Change Detection in Overhead Imagery Using Neural Networks

Get BibTex-formatted data

Download

PDF

Author

Christopher Clifton

Tech report number

CERIAS TR 2003-45

Entry type

article

Abstract

Identifying interesting changes from a sequence of overhead imageryâ€”as opposed to clutter, lighting/seasonal changes, etc.â€”has been a problem for some time. Recent advances in data mining have greatly increased the size of datasets that can be attacked with pattern discovery methods. This paper presents a technique for using predictive modeling to identify unusual changes in images. Neural networks are trained to predict â€œbeforeâ€ and â€œafterâ€ pixel values for a sequence of images. These networks are then used to predict expected values for the same images used in training. Substantial differences between the expected and actual values represent an unusual change. Results are presented on both multispectral and panchromatic imagery.

Download

PDF

Date

2003 – 03

URL

http://www.springerlink.com/content/q3860w21331k7l77/

Address

Dordrecht, The Netherlands

Journal

International Journal of Applied Intelligence

Key alpha

Clifton

Number

Pages

215-234

Publisher

Kluwer Academic Publishers

Volume

Publication Date

2003-03-01

BibTex-formatted data

To refer to this entry, you may select and copy the text below and paste it into your BibTex document. Note that the text may not contain all macros that BibTex supports.

@Article{ Clifton,
	title = "Change Detection in Overhead Imagery Using Neural Networks",
	author = "Christopher Clifton",
	year = "2003",
	month = "03",
	address = "Dordrecht, The Netherlands",
	journal = "International Journal of Applied Intelligence",
	number = "2",
	pages = "215-234",
	publisher = "Kluwer Academic Publishers",
	volume = "18",
	abstract = "Identifying interesting changes from a sequence of overhead imageryâ€”as opposed to clutter, lighting/seasonal changes, etc.â€”has been a problem for some time. Recent advances in data mining have greatly increased the size of datasets that can be attacked with pattern discovery methods. This paper presents a technique for using predictive modeling to identify unusual changes in images. Neural networks are trained to predict â€œbeforeâ€ and â€œafterâ€ pixel values for a sequence of images. These networks are then used to predict expected values for the same images used in training. Substantial differences between the expected and actual values represent an unusual change. Results are presented on both multispectral and panchromatic imagery. ",
	url = "http://www.springerlink.com/content/q3860w21331k7l77/",
}