Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery
Automatic mapping and monitoring of agricultural landscapes using remotely sensed imagery has been an important research problem. This paper describes our work on developing automatic methods for the detection of target landscape features in very high spatial resolution images. The target objects of interest consist of linear strips of woody vegetation that include hedgerows and riparian vegetation that are important elements of the landscape ecology and biodiversity. The proposed framework exploits the spectral, textural, and shape properties of objects using hierarchical feature extraction and decision-making steps. First, a multifeature and multiscale strategy is used to be able to cover different characteristics of these objects in a wide range of landscapes. Discriminant functions trained on combinations of spectral and textural features are used to select the pixels that may belong to candidate objects. Then, a shape analysis step employs morphological top-hat transforms to locate the woody vegetation areas that fall within the width limits of an acceptable object, and a skeletonization and iterative least-squares fitting procedure quantifies the linearity of the objects using the uniformity of the estimated radii along the skeleton points. Extensive experiments using QuickBird imagery from three European Union member states show that the proposed algorithms provide good localization of the target objects in a wide range of landscapes with very different characteristics.
Main Authors: | , , |
---|---|
Format: | article biblioteca |
Language: | eng |
Subjects: | U30 - Méthodes de recherche, B10 - Géographie, K01 - Foresterie - Considérations générales, végétation, plante ligneuse, http://aims.fao.org/aos/agrovoc/c_8176, http://aims.fao.org/aos/agrovoc/c_26837, http://aims.fao.org/aos/agrovoc/c_3245, http://aims.fao.org/aos/agrovoc/c_33095, http://aims.fao.org/aos/agrovoc/c_2080, |
Online Access: | http://agritrop.cirad.fr/553126/ http://agritrop.cirad.fr/553126/1/document_553126.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-cirad-fr-553126 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-5531262024-01-28T17:59:54Z http://agritrop.cirad.fr/553126/ http://agritrop.cirad.fr/553126/ Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery. Aksoy S., Gökhan Akçay, Wassenaar Tom. 2010. IEEE Transactions on Geoscience and Remote Sensing, 48 (1) : 511-522.https://doi.org/10.1109/TGRS.2009.2027702 <https://doi.org/10.1109/TGRS.2009.2027702> Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery Aksoy, S. Gökhan Akçay, Wassenaar, Tom eng 2010 IEEE Transactions on Geoscience and Remote Sensing U30 - Méthodes de recherche B10 - Géographie K01 - Foresterie - Considérations générales végétation plante ligneuse http://aims.fao.org/aos/agrovoc/c_8176 http://aims.fao.org/aos/agrovoc/c_26837 Allemagne Tchéquie Chypre http://aims.fao.org/aos/agrovoc/c_3245 http://aims.fao.org/aos/agrovoc/c_33095 http://aims.fao.org/aos/agrovoc/c_2080 Automatic mapping and monitoring of agricultural landscapes using remotely sensed imagery has been an important research problem. This paper describes our work on developing automatic methods for the detection of target landscape features in very high spatial resolution images. The target objects of interest consist of linear strips of woody vegetation that include hedgerows and riparian vegetation that are important elements of the landscape ecology and biodiversity. The proposed framework exploits the spectral, textural, and shape properties of objects using hierarchical feature extraction and decision-making steps. First, a multifeature and multiscale strategy is used to be able to cover different characteristics of these objects in a wide range of landscapes. Discriminant functions trained on combinations of spectral and textural features are used to select the pixels that may belong to candidate objects. Then, a shape analysis step employs morphological top-hat transforms to locate the woody vegetation areas that fall within the width limits of an acceptable object, and a skeletonization and iterative least-squares fitting procedure quantifies the linearity of the objects using the uniformity of the estimated radii along the skeleton points. Extensive experiments using QuickBird imagery from three European Union member states show that the proposed algorithms provide good localization of the target objects in a wide range of landscapes with very different characteristics. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/publishedVersion http://agritrop.cirad.fr/553126/1/document_553126.pdf application/pdf Cirad license info:eu-repo/semantics/restrictedAccess https://agritrop.cirad.fr/mention_legale.html https://doi.org/10.1109/TGRS.2009.2027702 10.1109/TGRS.2009.2027702 info:eu-repo/semantics/altIdentifier/doi/10.1109/TGRS.2009.2027702 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.1109/TGRS.2009.2027702 |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
