GrenierDemersLabrecqueEtAl2005

Référence

Grenier, M., Demers, A.-M., Labrecque, S., Fournier, R.A., Drolet, B., Benoit, M. (2005) A classification method to map wetlands in Quebec for the Canadian Wetland Inventory using a top-down approach with object-oriented segmentation. In Proceedings of the 26th Canadian Symposium on Remote Sensing. Pages 481-482. (Scopus )

Résumé

Canadian Wetland Inventory (CWI) started in spring 2002 and was first aimed to develop a method to map 5 wetland classes stratification, based on the Canadian Wetland Classification System, with a minimal mapping unit of 1 hectare. The 5 wetlands classes for the CWI are: marsh, swamp, shallow water, fen, and bog. Satellite image types used for CWI are RADARSAT-1 and Landsat-ETM. The Landsat-ETM images are acquired, when possible, in summer at a time when vegetation exhibit high level of activity and Radarsat images must be acquired during spring flood, or during a period of high water in fall. The mapping method, developed by the Canadian Wildlife Service (CWS) Quebec region, applies spectral, spatial and texture classification of satellite images using a top-down approach (coarser to the finer spatial objects) with a segmentation algorithm. The classification is accomplish with the eCognition© software. The method was tested on 5 study sites: Radisson, lac St. Pierre, lac St. François (Appalachian), GrandePlée-Bleue and Isle Verte. Theses sites provide a wide range of different wetland classes in varied environment which helped test the mapping method before applying it to large areas. Following the top-down approach requires that spatial objects in the images be identified starting at the coarser level, and gradually to finer levels, according to the size of the objects of interest: wetlands, water bodies, mineral surfaces, forest, etc. Generally 3 segmentation levels are required: The coarse levels allow toidentify large spatial ensembles. For example, large wetlands, water bodies, mineral surfaces, and «Potential Wetlands» are typically identified at that level. The medium level is the refinement of the coarse level, primarily on «Potential Wetlands» class. This level also allows to identify medium size wetlands. Lastly, the fine level is the refinement of the medium level, composed exclusively of «Potential Wetlands - Medium» class. The smallest wetlands are identified at this level, but always keeping in mind the spatial objects must be larger than 1 ha to be compatible with the CWI minimum mapping unit. Hierarchical classification optimizes wetland identification and reduces multi-class confusion. Sets of rules are assigned to each class based on membership functions using spatial and spectral attributes such as mean, ratio, texture, shape, neighbourhood, etc. Misclassified objects are reassigned manually after the automated classification which requires approximately 15-20% of processing time. This time may be reduced with better contextual knowledge of landscape or with use of more specific membership functions. The spatial and temporal variability of wetland lead to a validation strategy using the 'best knowledge' approach instead of comparing the final classification with other map products or ground-based plots. 'Best knowledge' approach involves a qualitative confidence-building assessment where an expert interprets the original image enhanced, and when possible, with additional available datasets. For the Wetlands vs Uplands map accuracy, the visual evaluation of the cells by a qualified interpreter allows detection of wetlands greater than 1 ha in upland. For the thematic and spatial accuracy of wetland polygons, the visual evaluation of the selected polygons is done by an interpreter who validates the wetland type and the spatial limit of the polygon. The classification of satellite images using a top-down approach with a segmentation algorithm is adaptable and matches the CWI requirements for the Quebec region. The multi-level segmentation allows wetland identification at levels that best fit variable wetland sizes. The 5 wetland classes at a regional scale are well suited to thematic mapping using satellite remote sensing. RADARSAT-1 and Landsat-ETM images provide independent information, both helpful for wetland detection. The results demonstrate the efficiency of the proposed method leading to high accuracy map of wetlands in a wide range of environments.

Format EndNote

Vous pouvez importer cette référence dans EndNote.

Format BibTeX-CSV

Vous pouvez importer cette référence en format BibTeX-CSV.

Format BibTeX

Vous pouvez copier l'entrée BibTeX de cette référence ci-bas, ou l'importer directement dans un logiciel tel que JabRef .

