This work aims to develop improved target detection methods, using a two-stage approach, firstly by development of a physics-based atmospheric correction algorithm to convert radiance into reflectance hyperspectral image data and secondly by use of improved outlier detection techniques. In this paper the use of the Percentage Occupancy Hit or Miss Transform is explored to provide an automated method for target detection in aerial hyperspectral imagery.
LanguageEnglish
Title of host publicationProc. SPIE 9844, Automatic Target Recognition XXVI
Number of pages10
DOIs
Publication statusPublished - 12 May 2016
EventSPIE Defense + Security 2016 - Baltimore, United States
Duration: 17 Apr 201621 Apr 2016

Conference

ConferenceSPIE Defense + Security 2016
CountryUnited States
CityBaltimore
Period17/04/1621/04/16

Fingerprint

aerial photography
Target tracking
Antennas
atmospheric correction
Remote sensing
grasses
Physics
Mathematical transformations
surveillance
visible spectrum
Infrared radiation
radiance
remote sensing
vehicles
infrared spectra
reflectance
physics

Keywords

  • hyperspectral imaging (HSI)
  • remote sensing
  • Sequential Maximum Angle Convex Cone (SMACC)
  • hit or miss transform
  • Percentage Occupancy Hit or Miss Transform
  • outlier detection
  • target detection

Cite this

@inproceedings{62a03c1e47c2443da40a08997b2c1477,
title = "Outlier and target detection in aerial hyperspectral imagery: a comparison of traditional and percentage occupancy hit or miss transform techniques",
abstract = "The use of aerial hyperspectral imagery for the purpose of remote sensing is a rapidly growing research area. Currently, targets are generally detected by looking for distinct spectral features of the objects under surveillance. For example, a camouflaged vehicle, deliberately designed to blend into background trees and grass in the visible spectrum, can be revealed using spectral features in the near-infrared spectrum. This work aims to develop improved target detection methods, using a two-stage approach, firstly by development of a physics-based atmospheric correction algorithm to convert radiance into reflectance hyperspectral image data and secondly by use of improved outlier detection techniques. In this paper the use of the Percentage Occupancy Hit or Miss Transform is explored to provide an automated method for target detection in aerial hyperspectral imagery.",
keywords = "hyperspectral imaging (HSI), remote sensing, Sequential Maximum Angle Convex Cone (SMACC), hit or miss transform , Percentage Occupancy Hit or Miss Transform, outlier detection, target detection",
author = "Andrew Young and Stephen Marshall and Alison Gray",
note = "Andrew Young ; Stephen Marshall ; Alison Gray; Outlier and target detection in aerial hyperspectral imagery: a comparison of traditional and percentage occupancy hit or miss transform techniques. Proc. SPIE 9844, Automatic Target Recognition XXVI, 98440S (May 12, 2016); doi:10.1117/12.2213530. Copyright 2016 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.",
year = "2016",
month = "5",
day = "12",
doi = "10.1117/12.2213530",
language = "English",
booktitle = "Proc. SPIE 9844, Automatic Target Recognition XXVI",

}

Outlier and target detection in aerial hyperspectral imagery : a comparison of traditional and percentage occupancy hit or miss transform techniques. / Young, Andrew; Marshall, Stephen; Gray, Alison.

Proc. SPIE 9844, Automatic Target Recognition XXVI. 2016.

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

TY - GEN

T1 - Outlier and target detection in aerial hyperspectral imagery

T2 - a comparison of traditional and percentage occupancy hit or miss transform techniques

AU - Young, Andrew

AU - Marshall, Stephen

AU - Gray, Alison

N1 - Andrew Young ; Stephen Marshall ; Alison Gray; Outlier and target detection in aerial hyperspectral imagery: a comparison of traditional and percentage occupancy hit or miss transform techniques. Proc. SPIE 9844, Automatic Target Recognition XXVI, 98440S (May 12, 2016); doi:10.1117/12.2213530. Copyright 2016 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.

PY - 2016/5/12

Y1 - 2016/5/12

N2 - The use of aerial hyperspectral imagery for the purpose of remote sensing is a rapidly growing research area. Currently, targets are generally detected by looking for distinct spectral features of the objects under surveillance. For example, a camouflaged vehicle, deliberately designed to blend into background trees and grass in the visible spectrum, can be revealed using spectral features in the near-infrared spectrum. This work aims to develop improved target detection methods, using a two-stage approach, firstly by development of a physics-based atmospheric correction algorithm to convert radiance into reflectance hyperspectral image data and secondly by use of improved outlier detection techniques. In this paper the use of the Percentage Occupancy Hit or Miss Transform is explored to provide an automated method for target detection in aerial hyperspectral imagery.

AB - The use of aerial hyperspectral imagery for the purpose of remote sensing is a rapidly growing research area. Currently, targets are generally detected by looking for distinct spectral features of the objects under surveillance. For example, a camouflaged vehicle, deliberately designed to blend into background trees and grass in the visible spectrum, can be revealed using spectral features in the near-infrared spectrum. This work aims to develop improved target detection methods, using a two-stage approach, firstly by development of a physics-based atmospheric correction algorithm to convert radiance into reflectance hyperspectral image data and secondly by use of improved outlier detection techniques. In this paper the use of the Percentage Occupancy Hit or Miss Transform is explored to provide an automated method for target detection in aerial hyperspectral imagery.

KW - hyperspectral imaging (HSI)

KW - remote sensing

KW - Sequential Maximum Angle Convex Cone (SMACC)

KW - hit or miss transform

KW - Percentage Occupancy Hit or Miss Transform

KW - outlier detection

KW - target detection

UR - http://spie.org/conferences-and-exhibitions/defense--commercial-sensing

U2 - 10.1117/12.2213530

DO - 10.1117/12.2213530

M3 - Conference contribution book

BT - Proc. SPIE 9844, Automatic Target Recognition XXVI

ER -