U30 - Méthodes de recherche B10 - Géographie K01 - Foresterie - Considérations générales végétation plante ligneuse http://aims.fao.org/aos/agrovoc/c_8176 http://aims.fao.org/aos/agrovoc/c_26837 http://aims.fao.org/aos/agrovoc/c_3245 http://aims.fao.org/aos/agrovoc/c_33095 http://aims.fao.org/aos/agrovoc/c_2080 U30 - Méthodes de recherche B10 - Géographie K01 - Foresterie - Considérations générales végétation plante ligneuse http://aims.fao.org/aos/agrovoc/c_8176 http://aims.fao.org/aos/agrovoc/c_26837 http://aims.fao.org/aos/agrovoc/c_3245 http://aims.fao.org/aos/agrovoc/c_33095 http://aims.fao.org/aos/agrovoc/c_2080 |
spellingShingle |
U30 - Méthodes de recherche B10 - Géographie K01 - Foresterie - Considérations générales végétation plante ligneuse http://aims.fao.org/aos/agrovoc/c_8176 http://aims.fao.org/aos/agrovoc/c_26837 http://aims.fao.org/aos/agrovoc/c_3245 http://aims.fao.org/aos/agrovoc/c_33095 http://aims.fao.org/aos/agrovoc/c_2080 U30 - Méthodes de recherche B10 - Géographie K01 - Foresterie - Considérations générales végétation plante ligneuse http://aims.fao.org/aos/agrovoc/c_8176 http://aims.fao.org/aos/agrovoc/c_26837 http://aims.fao.org/aos/agrovoc/c_3245 http://aims.fao.org/aos/agrovoc/c_33095 http://aims.fao.org/aos/agrovoc/c_2080 Aksoy, S. Gökhan Akçay, Wassenaar, Tom Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
description |
Automatic mapping and monitoring of agricultural landscapes using remotely sensed imagery has been an important research problem. This paper describes our work on developing automatic methods for the detection of target landscape features in very high spatial resolution images. The target objects of interest consist of linear strips of woody vegetation that include hedgerows and riparian vegetation that are important elements of the landscape ecology and biodiversity. The proposed framework exploits the spectral, textural, and shape properties of objects using hierarchical feature extraction and decision-making steps. First, a multifeature and multiscale strategy is used to be able to cover different characteristics of these objects in a wide range of landscapes. Discriminant functions trained on combinations of spectral and textural features are used to select the pixels that may belong to candidate objects. Then, a shape analysis step employs morphological top-hat transforms to locate the woody vegetation areas that fall within the width limits of an acceptable object, and a skeletonization and iterative least-squares fitting procedure quantifies the linearity of the objects using the uniformity of the estimated radii along the skeleton points. Extensive experiments using QuickBird imagery from three European Union member states show that the proposed algorithms provide good localization of the target objects in a wide range of landscapes with very different characteristics. |
format |
article |
topic_facet |
U30 - Méthodes de recherche B10 - Géographie K01 - Foresterie - Considérations générales végétation plante ligneuse http://aims.fao.org/aos/agrovoc/c_8176 http://aims.fao.org/aos/agrovoc/c_26837 http://aims.fao.org/aos/agrovoc/c_3245 http://aims.fao.org/aos/agrovoc/c_33095 http://aims.fao.org/aos/agrovoc/c_2080 |
author |
Aksoy, S. Gökhan Akçay, Wassenaar, Tom |
author_facet |
Aksoy, S. Gökhan Akçay, Wassenaar, Tom |
author_sort |
Aksoy, S. |
title |
Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
title_short |
Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
title_full |
Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
title_fullStr |
Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
title_full_unstemmed |
Automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
title_sort |
automatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imagery |
url |
http://agritrop.cirad.fr/553126/ http://agritrop.cirad.fr/553126/1/document_553126.pdf |
work_keys_str_mv |
AT aksoys automaticmappingoflinearwoodyvegetationfeaturesinagriculturallandscapesusingveryhighresolutionimagery AT gokhanakcay automaticmappingoflinearwoodyvegetationfeaturesinagriculturallandscapesusingveryhighresolutionimagery AT wassenaartom automaticmappingoflinearwoodyvegetationfeaturesinagriculturallandscapesusingveryhighresolutionimagery |
_version_ |
1792497474509733888 |