A neural network-based technique for change detection of linear features and its application to a Mediterranean Region

Idan Feldberg; Nathan S. Netanyahu; Maxim Shoshany

A neural network-based technique for change detection of linear features and its application to a Mediterranean Region

Idan Feldberg, Nathan S. Netanyahu, Maxim Shoshany

Department of Computer Science

Bar-Ilan University

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

An Artificial Neural Network (ANN) for change detection from multi-temporal satellite images, which was reported in [6], has been further developed and tested, as part of a study of an area of high spatio-temporal heterogeneity along a climatic gradient between humid and arid climate regions. Four recognition classes, "positive change", "negative change", "false change", and "no change" were learned by a backpropagation feedforward ANN and then applied to Landsat images that were acquired over the study area in 1992 and 1997. A comparison with existing classification techniques indicates, in many instances, significantly improved performance due to the ANN developed.

Original language	English
Pages	1195-1197
Number of pages	3
State	Published - 2002
Event	2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002) - Toronto, Ont., Canada Duration: 24 Jun 2002 → 28 Jun 2002

Conference

Conference	2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002)
Country/Territory	Canada
City	Toronto, Ont.
Period	24/06/02 → 28/06/02

Cite this

@conference{1d2f54f99d5c419c8397a09b99c7b737,

title = "A neural network-based technique for change detection of linear features and its application to a Mediterranean Region",

abstract = "An Artificial Neural Network (ANN) for change detection from multi-temporal satellite images, which was reported in [6], has been further developed and tested, as part of a study of an area of high spatio-temporal heterogeneity along a climatic gradient between humid and arid climate regions. Four recognition classes, {"}positive change{"}, {"}negative change{"}, {"}false change{"}, and {"}no change{"} were learned by a backpropagation feedforward ANN and then applied to Landsat images that were acquired over the study area in 1992 and 1997. A comparison with existing classification techniques indicates, in many instances, significantly improved performance due to the ANN developed.",

author = "Idan Feldberg and Netanyahu, {Nathan S.} and Maxim Shoshany",

year = "2002",

language = "אנגלית",

pages = "1195--1197",

note = "2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002) ; Conference date: 24-06-2002 Through 28-06-2002",

}

A neural network-based technique for change detection of linear features and its application to a Mediterranean Region. / Feldberg, Idan; Netanyahu, Nathan S.; Shoshany, Maxim.
2002. 1195-1197 Paper presented at 2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002), Toronto, Ont., Canada.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - A neural network-based technique for change detection of linear features and its application to a Mediterranean Region

AU - Feldberg, Idan

AU - Netanyahu, Nathan S.

AU - Shoshany, Maxim

PY - 2002

Y1 - 2002

N2 - An Artificial Neural Network (ANN) for change detection from multi-temporal satellite images, which was reported in [6], has been further developed and tested, as part of a study of an area of high spatio-temporal heterogeneity along a climatic gradient between humid and arid climate regions. Four recognition classes, "positive change", "negative change", "false change", and "no change" were learned by a backpropagation feedforward ANN and then applied to Landsat images that were acquired over the study area in 1992 and 1997. A comparison with existing classification techniques indicates, in many instances, significantly improved performance due to the ANN developed.

AB - An Artificial Neural Network (ANN) for change detection from multi-temporal satellite images, which was reported in [6], has been further developed and tested, as part of a study of an area of high spatio-temporal heterogeneity along a climatic gradient between humid and arid climate regions. Four recognition classes, "positive change", "negative change", "false change", and "no change" were learned by a backpropagation feedforward ANN and then applied to Landsat images that were acquired over the study area in 1992 and 1997. A comparison with existing classification techniques indicates, in many instances, significantly improved performance due to the ANN developed.

UR - http://www.scopus.com/inward/record.url?scp=0036028353&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:0036028353

SP - 1195

EP - 1197

T2 - 2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002)

Y2 - 24 June 2002 through 28 June 2002

ER -

A neural network-based technique for change detection of linear features and its application to a Mediterranean Region

Abstract

Conference

Other files and links

Fingerprint

Cite this