@INPROCEEDINGS { GrenierDemersLabrecqueEtAl2005,
    AUTHOR = { Grenier, M. and Demers, A.-M. and Labrecque, S. and Fournier, R.A. and Drolet, B. and Benoit, M. },
    TITLE = { A classification method to map wetlands in Quebec for the Canadian Wetland Inventory using a top-down approach with object-oriented segmentation },
    BOOKTITLE = { Proceedings of the 26th Canadian Symposium on Remote Sensing },
    YEAR = { 2005 },
    PAGES = { 481--482 },
    ABSTRACT = { Canadian Wetland Inventory (CWI) started in spring 2002 and was first aimed to develop a method to map 5 wetland classes stratification, based on the Canadian Wetland Classification System, with a minimal mapping unit of 1 hectare. The 5 wetlands classes for the CWI are: marsh, swamp, shallow water, fen, and bog. Satellite image types used for CWI are RADARSAT-1 and Landsat-ETM. The Landsat-ETM images are acquired, when possible, in summer at a time when vegetation exhibit high level of activity and Radarsat images must be acquired during spring flood, or during a period of high water in fall. The mapping method, developed by the Canadian Wildlife Service (CWS) Quebec region, applies spectral, spatial and texture classification of satellite images using a top-down approach (coarser to the finer spatial objects) with a segmentation algorithm. The classification is accomplish with the eCognition© software. The method was tested on 5 study sites: Radisson, lac St. Pierre, lac St. François (Appalachian), GrandePlée-Bleue and Isle Verte. Theses sites provide a wide range of different wetland classes in varied environment which helped test the mapping method before applying it to large areas. Following the top-down approach requires that spatial objects in the images be identified starting at the coarser level, and gradually to finer levels, according to the size of the objects of interest: wetlands, water bodies, mineral surfaces, forest, etc. Generally 3 segmentation levels are required: The coarse levels allow toidentify large spatial ensembles. For example, large wetlands, water bodies, mineral surfaces, and «Potential Wetlands» are typically identified at that level. The medium level is the refinement of the coarse level, primarily on «Potential Wetlands» class. This level also allows to identify medium size wetlands. Lastly, the fine level is the refinement of the medium level, composed exclusively of «Potential Wetlands - Medium» class. The smallest wetlands are identified at this level, but always keeping in mind the spatial objects must be larger than 1 ha to be compatible with the CWI minimum mapping unit. Hierarchical classification optimizes wetland identification and reduces multi-class confusion. Sets of rules are assigned to each class based on membership functions using spatial and spectral attributes such as mean, ratio, texture, shape, neighbourhood, etc. Misclassified objects are reassigned manually after the automated classification which requires approximately 15-20% of processing time. This time may be reduced with better contextual knowledge of landscape or with use of more specific membership functions. The spatial and temporal variability of wetland lead to a validation strategy using the 'best knowledge' approach instead of comparing the final classification with other map products or ground-based plots. 'Best knowledge' approach involves a qualitative confidence-building assessment where an expert interprets the original image enhanced, and when possible, with additional available datasets. For the Wetlands vs Uplands map accuracy, the visual evaluation of the cells by a qualified interpreter allows detection of wetlands greater than 1 ha in upland. For the thematic and spatial accuracy of wetland polygons, the visual evaluation of the selected polygons is done by an interpreter who validates the wetland type and the spatial limit of the polygon. The classification of satellite images using a top-down approach with a segmentation algorithm is adaptable and matches the CWI requirements for the Quebec region. The multi-level segmentation allows wetland identification at levels that best fit variable wetland sizes. The 5 wetland classes at a regional scale are well suited to thematic mapping using satellite remote sensing. RADARSAT-1 and Landsat-ETM images provide independent information, both helpful for wetland detection. The results demonstrate the efficiency of the proposed method leading to high accuracy map of wetlands in a wide range of environments. },
    COMMENT = { Export Date: 10 February 2010 Source: Scopus },
    KEYWORDS = { Classification (of information), Computer software, Hierarchical systems, Image segmentation, Imaging techniques, Mapping, Satellites, Thermal stratification, Wetlands, Marsh, Mineral surfaces, Shallow water, Swamp, Maps },
    OWNER = { Luc },
    TIMESTAMP = { 2010.02.10 },
    URL = { http://www.scopus.com/inward/record.url?eid=2-s2.0-33745184653&partnerID=40&md5=afca3cc2c1049e0c12e22011478ad70f },
}

********************************************************** *************************** FRQNT ************************ **********************************************************

Un regroupement stratégique du

********************************************************** ***************** Facebook Twitter *********************** **********************************************************

Abonnez-vous à
l'Infolettre du CEF!

********************************************************** ***************** Pub - ABC CBA 2020 ****************** **********************************************************

31 mai au 4 juin 2020

********************************************************** ***************** Pub - Symphonies_Boreales ****************** **********************************************************

********************************************************** ***************** Boîte à trucs *************** **********************************************************

CEF-Référence
La référence vedette !

Jérémie Alluard (2016) Les statistiques au moments de la rédaction 

  • Ce document a pour but de guider les étudiants à intégrer de manière appropriée une analyse statistique dans leur rapport de recherche.

Voir les autres...